Dataset Viewer
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_0-0-0 | false | [{"name": "get_user_info", "description": "Retrieve details for a specific user by their unique identifier. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["user_id"], "properties": {"user_id": {"type": "integer", "description": "The unique identifier of the user. It is used to fetch the specific user details from the database."}, "special": {"type": "string", "description": "Any special information or parameters that need to be considered while fetching user details.", "default": "none"}}}}] | [{"type": "function", "function": {"name": "get_user_info", "description": "Retrieve details for a specific user by their unique identifier. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["user_id"], "properties": {"user_id": {"type": "integer", "description": "The unique identifier of the user. It is used to fetch the specific user details from the database."}, "special": {"type": "string", "description": "Any special information or parameters that need to be considered while fetching user details.", "default": "none"}}}}}] | {} | {} | [] | [[{"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': 'get_user_info', 'description': 'Retrieve details for a specific user by their unique identifier. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['user_id'], 'properties': {'user_id': {'type': 'integer', 'description': 'The unique identifier of the user. It is used to fetch the specific user details from the database.'}, 'special': {'type': 'string', 'description': 'Any special information or parameters that need to be considered while fetching user details.', 'default': 'none'}}}}]\n"}, {"role": "user", "content": "Can you retrieve the details for the user with the ID 7890, who has black as their special request?"}]] | Python | live_simple | live_simple | [{"get_user_info": {"user_id": [7890], "special": ["black"]}}] |
live_simple_1-1-0 | false | [{"name": "github_star", "description": "Generates a URL for tracking the star history of specified GitHub repositories, with the option to align them on the same timeline. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["repos"], "properties": {"repos": {"type": "string", "description": "A comma-separated list of GitHub repositories to track, each in the 'owner/repo' format, such as 'octocat/Hello-World,octo-org/octo-repo'."}, "aligned": {"type": "boolean", "description": "Whether to align the repositories on the same timeline for comparison. If true, the star history of all repositories will start from the same point.", "default": false}}}}] | [{"type": "function", "function": {"name": "github_star", "description": "Generates a URL for tracking the star history of specified GitHub repositories, with the option to align them on the same timeline. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["repos"], "properties": {"repos": {"type": "string", "description": "A comma-separated list of GitHub repositories to track, each in the 'owner/repo' format, such as 'octocat/Hello-World,octo-org/octo-repo'."}, "aligned": {"type": "boolean", "description": "Whether to align the repositories on the same timeline for comparison. If true, the star history of all repositories will start from the same point.", "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': 'github_star', 'description': 'Generates a URL for tracking the star history of specified GitHub repositories, with the option to align them on the same timeline. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['repos'], 'properties': {'repos': {'type': 'string', 'description': \"A comma-separated list of GitHub repositories to track, each in the 'owner/repo' format, such as 'octocat/Hello-World,octo-org/octo-repo'.\"}, 'aligned': {'type': 'boolean', 'description': 'Whether to align the repositories on the same timeline for comparison. If true, the star history of all repositories will start from the same point.', 'default': False}}}}]\n"}, {"role": "user", "content": "I want to see the star history of ShishirPatil/gorilla and gorilla-llm/gorilla-cli, with the timelines aligned, so that I can more clearly observe the rate of change from their initial releases."}]] | Python | live_simple | live_simple | [{"github_star": {"repos": ["ShishirPatil/gorilla,gorilla-llm/gorilla-cli"], "aligned": [true]}}] |
live_simple_2-2-0 | false | [{"name": "uber.ride", "description": "Finds a suitable Uber ride for customers based on their location, desired ride type, and maximum wait time. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["loc", "type", "time"], "properties": {"loc": {"type": "string", "description": "The starting location for the Uber ride, in the format of 'Street Address, City, State (abbr), Country'."}, "type": {"type": "string", "description": "The type of Uber ride the user is requesting.", "enum": ["plus", "comfort", "black"]}, "time": {"type": "integer", "description": "The maximum amount of time the customer is willing to wait for the ride, specified in seconds."}}}}] | [{"type": "function", "function": {"name": "uber_ride", "description": "Finds a suitable Uber ride for customers based on their location, desired ride type, and maximum wait time. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["loc", "type", "time"], "properties": {"loc": {"type": "string", "description": "The starting location for the Uber ride, in the format of 'Street Address, City, State (abbr), Country'."}, "type": {"type": "string", "description": "The type of Uber ride the user is requesting.", "enum": ["plus", "comfort", "black"]}, "time": {"type": "integer", "description": "The maximum amount of time the customer is willing to wait for the ride, specified in seconds."}}}}}] | {} | {} | [] | [[{"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.ride', 'description': 'Finds a suitable Uber ride for customers based on their location, desired ride type, and maximum wait time. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['loc', 'type', 'time'], 'properties': