id
stringlengths 17
22
| multi_turn
bool 1
class | functions
stringlengths 288
2.32k
| tools
stringlengths 324
2.35k
| missed_functions
stringclasses 1
value | initial_config
stringclasses 1
value | involved_classes
sequencelengths 0
0
| turns
stringlengths 2.98k
5.8k
| language
stringclasses 1
value | test_category
stringclasses 1
value | subset
stringclasses 1
value | ground_truth
stringlengths 30
1.33k
|
---|---|---|---|---|---|---|---|---|---|---|---|
live_simple_200-116-8 | false | [{"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}] | [{"type": "function", "function": {"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Weather_1_GetWeather', 'description': 'Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['city'], 'properties': {'city': {'type': 'string', 'description': 'The name of the city for which weather information is requested.'}, 'date': {'type': 'string', 'description': \"The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.\", 'default': '2019-03-01'}}}}]\n"}, {"role": "user", "content": "I want to check the weather condition in Fremont on March 1st 2023. "}]] | Python | live_simple | live_simple | [{"Weather_1_GetWeather": {"city": ["Fremont"], "date": ["2023-03-01"]}}] |
live_simple_201-116-9 | false | [{"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}] | [{"type": "function", "function": {"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Weather_1_GetWeather', 'description': 'Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['city'], 'properties': {'city': {'type': 'string', 'description': 'The name of the city for which weather information is requested.'}, 'date': {'type': 'string', 'description': \"The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.\", 'default': '2019-03-01'}}}}]\n"}, {"role": "user", "content": "I'm planning a picnic on the 4th march 2023 and would like to know the forecast for Campbell on that day. Could you provide that information?"}]] | Python | live_simple | live_simple | [{"Weather_1_GetWeather": {"city": ["Campbell"], "date": ["2023-03-04"]}}] |
live_simple_202-116-10 | false | [{"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}] | [{"type": "function", "function": {"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Weather_1_GetWeather', 'description': 'Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['city'], 'properties': {'city': {'type': 'string', 'description': 'The name of the city for which weather information is requested.'}, 'date': {'type': 'string', 'description': \"The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.\", 'default': '2019-03-01'}}}}]\n"}, {"role": "user", "content": "Can you provide me with the weather forecast for Foster City for April 25th 2023?"}]] | Python | live_simple | live_simple | [{"Weather_1_GetWeather": {"city": ["Foster City"], "date": ["2023-04-25"]}}] |
live_simple_203-116-11 | false | [{"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}] | [{"type": "function", "function": {"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Weather_1_GetWeather', 'description': 'Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['city'], 'properties': {'city': {'type': 'string', 'description': 'The name of the city for which weather information is requested.'}, 'date': {'type': 'string', 'description': \"The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.\", 'default': '2019-03-01'}}}}]\n"}, {"role": "user", "content": "Hi, could you help me check the weather in Washington, DC for March 1st, 2023 please?"}]] | Python | live_simple | live_simple | [{"Weather_1_GetWeather": {"city": ["Washington"], "date": ["2023-03-01"]}}] |
live_simple_204-116-12 | false | [{"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}] | [{"type": "function", "function": {"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Weather_1_GetWeather', 'description': 'Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['city'], 'properties': {'city': {'type': 'string', 'description': 'The name of the city for which weather information is requested.'}, 'date': {'type': 'string', 'description': \"The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.\", 'default': '2019-03-01'}}}}]\n"}, {"role": "user", "content": "Could you tell me what the weather will be like in Rutherford, NJ, on April 22nd 2023?"}]] | Python | live_simple | live_simple | [{"Weather_1_GetWeather": {"city": ["Rutherford"], "date": ["2023-04-22"]}}] |
live_simple_205-116-13 | false | [{"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}] | [{"type": "function", "function": {"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Weather_1_GetWeather', 'description': 'Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['city'], 'properties': {'city': {'type': 'string', 'description': 'The name of the city for which weather information is requested.'}, 'date': {'type': 'string', 'description': \"The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.\", 'default': '2019-03-01'}}}}]\n"}, {"role": "user", "content": "What's the weather forecast for Berkeley on the upcoming Saturday? Today is Tuesday April 25th 2023"}]] | Python | live_simple | live_simple | [{"Weather_1_GetWeather": {"city": ["Berkeley"], "date": ["2023-04-27"]}}] |
live_simple_206-116-14 | false | [{"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}] | [{"type": "function", "function": {"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Weather_1_GetWeather', 'description': 'Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['city'], 'properties': {'city': {'type': 'string', 'description': 'The name of the city for which weather information is requested.'}, 'date': {'type': 'string', 'description': \"The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.\", 'default': '2019-03-01'}}}}]\n"}, {"role": "user", "content": "Hi, could you tell me the forecast for London, England on the 5th of march 2023?"}]] | Python | live_simple | live_simple | [{"Weather_1_GetWeather": {"city": ["London"], "date": ["2023-03-05"]}}] |
live_simple_207-116-15 | false | [{"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}] | [{"type": "function", "function": {"name": "Weather_1_GetWeather", "description": "Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["city"], "properties": {"city": {"type": "string", "description": "The name of the city for which weather information is requested."}, "date": {"type": "string", "description": "The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.", "default": "2019-03-01"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Weather_1_GetWeather', 'description': 'Retrieves the weather forecast for a specified city on a particular date. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['city'], 'properties': {'city': {'type': 'string', 'description': 'The name of the city for which weather information is requested.'}, 'date': {'type': 'string', 'description': \"The date for which weather information is requested, in the format of 'YYYY-MM-DD'. If not provided, the current date is used.\", 'default': '2019-03-01'}}}}]\n"}, {"role": "user", "content": "Can you tell me what the weather will be like in Sacramento on April 22nd 2023?"}]] | Python | live_simple | live_simple | [{"Weather_1_GetWeather": {"city": ["Sacramento"], "date": ["2023-04-22"]}}] |
live_simple_208-117-0 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I want to find a good film to watch with Duane Whitaker and I want something directed by Quentin Tarantino."}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Quentin Tarantino"], "genre": ["", "dontcare"], "cast": ["Duane Whitaker"]}}] |
live_simple_209-117-1 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I wish to see the movie which is directed by David Leitch and acted by Lori Pelenise Tuisano."}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["David Leitch"], "genre": ["", "dontcare"], "cast": ["Lori Pelenise Tuisano"]}}] |
live_simple_210-117-2 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "My friend and I want to go see a movie but we can't find one we like. We really want to see a Drama."}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["", "dontcare"], "genre": ["Drama"], "cast": ["", "dontcare"]}}] |
live_simple_211-117-3 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user or genre is not specified by user Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres.", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user or genre is not specified by user Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres.", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user or genre is not specified by user Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres.\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I would like to choose a movie to watch. Can you help me find a movie in the Comic genre with James Corden in it?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["", "dontcare"], "genre": ["Comedy"], "cast": ["James Corden"]}}] |
live_simple_212-117-4 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I'm in the mood for a good laugh. Find a comedy movie directed by Edgar Wright?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Edgar Wright"], "genre": ["Comedy"], "cast": ["", "dontcare"]}}] |
live_simple_213-117-5 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "Find me a list of Offbeat genre movies directed by Tim Burton?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Tim Burton"], "genre": ["Offbeat"], "cast": ["", "dontcare"]}}] |
live_simple_214-117-6 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "It's suppose to be raining all day so I'm cooped up in the house and bored. Can you help find me a movie to watch, preferably one that is classified as a Comic and directed by Nitesh Tiwari?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Nitesh Tiwari"], "genre": ["Comedy", "Comedy-drama"], "cast": ["", "dontcare"]}}] |
live_simple_215-117-7 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I'm looking for a movie to watch tonight, preferably something in the Fantasy genre. Any suggestions?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["", "dontcare"], "genre": ["Fantasy"], "cast": ["", "dontcare"]}}] |
live_simple_216-117-8 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "Find me action movies that have David Leitch as the director and include Alex King in the cast?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["David Leitch"], "genre": ["Action"], "cast": ["Alex King"]}}] |
live_simple_217-117-9 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "Let me enjoy movie directed by Nitesh Tiwari, is there any one?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Nitesh Tiwari"], "genre": ["", "dontcare"], "cast": ["", "dontcare"]}}] |
live_simple_218-117-10 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I'm at home alone and it is awfully quiet, so it's the perfect time to sit back and watch a movie. Can you find me a movie with Michaela Watkins starring in it and preferably directed by Paul Downs Colaizzo?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Paul Downs Colaizzo"], "genre": ["", "dontcare"], "cast": ["Michaela Watkins"]}}] |
live_simple_219-117-11 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I want to watch a McKinley Belcher III movie. I want something directed by Simon Curtis. It should be a drama."}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Simon Curtis"], "genre": ["Drama"], "cast": ["McKinley Belcher III"]}}] |
live_simple_220-117-12 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "Can you find me a thriller movie directed by Alexander Mackendrick?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Alexander Mackendrick"], "genre": ["Thriller"], "cast": ["", "dontcare"]}}] |
live_simple_221-117-13 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres. Use 'dontcare' if the genre is not a specific search criterion or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres. Use 'dontcare' if the genre is not a specific search criterion or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres. Use 'dontcare' if the genre is not a specific search criterion or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "Can you find me a nice movie directed by James Gray to watch?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["James Gray"], "genre": ["", "dontcare"], "cast": ["", "dontcare"]}}] |
live_simple_222-117-14 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I like to watch a movie. will you find me a movie which has sterling K. Brown as a actor and it should be directed by Thurop Van Orman"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Thurop Van Orman"], "genre": ["", "dontcare"], "cast": ["Sterling K. Brown"]}}] |
live_simple_223-117-15 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I would like to find a movie to watch in the Imaginative fiction genre, as I have started to watch a lot of fantasy-type movies lately, you know!!!!!!"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["", "dontcare"], "genre": ["Fantasy"], "cast": ["", "dontcare"]}}] |
live_simple_224-117-16 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "Could you suggest some Offbeat genre movies directed by Tim Burton with Johnny Depp in the cast?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Tim Burton"], "genre": ["Offbeat"], "cast": ["Johnny Depp"]}}] |
live_simple_225-117-17 | false | [{"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}] | [{"type": "function", "function": {"name": "Movies_3_FindMovies", "description": "Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {"directed_by": {"type": "string", "description": "Director of the movie. Use 'dontcare' if the director is not a specific search criterion.", "default": "dontcare"}, "genre": {"type": "string", "description": "Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user", "enum": ["Offbeat", "Fantasy", "World", "Mystery", "Thriller", "Comedy", "Comedy-drama", "Horror", "Animation", "Sci-fi", "Cult", "Drama", "Anime", "Family", "Action", "dontcare"], "default": "dontcare"}, "cast": {"type": "string", "description": "Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.", "default": "dontcare"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'Movies_3_FindMovies', 'description': 'Retrieves a list of movies based on the director, genre, and cast specified by the user. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {'directed_by': {'type': 'string', 'description': \"Director of the movie. Use 'dontcare' if the director is not a specific search criterion.\", 'default': 'dontcare'}, 'genre': {'type': 'string', 'description': \"Genre of the movie. Use 'dontcare' to include all genres or genre is not specified by user\", 'enum': ['Offbeat', 'Fantasy', 'World', 'Mystery', 'Thriller', 'Comedy', 'Comedy-drama', 'Horror', 'Animation', 'Sci-fi', 'Cult', 'Drama', 'Anime', 'Family', 'Action', 'dontcare'], 'default': 'dontcare'}, 'cast': {'type': 'string', 'description': \"Names of leading actors or actresses in the movie. Use 'dontcare' if the cast is not a specific search criterion.\", 'default': 'dontcare'}}}}]\n"}, {"role": "user", "content": "I have some leisure time so that i could watch a movie. Will you find me a movie directed by Kirill Mikhanovsky and find something like Comedy-drama genre?"}]] | Python | live_simple | live_simple | [{"Movies_3_FindMovies": {"directed_by": ["Kirill Mikhanovsky"], "genre": ["Comedy-drama"], "cast": ["", "dontcare"]}}] |
live_simple_226-118-0 | false | [{"name": "text_to_speech.convert", "description": "Converts input text into spoken audio, providing the resulting audio in a specified format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["text"], "properties": {"text": {"type": "string", "description": "The text to be converted to speech."}, "language": {"type": "string", "description": "The language of the input text, use default if nothing specified", "enum": ["en-US", "es-ES", "de-DE", "fr-FR", "it-IT"], "default": "en-US"}, "gender": {"type": "string", "description": "The gender of the voice used for the text-to-speech conversion, use default if nothing specified", "enum": ["male", "female"], "default": "female"}, "format": {"type": "string", "description": "The audio format of the resulting spoken text, use default if nothing specified", "enum": ["mp3", "wav", "ogg"], "default": "mp3"}, "speed": {"type": "float", "description": "The speed of the speech, represented as a float where 1.0 is the normal speed.", "default": 1.0}}}}] | [{"type": "function", "function": {"name": "text_to_speech_convert", "description": "Converts input text into spoken audio, providing the resulting audio in a specified format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["text"], "properties": {"text": {"type": "string", "description": "The text to be converted to speech."}, "language": {"type": "string", "description": "The language of the input text, use default if nothing specified", "enum": ["en-US", "es-ES", "de-DE", "fr-FR", "it-IT"], "default": "en-US"}, "gender": {"type": "string", "description": "The gender of the voice used for the text-to-speech conversion, use default if nothing specified", "enum": ["male", "female"], "default": "female"}, "format": {"type": "string", "description": "The audio format of the resulting spoken text, use default if nothing specified", "enum": ["mp3", "wav", "ogg"], "default": "mp3"}, "speed": {"type": "number", "description": "The speed of the speech, represented as a float where 1.0 is the normal speed. This is a float type value.", "default": 1.0, "format": "float"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'text_to_speech.convert', 'description': 'Converts input text into spoken audio, providing the resulting audio in a specified format. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['text'], 'properties': {'text': {'type': 'string', 'description': 'The text to be converted to speech.'}, 'language': {'type': 'string', 'description': 'The language of the input text, use default if nothing specified', 'enum': ['en-US', 'es-ES', 'de-DE', 'fr-FR', 'it-IT'], 'default': 'en-US'}, 'gender': {'type': 'string', 'description': 'The gender of the voice used for the text-to-speech conversion, use default if nothing specified', 'enum': ['male', 'female'], 'default': 'female'}, 'format': {'type': 'string', 'description': 'The audio format of the resulting spoken text, use default if nothing specified', 'enum': ['mp3', 'wav', 'ogg'], 'default': 'mp3'}, 'speed': {'type': 'float', 'description': 'The speed of the speech, represented as a float where 1.0 is the normal speed.', 'default': 1.0}}}}]\n"}, {"role": "user", "content": "Convert the phrase 'I am a pretty girl' into spoken audio in Spanish with a female voice?"}]] | Python | live_simple | live_simple | [{"text_to_speech.convert": {"text": ["I am a pretty girl", "Soy una chica bonita"], "language": ["es-ES"], "gender": ["", "female"], "format": ["", "mp3"], "speed": ["", 1.0]}}] |
live_simple_227-118-1 | false | [{"name": "text_to_speech.convert", "description": "Converts input text into spoken audio, providing the resulting audio in a specified format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["text"], "properties": {"text": {"type": "string", "description": "The text to be converted to speech."}, "language": {"type": "string", "description": "The language to convert the input text to, use default if nothing specified", "enum": ["en-US", "es-ES", "de-DE", "fr-FR", "it-IT", "zh-CN"], "default": "en-US"}, "gender": {"type": "string", "description": "The gender of the voice used for the text-to-speech conversion, use default if nothing specified", "enum": ["male", "female"], "default": "female"}, "format": {"type": "string", "description": "The audio format of the resulting spoken text, use default if nothing specified", "enum": ["mp3", "wav", "ogg"], "default": "mp3"}, "speed": {"type": "float", "description": "The speed of the speech, represented as a float where 1.0 is the normal speed.", "default": 1.0}}}}] | [{"type": "function", "function": {"name": "text_to_speech_convert", "description": "Converts input text into spoken audio, providing the resulting audio in a specified format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["text"], "properties": {"text": {"type": "string", "description": "The text to be converted to speech."}, "language": {"type": "string", "description": "The language to convert the input text to, use default if nothing specified", "enum": ["en-US", "es-ES", "de-DE", "fr-FR", "it-IT", "zh-CN"], "default": "en-US"}, "gender": {"type": "string", "description": "The gender of the voice used for the text-to-speech conversion, use default if nothing specified", "enum": ["male", "female"], "default": "female"}, "format": {"type": "string", "description": "The audio format of the resulting spoken text, use default if nothing specified", "enum": ["mp3", "wav", "ogg"], "default": "mp3"}, "speed": {"type": "number", "description": "The speed of the speech, represented as a float where 1.0 is the normal speed. This is a float type value.", "default": 1.0, "format": "float"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'text_to_speech.convert', 'description': 'Converts input text into spoken audio, providing the resulting audio in a specified format. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['text'], 'properties': {'text': {'type': 'string', 'description': 'The text to be converted to speech.'}, 'language': {'type': 'string', 'description': 'The language to convert the input text to, use default if nothing specified', 'enum': ['en-US', 'es-ES', 'de-DE', 'fr-FR', 'it-IT', 'zh-CN'], 'default': 'en-US'}, 'gender': {'type': 'string', 'description': 'The gender of the voice used for the text-to-speech conversion, use default if nothing specified', 'enum': ['male', 'female'], 'default': 'female'}, 'format': {'type': 'string', 'description': 'The audio format of the resulting spoken text, use default if nothing specified', 'enum': ['mp3', 'wav', 'ogg'], 'default': 'mp3'}, 'speed': {'type': 'float', 'description': 'The speed of the speech, represented as a float where 1.0 is the normal speed.', 'default': 1.0}}}}]\n"}, {"role": "user", "content": "Listen to the phrase '\u6211\u7231\u5b66\u4e60' in a male voice and in Chinese, and could I get the audio in WAV format, please?"}]] | Python | live_simple | live_simple | [{"text_to_speech.convert": {"text": ["\u6211\u7231\u5b66\u4e60"], "language": ["zh-CN"], "gender": ["male"], "format": ["wav"], "speed": ["", 1.0]}}] |
live_simple_228-119-0 | false | [{"name": "text_to_speech.convert", "description": "Converts a given text string into spoken words in an audio format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["text"], "properties": {"text": {"type": "string", "description": "The text content to be converted into speech."}, "language": {"type": "string", "description": "The language in which the text is written, use default if nothing specified", "enum": ["en-US", "es-ES", "de-DE", "fr-FR", "it-IT"], "default": "en-US"}, "gender": {"type": "string", "description": "The gender of the voice used for the text-to-speech conversion, use default if nothing specified", "enum": ["male", "female"], "default": "female"}, "speed": {"type": "float", "description": "The speed at which the speech is narrated, ranging from 0.5 (slow) to 2.0 (fast), use default if nothing specified", "default": 1.0}}}}] | [{"type": "function", "function": {"name": "text_to_speech_convert", "description": "Converts a given text string into spoken words in an audio format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["text"], "properties": {"text": {"type": "string", "description": "The text content to be converted into speech."}, "language": {"type": "string", "description": "The language in which the text is written, use default if nothing specified", "enum": ["en-US", "es-ES", "de-DE", "fr-FR", "it-IT"], "default": "en-US"}, "gender": {"type": "string", "description": "The gender of the voice used for the text-to-speech conversion, use default if nothing specified", "enum": ["male", "female"], "default": "female"}, "speed": {"type": "number", "description": "The speed at which the speech is narrated, ranging from 0.5 (slow) to 2.0 (fast), use default if nothing specified This is a float type value.", "default": 1.0, "format": "float"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'text_to_speech.convert', 'description': 'Converts a given text string into spoken words in an audio format. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['text'], 'properties': {'text': {'type': 'string', 'description': 'The text content to be converted into speech.'}, 'language': {'type': 'string', 'description': 'The language in which the text is written, use default if nothing specified', 'enum': ['en-US', 'es-ES', 'de-DE', 'fr-FR', 'it-IT'], 'default': 'en-US'}, 'gender': {'type': 'string', 'description': 'The gender of the voice used for the text-to-speech conversion, use default if nothing specified', 'enum': ['male', 'female'], 'default': 'female'}, 'speed': {'type': 'float', 'description': 'The speed at which the speech is narrated, ranging from 0.5 (slow) to 2.0 (fast), use default if nothing specified', 'default': 1.0}}}}]\n"}, {"role": "user", "content": "Convert it to audio format: I am a pretty girl"}]] | Python | live_simple | live_simple | [{"text_to_speech.convert": {"text": ["I am a pretty girl"], "language": ["", "en-US"], "gender": ["", "female"], "speed": ["", 1.0]}}] |
live_simple_229-120-0 | false | [{"name": "requests.get", "description": "Retrieve a list of Business Unit (BU) products from the specified API endpoint. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["anchor"], "properties": {"anchor": {"type": "string", "description": "Specifies the subset of BU products to retrieve, either all available products or only those associated with the user.", "enum": ["all", "user"]}}}}] | [{"type": "function", "function": {"name": "requests_get", "description": "Retrieve a list of Business Unit (BU) products from the specified API endpoint. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["anchor"], "properties": {"anchor": {"type": "string", "description": "Specifies the subset of BU products to retrieve, either all available products or only those associated with the user.", "enum": ["all", "user"]}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'requests.get', 'description': 'Retrieve a list of Business Unit (BU) products from the specified API endpoint. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['anchor'], 'properties': {'anchor': {'type': 'string', 'description': 'Specifies the subset of BU products to retrieve, either all available products or only those associated with the user.', 'enum': ['all', 'user']}}}}]\n"}, {"role": "user", "content": "Retrieve the list of Business Unit products that are associated with me?"}]] | Python | live_simple | live_simple | [{"requests.get": {"anchor": ["user"]}}] |
live_simple_230-121-0 | false | [{"name": "play_song", "description": "Initiates playback of a specified song through the Spotify API. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["song_id"], "properties": {"song_id": {"type": "string", "description": "The unique identifier for the song to be played."}, "artist": {"type": "string", "description": "The name of the artist performing the song.", "default": null}, "quality": {"type": "string", "description": "The streaming quality preference.", "enum": ["low", "medium", "high"], "default": "medium"}, "device_id": {"type": "string", "description": "The identifier for the device on which the song will be played. If not specified, the default playback device is used.", "default": null}}}}] | [{"type": "function", "function": {"name": "play_song", "description": "Initiates playback of a specified song through the Spotify API. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["song_id"], "properties": {"song_id": {"type": "string", "description": "The unique identifier for the song to be played."}, "artist": {"type": "string", "description": "The name of the artist performing the song.", "default": null}, "quality": {"type": "string", "description": "The streaming quality preference.", "enum": ["low", "medium", "high"], "default": "medium"}, "device_id": {"type": "string", "description": "The identifier for the device on which the song will be played. If not specified, the default playback device is used.", "default": null}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'play_song', 'description': 'Initiates playback of a specified song through the Spotify API. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['song_id'], 'properties': {'song_id': {'type': 'string', 'description': 'The unique identifier for the song to be played.'}, 'artist': {'type': 'string', 'description': 'The name of the artist performing the song.', 'default': None}, 'quality': {'type': 'string', 'description': 'The streaming quality preference.', 'enum': ['low', 'medium', 'high'], 'default': 'medium'}, 'device_id': {'type': 'string', 'description': 'The identifier for the device on which the song will be played. If not specified, the default playback device is used.', 'default': None}}}}]\n"}, {"role": "user", "content": "Play high quality Roar by Katy Perry. The song_id is wjeiruhuq_roar."}]] | Python | live_simple | live_simple | [{"play_song": {"song_id": ["wjeiruhuq_roar"], "artist": ["Katy Perry"], "quality": ["high"], "device_id": ["", null]}}] |
live_simple_231-122-0 | false | [{"name": "reschedule_event", "description": "Reschedule an event to a new date or time, specified in ISO-8601 format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["event_identifier", "new_datetime"], "properties": {"event_identifier": {"type": "string", "description": "The unique identifier of the event to be rescheduled."}, "new_datetime": {"type": "string", "description": "The new date and time for the event in ISO-8601 format, such as '2023-04-15T13:45:00Z'."}}}}] | [{"type": "function", "function": {"name": "reschedule_event", "description": "Reschedule an event to a new date or time, specified in ISO-8601 format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["event_identifier", "new_datetime"], "properties": {"event_identifier": {"type": "string", "description": "The unique identifier of the event to be rescheduled."}, "new_datetime": {"type": "string", "description": "The new date and time for the event in ISO-8601 format, such as '2023-04-15T13:45:00Z'."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'reschedule_event', 'description': 'Reschedule an event to a new date or time, specified in ISO-8601 format. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['event_identifier', 'new_datetime'], 'properties': {'event_identifier': {'type': 'string', 'description': 'The unique identifier of the event to be rescheduled.'}, 'new_datetime': {'type': 'string', 'description': \"The new date and time for the event in ISO-8601 format, such as '2023-04-15T13:45:00Z'.\"}}}}]\n"}, {"role": "user", "content": "Can you move my next gym session, which is event number 456123, to next Thursday at 4:30 PM? Today is monday 2022-10-20"}]] | Python | live_simple | live_simple | [{"reschedule_event": {"event_identifier": ["456123"], "new_datetime": ["2022-10-30T16:30:00Z"]}}] |
live_simple_232-122-1 | false | [{"name": "reschedule_event", "description": "Reschedule an event to a new date or time, specified in ISO-8601 format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["event_identifier", "new_datetime"], "properties": {"event_identifier": {"type": "string", "description": "The unique identifier of the event to be rescheduled."}, "new_datetime": {"type": "string", "description": "The new date and time for the event in ISO-8601 format, such as '2023-04-15T13:45:00Z'."}}}}] | [{"type": "function", "function": {"name": "reschedule_event", "description": "Reschedule an event to a new date or time, specified in ISO-8601 format. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["event_identifier", "new_datetime"], "properties": {"event_identifier": {"type": "string", "description": "The unique identifier of the event to be rescheduled."}, "new_datetime": {"type": "string", "description": "The new date and time for the event in ISO-8601 format, such as '2023-04-15T13:45:00Z'."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'reschedule_event', 'description': 'Reschedule an event to a new date or time, specified in ISO-8601 format. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['event_identifier', 'new_datetime'], 'properties': {'event_identifier': {'type': 'string', 'description': 'The unique identifier of the event to be rescheduled.'}, 'new_datetime': {'type': 'string', 'description': \"The new date and time for the event in ISO-8601 format, such as '2023-04-15T13:45:00Z'.\"}}}}]\n"}, {"role": "user", "content": "I need to change the date for Oscar's medicine appointment to this coming Friday. The event identifier is 'med123'. What's the best way to move it to the 15th of April 2021 at 1:45 pm, UTC?"}]] | Python | live_simple | live_simple | [{"reschedule_event": {"event_identifier": ["med123"], "new_datetime": ["2021-04-15T13:45:00Z"]}}] |
live_simple_233-123-0 | false | [{"name": "book_flight", "description": "Books a flight based on the provided departure location and time. Optionally, a return time can be specified for round-trip bookings. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["departure_location", "departure_time"], "properties": {"departure_location": {"type": "string", "description": "The departure location in the format of 'City, State (abbr)' or 'City, Country', such as 'Los Angeles, CA', 'Paris, France', or 'New York, NY'."}, "departure_time": {"type": "string", "description": "The departure time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location."}, "return_time": {"type": "string", "description": "The return time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location. If not specified, a one-way ticket is booked.", "default": null}}}}] | [{"type": "function", "function": {"name": "book_flight", "description": "Books a flight based on the provided departure location and time. Optionally, a return time can be specified for round-trip bookings. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["departure_location", "departure_time"], "properties": {"departure_location": {"type": "string", "description": "The departure location in the format of 'City, State (abbr)' or 'City, Country', such as 'Los Angeles, CA', 'Paris, France', or 'New York, NY'."}, "departure_time": {"type": "string", "description": "The departure time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location."}, "return_time": {"type": "string", "description": "The return time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location. If not specified, a one-way ticket is booked.", "default": null}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'book_flight', 'description': 'Books a flight based on the provided departure location and time. Optionally, a return time can be specified for round-trip bookings. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['departure_location', 'departure_time'], 'properties': {'departure_location': {'type': 'string', 'description': \"The departure location in the format of 'City, State (abbr)' or 'City, Country', such as 'Los Angeles, CA', 'Paris, France', or 'New York, NY'.\"}, 'departure_time': {'type': 'string', 'description': \"The departure time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location.\"}, 'return_time': {'type': 'string', 'description': \"The return time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location. If not specified, a one-way ticket is booked.\", 'default': None}}}}]\n"}, {"role": "user", "content": "Can you book a flight for me departing from Paris, France, on the 12th of March 2023 at 3 in the afternoon?"}]] | Python | live_simple | live_simple | [{"book_flight": {"departure_location": ["Paris, France"], "departure_time": ["12/03/2023 15:00"], "return_time": ["", null]}}] |
live_simple_234-123-1 | false | [{"name": "book_flight", "description": "Books a flight based on the provided departure location and time. Optionally, a return time can be specified for round-trip bookings. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["departure_location", "departure_time"], "properties": {"departure_location": {"type": "string", "description": "The departure location in the format of 'City (abbr), State', such as 'Los Angeles, CA' or 'New York, NY'."}, "departure_time": {"type": "string", "description": "The departure time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location."}, "return_time": {"type": "string", "description": "The return time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location. If not specified, a one-way ticket is booked.", "default": null}}}}] | [{"type": "function", "function": {"name": "book_flight", "description": "Books a flight based on the provided departure location and time. Optionally, a return time can be specified for round-trip bookings. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["departure_location", "departure_time"], "properties": {"departure_location": {"type": "string", "description": "The departure location in the format of 'City (abbr), State', such as 'Los Angeles, CA' or 'New York, NY'."}, "departure_time": {"type": "string", "description": "The departure time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location."}, "return_time": {"type": "string", "description": "The return time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location. If not specified, a one-way ticket is booked.", "default": null}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'book_flight', 'description': 'Books a flight based on the provided departure location and time. Optionally, a return time can be specified for round-trip bookings. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['departure_location', 'departure_time'], 'properties': {'departure_location': {'type': 'string', 'description': \"The departure location in the format of 'City (abbr), State', such as 'Los Angeles, CA' or 'New York, NY'.\"}, 'departure_time': {'type': 'string', 'description': \"The departure time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location.\"}, 'return_time': {'type': 'string', 'description': \"The return time in the format of 'dd/mm/yyyy HH:MM', representing the local time of the departure location. If not specified, a one-way ticket is booked.\", 'default': None}}}}]\n"}, {"role": "user", "content": "Can you arrange a flight for me from New York, NY to Paris with a departure on the 20th of June 2022 at 5 in the afternoon?"}]] | Python | live_simple | live_simple | [{"book_flight": {"departure_location": ["New York, NY"], "departure_time": ["20/06/2022 17:00"], "return_time": ["", null]}}] |
live_simple_235-124-0 | false | [{"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a provided query and plays the selected track Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song, including track and artist information, in the format 'track:SongName artist:ArtistName', such as 'track:Doxy artist:Miles Davis'."}, "shuffle": {"type": "boolean", "description": "Indicates whether to play the songs in shuffle mode, use default if not specified", "default": false}, "volume": {"type": "integer", "description": "The volume level to set when playing the song, expressed as a percentage from 0 to 100m, use default if not specified", "default": 50}}}}] | [{"type": "function", "function": {"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a provided query and plays the selected track Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song, including track and artist information, in the format 'track:SongName artist:ArtistName', such as 'track:Doxy artist:Miles Davis'."}, "shuffle": {"type": "boolean", "description": "Indicates whether to play the songs in shuffle mode, use default if not specified", "default": false}, "volume": {"type": "integer", "description": "The volume level to set when playing the song, expressed as a percentage from 0 to 100m, use default if not specified", "default": 50}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'play_spotify_song', 'description': 'This function searches for a song on Spotify using a provided query and plays the selected track Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': \"The search query for the song, including track and artist information, in the format 'track:SongName artist:ArtistName', such as 'track:Doxy artist:Miles Davis'.\"}, 'shuffle': {'type': 'boolean', 'description': 'Indicates whether to play the songs in shuffle mode, use default if not specified', 'default': False}, 'volume': {'type': 'integer', 'description': 'The volume level to set when playing the song, expressed as a percentage from 0 to 100m, use default if not specified', 'default': 50}}}}]\n"}, {"role": "user", "content": "Play the song 'Friends' by Marshmello"}]] | Python | live_simple | live_simple | [{"play_spotify_song": {"query": ["track:Friends artist:Marshmello"], "shuffle": ["", false], "volume": ["", 50]}}] |
live_simple_236-124-1 | false | [{"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a provided query and plays the selected track. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song, including track and artist information, in the format 'track:SongName artist:ArtistName', such as 'track:Doxy artist:Miles Davis'."}, "shuffle": {"type": "boolean", "description": "Indicates whether to play the songs in shuffle mode.", "default": false}, "volume": {"type": "integer", "description": "The volume level to set when playing the song, expressed as a percentage from 0 to 100, use default if not specified", "default": 50}}}}] | [{"type": "function", "function": {"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a provided query and plays the selected track. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song, including track and artist information, in the format 'track:SongName artist:ArtistName', such as 'track:Doxy artist:Miles Davis'."}, "shuffle": {"type": "boolean", "description": "Indicates whether to play the songs in shuffle mode.", "default": false}, "volume": {"type": "integer", "description": "The volume level to set when playing the song, expressed as a percentage from 0 to 100, use default if not specified", "default": 50}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'play_spotify_song', 'description': 'This function searches for a song on Spotify using a provided query and plays the selected track. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': \"The search query for the song, including track and artist information, in the format 'track:SongName artist:ArtistName', such as 'track:Doxy artist:Miles Davis'.\"}, 'shuffle': {'type': 'boolean', 'description': 'Indicates whether to play the songs in shuffle mode.', 'default': False}, 'volume': {'type': 'integer', 'description': 'The volume level to set when playing the song, expressed as a percentage from 0 to 100, use default if not specified', 'default': 50}}}}]\n"}, {"role": "user", "content": "I'd like to listen to the song 'Dil Nu' by Maninder Buttar on Spotify."}]] | Python | live_simple | live_simple | [{"play_spotify_song": {"query": ["track:Dil Nu artist:Maninder Buttar"], "shuffle": ["", false], "volume": ["", 50]}}] |
live_simple_237-125-0 | false | [{"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}] | [{"type": "function", "function": {"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'play_spotify_song', 'description': 'This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': \"The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown.\"}, 'device_id': {'type': 'string', 'description': 'The unique identifier for the device on which the song should be played.', 'default': 'null'}, 'play': {'type': 'boolean', 'description': 'A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.', 'default': True}}}}]\n"}, {"role": "user", "content": "play wrecking ball by Miley Cyrus"}]] | Python | live_simple | live_simple | [{"play_spotify_song": {"query": ["track:Wrecking Ball artist:Miley Cyrus"], "device_id": ["", "null"], "play": ["", true]}}] |
live_simple_238-125-1 | false | [{"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}] | [{"type": "function", "function": {"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'play_spotify_song', 'description': 'This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': \"The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown.\"}, 'device_id': {'type': 'string', 'description': 'The unique identifier for the device on which the song should be played.', 'default': 'null'}, 'play': {'type': 'boolean', 'description': 'A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.', 'default': True}}}}]\n"}, {"role": "user", "content": "I want to listen to 'Dil Nu' by Maninder Buttar. Can you find it on Spotify."}]] | Python | live_simple | live_simple | [{"play_spotify_song": {"query": ["track:Dil Nu artist:Maninder Buttar"], "device_id": ["", "null"], "play": ["", true]}}] |
live_simple_239-125-2 | false | [{"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}] | [{"type": "function", "function": {"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'play_spotify_song', 'description': 'This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': \"The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown.\"}, 'device_id': {'type': 'string', 'description': 'The unique identifier for the device on which the song should be played.', 'default': 'null'}, 'play': {'type': 'boolean', 'description': 'A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.', 'default': True}}}}]\n"}, {"role": "user", "content": "Can you search for the song 'Shape of You'?"}]] | Python | live_simple | live_simple | [{"play_spotify_song": {"query": ["track:Shape of You artist:Ed Sheeran", "Shape of You"], "device_id": ["", "null"], "play": ["", true]}}] |
live_simple_240-125-3 | false | [{"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}] | [{"type": "function", "function": {"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'play_spotify_song', 'description': 'This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': \"The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown.\"}, 'device_id': {'type': 'string', 'description': 'The unique identifier for the device on which the song should be played.', 'default': 'null'}, 'play': {'type': 'boolean', 'description': 'A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.', 'default': True}}}}]\n"}, {"role": "user", "content": "Can you search for 'Baby Shark'?"}]] | Python | live_simple | live_simple | [{"play_spotify_song": {"query": ["Baby Shark"], "device_id": ["", "null"], "play": ["", true]}}] |
live_simple_241-125-4 | false | [{"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}] | [{"type": "function", "function": {"name": "play_spotify_song", "description": "This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["query"], "properties": {"query": {"type": "string", "description": "The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown."}, "device_id": {"type": "string", "description": "The unique identifier for the device on which the song should be played.", "default": "null"}, "play": {"type": "boolean", "description": "A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.", "default": true}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'play_spotify_song', 'description': 'This function searches for a song on Spotify using a specified query and plays it. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['query'], 'properties': {'query': {'type': 'string', 'description': \"The search query for the song. It should be formatted as 'track:Song Name artist:Artist Name' for specific searches, or just 'Song Name' if the artist is unknown.\"}, 'device_id': {'type': 'string', 'description': 'The unique identifier for the device on which the song should be played.', 'default': 'null'}, 'play': {'type': 'boolean', 'description': 'A flag that indicates whether to start playing the song immediately after it is found. Defaults to true.', 'default': True}}}}]\n"}, {"role": "user", "content": "play Johnny Johnny Yes papa"}]] | Python | live_simple | live_simple | [{"play_spotify_song": {"query": ["Johnny Johnny Yes Papa", "Johnny Johnny Yes papa"], "device_id": ["", "null"], "play": ["", true]}}] |
live_simple_242-126-0 | false | [{"name": "set_volume", "description": "Set the global volume for all audio playback. The volume level can be specified as an integer percentage between 0 (mute) and 100 (maximum volume). Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["volume"], "properties": {"volume": {"type": "integer", "description": "The volume level as a percentage from 0 (silent) to 100 (full volume)."}}}}] | [{"type": "function", "function": {"name": "set_volume", "description": "Set the global volume for all audio playback. The volume level can be specified as an integer percentage between 0 (mute) and 100 (maximum volume). Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["volume"], "properties": {"volume": {"type": "integer", "description": "The volume level as a percentage from 0 (silent) to 100 (full volume)."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'set_volume', 'description': 'Set the global volume for all audio playback. The volume level can be specified as an integer percentage between 0 (mute) and 100 (maximum volume). Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['volume'], 'properties': {'volume': {'type': 'integer', 'description': 'The volume level as a percentage from 0 (silent) to 100 (full volume).'}}}}]\n"}, {"role": "user", "content": "Make the volume 20"}]] | Python | live_simple | live_simple | [{"set_volume": {"volume": [20]}}] |
live_simple_243-126-1 | false | [{"name": "set_volume", "description": "Set the global volume for all audio playback. The volume level can be specified as an integer percentage between 0 (mute) and 100 (maximum volume). Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["volume"], "properties": {"volume": {"type": "integer", "description": "The volume level as a percentage from 0 (silent) to 100 (full volume)."}}}}] | [{"type": "function", "function": {"name": "set_volume", "description": "Set the global volume for all audio playback. The volume level can be specified as an integer percentage between 0 (mute) and 100 (maximum volume). Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["volume"], "properties": {"volume": {"type": "integer", "description": "The volume level as a percentage from 0 (silent) to 100 (full volume)."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'set_volume', 'description': 'Set the global volume for all audio playback. The volume level can be specified as an integer percentage between 0 (mute) and 100 (maximum volume). Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['volume'], 'properties': {'volume': {'type': 'integer', 'description': 'The volume level as a percentage from 0 (silent) to 100 (full volume).'}}}}]\n"}, {"role": "user", "content": "Can you lower the audio playback to 30% volume?"}]] | Python | live_simple | live_simple | [{"set_volume": {"volume": [30]}}] |
live_simple_244-126-2 | false | [{"name": "set_volume", "description": "Set the global volume for all audio playback. The volume level can be specified as an integer percentage between 0 (mute) and 100 (maximum volume). Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["volume"], "properties": {"volume": {"type": "integer", "description": "The volume level as a percentage from 0 (silent) to 100 (full volume)."}}}}] | [{"type": "function", "function": {"name": "set_volume", "description": "Set the global volume for all audio playback. The volume level can be specified as an integer percentage between 0 (mute) and 100 (maximum volume). Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["volume"], "properties": {"volume": {"type": "integer", "description": "The volume level as a percentage from 0 (silent) to 100 (full volume)."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'set_volume', 'description': 'Set the global volume for all audio playback. The volume level can be specified as an integer percentage between 0 (mute) and 100 (maximum volume). Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['volume'], 'properties': {'volume': {'type': 'integer', 'description': 'The volume level as a percentage from 0 (silent) to 100 (full volume).'}}}}]\n"}, {"role": "user", "content": "Set the volume to 70"}]] | Python | live_simple | live_simple | [{"set_volume": {"volume": [70]}}] |
live_simple_245-127-0 | false | [{"name": "book_flight", "description": "Books a flight based on the provided departure location, date, and time. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["departure_location", "departure_date", "departure_time"], "properties": {"departure_location": {"type": "string", "description": "The city or airport code from which the flight will depart, such as 'JFK' for John F. Kennedy International Airport."}, "departure_date": {"type": "string", "description": "The departure date for the flight in the format of 'dd/mm/yyyy', such as '15/03/2024'. The date must be after 14/03/2024."}, "departure_time": {"type": "string", "description": "The departure time for the flight in 24-hour format, such as '18:45'."}}}}] | [{"type": "function", "function": {"name": "book_flight", "description": "Books a flight based on the provided departure location, date, and time. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["departure_location", "departure_date", "departure_time"], "properties": {"departure_location": {"type": "string", "description": "The city or airport code from which the flight will depart, such as 'JFK' for John F. Kennedy International Airport."}, "departure_date": {"type": "string", "description": "The departure date for the flight in the format of 'dd/mm/yyyy', such as '15/03/2024'. The date must be after 14/03/2024."}, "departure_time": {"type": "string", "description": "The departure time for the flight in 24-hour format, such as '18:45'."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'book_flight', 'description': 'Books a flight based on the provided departure location, date, and time. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['departure_location', 'departure_date', 'departure_time'], 'properties': {'departure_location': {'type': 'string', 'description': \"The city or airport code from which the flight will depart, such as 'JFK' for John F. Kennedy International Airport.\"}, 'departure_date': {'type': 'string', 'description': \"The departure date for the flight in the format of 'dd/mm/yyyy', such as '15/03/2024'. The date must be after 14/03/2024.\"}, 'departure_time': {'type': 'string', 'description': \"The departure time for the flight in 24-hour format, such as '18:45'.\"}}}}]\n"}, {"role": "user", "content": "I need to get a flight from JFK on the 16th of March 2024. Can you find me something that leaves around 14:00?"}]] | Python | live_simple | live_simple | [{"book_flight": {"departure_location": ["JFK"], "departure_date": ["16/03/2024"], "departure_time": ["14:00"]}}] |
live_simple_246-128-0 | false | [{"name": "book_flight", "description": "Books a flight based on the provided departure location and departure time. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["departure_location", "departure_time"], "properties": {"departure_location": {"type": "string", "description": "The city or airport from where the flight will depart. Expected in the format of 'City, State' or 'Airport Code', such as 'New York, NY' or 'LAX'."}, "departure_time": {"type": "string", "description": "The departure time of the flight, specified in the format of 'dd/mm/yyyy'. Must be a date after 14/03/2024."}}}}] | [{"type": "function", "function": {"name": "book_flight", "description": "Books a flight based on the provided departure location and departure time. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["departure_location", "departure_time"], "properties": {"departure_location": {"type": "string", "description": "The city or airport from where the flight will depart. Expected in the format of 'City, State' or 'Airport Code', such as 'New York, NY' or 'LAX'."}, "departure_time": {"type": "string", "description": "The departure time of the flight, specified in the format of 'dd/mm/yyyy'. Must be a date after 14/03/2024."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'book_flight', 'description': 'Books a flight based on the provided departure location and departure time. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['departure_location', 'departure_time'], 'properties': {'departure_location': {'type': 'string', 'description': \"The city or airport from where the flight will depart. Expected in the format of 'City, State' or 'Airport Code', such as 'New York, NY' or 'LAX'.\"}, 'departure_time': {'type': 'string', 'description': \"The departure time of the flight, specified in the format of 'dd/mm/yyyy'. Must be a date after 14/03/2024.\"}}}}]\n"}, {"role": "user", "content": "Can you arrange a flight for me departing from New York on the 15th of March, 2024?"}]] | Python | live_simple | live_simple | [{"book_flight": {"departure_location": ["New York, NY"], "departure_time": ["15/03/2024"]}}] |
live_simple_247-129-0 | false | [{"name": "version_api.VersionApi.get_version", "description": "Retrieves the current version information of the application, including its name and version number. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": [], "properties": {}}}] | [{"type": "function", "function": {"name": "version_api_VersionApi_get_version", "description": "Retrieves the current version information of the application, including its name and version number. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": [], "properties": {}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'version_api.VersionApi.get_version', 'description': 'Retrieves the current version information of the application, including its name and version number. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': [], 'properties': {}}}]\n"}, {"role": "user", "content": "Give me the application version."}]] | Python | live_simple | live_simple | [{"version_api.VersionApi.get_version": {}}] |
live_simple_248-130-0 | false | [{"name": "acl_api.AclApi.retrieve_projects", "description": "Retrieve the list of projects assigned to a specified team, with options to exclude inactive or child projects. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["uuid"], "properties": {"uuid": {"type": "string", "description": "The UUID of the team for which to retrieve the project mappings."}, "excludeInactive": {"type": "boolean", "description": "If set to true, inactive projects will be excluded from the results.", "default": false}, "onlyRoot": {"type": "boolean", "description": "If set to true, only root projects will be returned, excluding any child projects.", "default": false}}}}] | [{"type": "function", "function": {"name": "acl_api_AclApi_retrieve_projects", "description": "Retrieve the list of projects assigned to a specified team, with options to exclude inactive or child projects. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["uuid"], "properties": {"uuid": {"type": "string", "description": "The UUID of the team for which to retrieve the project mappings."}, "excludeInactive": {"type": "boolean", "description": "If set to true, inactive projects will be excluded from the results.", "default": false}, "onlyRoot": {"type": "boolean", "description": "If set to true, only root projects will be returned, excluding any child projects.", "default": false}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'acl_api.AclApi.retrieve_projects', 'description': 'Retrieve the list of projects assigned to a specified team, with options to exclude inactive or child projects. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['uuid'], 'properties': {'uuid': {'type': 'string', 'description': 'The UUID of the team for which to retrieve the project mappings.'}, 'excludeInactive': {'type': 'boolean', 'description': 'If set to true, inactive projects will be excluded from the results.', 'default': False}, 'onlyRoot': {'type': 'boolean', 'description': 'If set to true, only root projects will be returned, excluding any child projects.', 'default': False}}}}]\n"}, {"role": "user", "content": "What are the active root projects of the TEAM with UUID '12'?"}]] | Python | live_simple | live_simple | [{"acl_api.AclApi.retrieve_projects": {"uuid": ["12"], "excludeInactive": [true], "onlyRoot": [true]}}] |
live_simple_249-131-0 | false | [{"name": "chat_with_friend", "description": "Initiates a chat session with an AI-powered virtual bunny, where the user can send messages and receive responses. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["user_message"], "properties": {"user_message": {"type": "string", "description": "The user's message to the bunny. The message should be a text string representing the user's query or statement for interaction."}}}}] | [{"type": "function", "function": {"name": "chat_with_friend", "description": "Initiates a chat session with an AI-powered virtual bunny, where the user can send messages and receive responses. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["user_message"], "properties": {"user_message": {"type": "string", "description": "The user's message to the bunny. The message should be a text string representing the user's query or statement for interaction."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'chat_with_friend', 'description': 'Initiates a chat session with an AI-powered virtual bunny, where the user can send messages and receive responses. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['user_message'], 'properties': {'user_message': {'type': 'string', 'description': \"The user's message to the bunny. The message should be a text string representing the user's query or statement for interaction.\"}}}}]\n"}, {"role": "user", "content": "Hey bunny, How are you doing"}]] | Python | live_simple | live_simple | [{"chat_with_friend": {"user_message": ["Hey bunny, How are you doing"]}}] |
live_simple_250-132-0 | false | [{"name": "uber.eat.order", "description": "Place an order for food on Uber Eats, specifying the restaurant, items, and their respective quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["restaurants", "items", "quantities"], "properties": {"restaurants": {"type": "string", "description": "The name of the restaurant from which to order food."}, "items": {"type": "array", "items": {"type": "string"}, "description": "A list of food item names selected from the restaurant's menu."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "An array of integers representing the quantity for each corresponding item in the 'items' list. Must have the same number of elements as 'items'."}}}}] | [{"type": "function", "function": {"name": "uber_eat_order", "description": "Place an order for food on Uber Eats, specifying the restaurant, items, and their respective quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["restaurants", "items", "quantities"], "properties": {"restaurants": {"type": "string", "description": "The name of the restaurant from which to order food."}, "items": {"type": "array", "items": {"type": "string"}, "description": "A list of food item names selected from the restaurant's menu."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "An array of integers representing the quantity for each corresponding item in the 'items' list. Must have the same number of elements as 'items'."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'uber.eat.order', 'description': 'Place an order for food on Uber Eats, specifying the restaurant, items, and their respective quantities. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['restaurants', 'items', 'quantities'], 'properties': {'restaurants': {'type': 'string', 'description': 'The name of the restaurant from which to order food.'}, 'items': {'type': 'array', 'items': {'type': 'string'}, 'description': \"A list of food item names selected from the restaurant's menu.\"}, 'quantities': {'type': 'array', 'items': {'type': 'integer'}, 'description': \"An array of integers representing the quantity for each corresponding item in the 'items' list. Must have the same number of elements as 'items'.\"}}}}]\n"}, {"role": "user", "content": "Want to have an order for me from McDonald's on Uber Eats? I'd like two Big Macs and one McFlurry."}]] | Python | live_simple | live_simple | [{"uber.eat.order": {"restaurants": ["McDonald's", "McDonalds", "McDonald"], "items": [["Big Mac", "McFlurry"]], "quantities": [[2, 1]]}}] |
live_simple_251-133-0 | false | [{"name": "flight.status.check", "description": "Checks the current status of a flight using the flight's unique identifier and the passenger's name and ticket number. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["flight_id", "passenger_name", "ticket_number"], "properties": {"flight_id": {"type": "string", "description": "The unique identifier of the flight, typically in the format 'XX123' where 'XX' represents the airline code followed by the flight number."}, "passenger_name": {"type": "string", "description": "Full name or first name of the passenger as it appears on the ticket."}, "ticket_number": {"type": "string", "description": "Unique ticket number provided to the passenger upon booking, usually consisting of a series of numbers and/or letters."}}}}] | [{"type": "function", "function": {"name": "flight_status_check", "description": "Checks the current status of a flight using the flight's unique identifier and the passenger's name and ticket number. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["flight_id", "passenger_name", "ticket_number"], "properties": {"flight_id": {"type": "string", "description": "The unique identifier of the flight, typically in the format 'XX123' where 'XX' represents the airline code followed by the flight number."}, "passenger_name": {"type": "string", "description": "Full name or first name of the passenger as it appears on the ticket."}, "ticket_number": {"type": "string", "description": "Unique ticket number provided to the passenger upon booking, usually consisting of a series of numbers and/or letters."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'flight.status.check', 'description': \"Checks the current status of a flight using the flight's unique identifier and the passenger's name and ticket number. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['flight_id', 'passenger_name', 'ticket_number'], 'properties': {'flight_id': {'type': 'string', 'description': \"The unique identifier of the flight, typically in the format 'XX123' where 'XX' represents the airline code followed by the flight number.\"}, 'passenger_name': {'type': 'string', 'description': 'Full name or first name of the passenger as it appears on the ticket.'}, 'ticket_number': {'type': 'string', 'description': 'Unique ticket number provided to the passenger upon booking, usually consisting of a series of numbers and/or letters.'}}}}]\n"}, {"role": "user", "content": "Hi, I am Karan. Could you tell me the current status of my Indigo flight 6E123? My ticket number is IND4567."}]] | Python | live_simple | live_simple | [{"flight.status.check": {"flight_id": ["6E123"], "passenger_name": ["Karan"], "ticket_number": ["IND4567"]}}] |
live_simple_252-134-0 | false | [{"name": "flight.status.check", "description": "Checks the current status of a flight using the airline, passenger's name, and ticket number. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["airlines", "person_name", "ticket_number"], "properties": {"airlines": {"type": "string", "description": "The name of the airline for which to check the flight status, such as 'Delta' or 'United'."}, "person_name": {"type": "string", "description": "The full name or first name of the passenger as it appears on the ticket, in the format 'First Last'. If only one name mentioned assume last name is not specified and instead use LNU"}, "ticket_number": {"type": "string", "description": "The alphanumeric ticket number associated with the passenger's flight booking."}}}}] | [{"type": "function", "function": {"name": "flight_status_check", "description": "Checks the current status of a flight using the airline, passenger's name, and ticket number. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["airlines", "person_name", "ticket_number"], "properties": {"airlines": {"type": "string", "description": "The name of the airline for which to check the flight status, such as 'Delta' or 'United'."}, "person_name": {"type": "string", "description": "The full name or first name of the passenger as it appears on the ticket, in the format 'First Last'. If only one name mentioned assume last name is not specified and instead use LNU"}, "ticket_number": {"type": "string", "description": "The alphanumeric ticket number associated with the passenger's flight booking."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'flight.status.check', 'description': \"Checks the current status of a flight using the airline, passenger's name, and ticket number. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['airlines', 'person_name', 'ticket_number'], 'properties': {'airlines': {'type': 'string', 'description': \"The name of the airline for which to check the flight status, such as 'Delta' or 'United'.\"}, 'person_name': {'type': 'string', 'description': \"The full name or first name of the passenger as it appears on the ticket, in the format 'First Last'. If only one name mentioned assume last name is not specified and instead use LNU\"}, 'ticket_number': {'type': 'string', 'description': \"The alphanumeric ticket number associated with the passenger's flight booking.\"}}}}]\n"}, {"role": "user", "content": "Hi, I am Karan. Can you tell me the current status of my Indigo flight? My ticket number is IND4567."}]] | Python | live_simple | live_simple | [{"flight.status.check": {"airlines": ["Indigo"], "person_name": ["Karan"], "ticket_number": ["IND4567"]}}] |
live_simple_253-135-0 | false | [{"name": "uber.eat.order", "description": "Place an order for food from selected restaurants with specified items and their quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["restaurants", "items", "quantities"], "properties": {"restaurants": {"type": "string", "description": "The name of the restaurant from which the user wants to order food. Use the exact name as registered on Uber Eats."}, "items": {"type": "array", "items": {"type": "string"}, "description": "A list of item names that the user wants to order from the restaurant."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "A list of integers, each representing the quantity of the corresponding item in the order. The quantities should align with the items list by index."}}}}] | [{"type": "function", "function": {"name": "uber_eat_order", "description": "Place an order for food from selected restaurants with specified items and their quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["restaurants", "items", "quantities"], "properties": {"restaurants": {"type": "string", "description": "The name of the restaurant from which the user wants to order food. Use the exact name as registered on Uber Eats."}, "items": {"type": "array", "items": {"type": "string"}, "description": "A list of item names that the user wants to order from the restaurant."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "A list of integers, each representing the quantity of the corresponding item in the order. The quantities should align with the items list by index."}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'uber.eat.order', 'description': 'Place an order for food from selected restaurants with specified items and their quantities. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['restaurants', 'items', 'quantities'], 'properties': {'restaurants': {'type': 'string', 'description': 'The name of the restaurant from which the user wants to order food. Use the exact name as registered on Uber Eats.'}, 'items': {'type': 'array', 'items': {'type': 'string'}, 'description': 'A list of item names that the user wants to order from the restaurant.'}, 'quantities': {'type': 'array', 'items': {'type': 'integer'}, 'description': 'A list of integers, each representing the quantity of the corresponding item in the order. The quantities should align with the items list by index.'}}}}]\n"}, {"role": "user", "content": "I want to order five burgers and six chicken wings from McDonald's."}]] | Python | live_simple | live_simple | [{"uber.eat.order": {"restaurants": ["McDonald's", "McDonalds"], "items": [["burgers", "chicken wings"], ["burger", "chicken wing"]], "quantities": [[5, 6]]}}] |
live_simple_254-136-0 | false | [{"name": "user.mandates", "description": "Fetches a list of mandates for a user given the user's ID and the status of the mandates. The user ID is a required parameter, while the status is optional and can be used to filter the mandates by their current status. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["user_id"], "properties": {"user_id": {"type": "string", "description": "The unique identifier of the user for whom the mandates need to be fetched."}, "status": {"type": "string", "description": "The current status of the mandates to fetch. If not specified, mandates with all statuses are fetched.", "enum": ["active", "pending", "inactive"], "default": "active"}}}}] | [{"type": "function", "function": {"name": "user_mandates", "description": "Fetches a list of mandates for a user given the user's ID and the status of the mandates. The user ID is a required parameter, while the status is optional and can be used to filter the mandates by their current status. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["user_id"], "properties": {"user_id": {"type": "string", "description": "The unique identifier of the user for whom the mandates need to be fetched."}, "status": {"type": "string", "description": "The current status of the mandates to fetch. If not specified, mandates with all statuses are fetched.", "enum": ["active", "pending", "inactive"], "default": "active"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'user.mandates', 'description': \"Fetches a list of mandates for a user given the user's ID and the status of the mandates. The user ID is a required parameter, while the status is optional and can be used to filter the mandates by their current status. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['user_id'], 'properties': {'user_id': {'type': 'string', 'description': 'The unique identifier of the user for whom the mandates need to be fetched.'}, 'status': {'type': 'string', 'description': 'The current status of the mandates to fetch. If not specified, mandates with all statuses are fetched.', 'enum': ['active', 'pending', 'inactive'], 'default': 'active'}}}}]\n"}, {"role": "user", "content": "need all pending mandates of Parath with ID U123?"}]] | Python | live_simple | live_simple | [{"user.mandates": {"user_id": ["U123"], "status": ["pending"]}}] |
live_simple_255-136-1 | false | [{"name": "user.mandates", "description": "Fetches a list of mandates for a user given the user's ID and the status of the mandates. The user ID is a required parameter, while the status is optional and can be used to filter the mandates by their current status. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["user_id"], "properties": {"user_id": {"type": "string", "description": "The unique identifier of the user for whom the mandates need to be fetched."}, "status": {"type": "string", "description": "The current status of the mandates to fetch. If not specified, mandates with all statuses are fetched.", "enum": ["active", "pending", "inactive"], "default": "active"}}}}] | [{"type": "function", "function": {"name": "user_mandates", "description": "Fetches a list of mandates for a user given the user's ID and the status of the mandates. The user ID is a required parameter, while the status is optional and can be used to filter the mandates by their current status. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["user_id"], "properties": {"user_id": {"type": "string", "description": "The unique identifier of the user for whom the mandates need to be fetched."}, "status": {"type": "string", "description": "The current status of the mandates to fetch. If not specified, mandates with all statuses are fetched.", "enum": ["active", "pending", "inactive"], "default": "active"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'user.mandates', 'description': \"Fetches a list of mandates for a user given the user's ID and the status of the mandates. The user ID is a required parameter, while the status is optional and can be used to filter the mandates by their current status. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['user_id'], 'properties': {'user_id': {'type': 'string', 'description': 'The unique identifier of the user for whom the mandates need to be fetched.'}, 'status': {'type': 'string', 'description': 'The current status of the mandates to fetch. If not specified, mandates with all statuses are fetched.', 'enum': ['active', 'pending', 'inactive'], 'default': 'active'}}}}]\n"}, {"role": "user", "content": "Get the list of active mandates for the user with ID U123456?"}]] | Python | live_simple | live_simple | [{"user.mandates": {"user_id": ["U123456"], "status": ["", "active"]}}] |
live_simple_256-137-0 | false | [{"name": "answer_question", "description": "This function transfers the chat interaction to a human agent when the automated system encounters a question that it cannot answer. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["statement"], "properties": {"statement": {"type": "string", "description": "The question posed by the user that needs to be transferred to a human agent."}, "urgency": {"type": "string", "description": "The level of urgency for the question to be answered.", "enum": ["low", "medium", "high"], "default": "medium"}, "language": {"type": "string", "description": "The language in which the question is asked, using ISO 639-1 codes (e.g., 'en' for English, 'es' for Spanish)", "default": "en"}}}}] | [{"type": "function", "function": {"name": "answer_question", "description": "This function transfers the chat interaction to a human agent when the automated system encounters a question that it cannot answer. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["statement"], "properties": {"statement": {"type": "string", "description": "The question posed by the user that needs to be transferred to a human agent."}, "urgency": {"type": "string", "description": "The level of urgency for the question to be answered.", "enum": ["low", "medium", "high"], "default": "medium"}, "language": {"type": "string", "description": "The language in which the question is asked, using ISO 639-1 codes (e.g., 'en' for English, 'es' for Spanish)", "default": "en"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'answer_question', 'description': 'This function transfers the chat interaction to a human agent when the automated system encounters a question that it cannot answer. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['statement'], 'properties': {'statement': {'type': 'string', 'description': 'The question posed by the user that needs to be transferred to a human agent.'}, 'urgency': {'type': 'string', 'description': 'The level of urgency for the question to be answered.', 'enum': ['low', 'medium', 'high'], 'default': 'medium'}, 'language': {'type': 'string', 'description': \"The language in which the question is asked, using ISO 639-1 codes (e.g., 'en' for English, 'es' for Spanish)\", 'default': 'en'}}}}]\n\n\ncall HANDOVER function to transfer the request if user asks a question."}, {"role": "user", "content": "I have had submit a compaint and I like to check its status"}]] | Python | live_simple | live_simple | [{"answer_question": {"statement": ["I have had submit a compaint and I like to check its status"], "urgency": ["", "medium"], "language": ["", "en"]}}] |
live_simple_257-137-1 | false | [{"name": "answer_question", "description": "This function transfers the chat interaction to a human agent when the automated system encounters a question that it cannot answer. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["statement"], "properties": {"statement": {"type": "string", "description": "The question posed by the user that needs to be transferred to a human agent."}, "urgency": {"type": "string", "description": "The level of urgency for the question to be answered.", "enum": ["low", "medium", "high"], "default": "medium"}, "language": {"type": "string", "description": "The language in which the question is asked, using ISO 639-1 codes (e.g., 'en' for English, 'es' for Spanish).", "default": "en"}}}}] | [{"type": "function", "function": {"name": "answer_question", "description": "This function transfers the chat interaction to a human agent when the automated system encounters a question that it cannot answer. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["statement"], "properties": {"statement": {"type": "string", "description": "The question posed by the user that needs to be transferred to a human agent."}, "urgency": {"type": "string", "description": "The level of urgency for the question to be answered.", "enum": ["low", "medium", "high"], "default": "medium"}, "language": {"type": "string", "description": "The language in which the question is asked, using ISO 639-1 codes (e.g., 'en' for English, 'es' for Spanish).", "default": "en"}}}}}] | {} | {} | [] | [[{"role": "system", "content": "\nYou are a helpful assistant and an expert in function composition. You can answer general questions using your internal knowledge OR invoke functions when necessary. Follow these strict guidelines:\n\n1. FUNCTION CALLS:\n- ONLY use functions that are EXPLICITLY listed in the function list below\n- If NO functions are listed (empty function list []), respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If a function is not in the list, respond ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\"\n- If ALL required parameters are present AND the query EXACTLY matches a listed function's purpose: output ONLY the function call(s)\n- Use exact format: [func_name1(param1=value1, param2=value2), func_name2(...)]\nExamples:\nCORRECT: [get_weather(location=\"Vancouver\"), calculate_route(start=\"Boston\", end=\"New York\")] <- Only if get_weather and calculate_route are in function list\nINCORRECT: get_weather(location=\"New York\")\nINCORRECT: Let me check the weather: [get_weather(location=\"New York\")]\nINCORRECT: [get_events(location=\"Singapore\")] <- If function not in list\n\n2. RESPONSE RULES:\n- For pure function requests matching a listed function: ONLY output the function call(s)\n- For knowledge questions: ONLY output text\n- For missing parameters: ONLY request the specific missing parameters\n- For unavailable services (not in function list): output ONLY with internal knowledge or \"I don't have access to [Unavailable service] information\". Do NOT execute a function call.\n- If the query asks for information beyond what a listed function provides: output ONLY with internal knowledge about your limitations\n- NEVER combine text and function calls in the same response\n- NEVER suggest alternative functions when the requested service is unavailable\n- NEVER create or invent new functions not listed below\n\n3. STRICT BOUNDARIES:\n- ONLY use functions from the list below - no exceptions\n- NEVER use a function as an alternative to unavailable information\n- NEVER call functions not present in the function list\n- NEVER add explanatory text to function calls\n- NEVER respond with empty brackets\n- Use proper Python/JSON syntax for function calls\n- Check the function list carefully before responding\n\n4. TOOL RESPONSE HANDLING:\n- When receiving tool responses: provide concise, natural language responses\n- Don't repeat tool response verbatim\n- Don't add supplementary information\n\nHere is a list of functions in JSON format that you can invoke:\n[{'name': 'answer_question', 'description': 'This function transfers the chat interaction to a human agent when the automated system encounters a question that it cannot answer. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['statement'], 'properties': {'statement': {'type': 'string', 'description': 'The question posed by the user that needs to be transferred to a human agent.'}, 'urgency': {'type': 'string', 'description': 'The level of urgency for the question to be answered.', 'enum': ['low', 'medium', 'high'], 'default': 'medium'}, 'language': {'type': 'string', 'description': \"The language in which the question is asked, using ISO 639-1 codes (e.g., 'en' for English, 'es' for Spanish).\", 'default': 'en'}}}}]\n\n\ncall HANDOVER function to transfer the request if user asks a question."}, {"role": "user", "content": "Can you tell me what is the minimum package arrival time? "}]] | Python | live_simple | live_simple | [{"answer_question": {"statement": ["Can you tell me what is the minimum package arrival time?"], "urgency": ["", "medium"], "language": ["", "en"]}}] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.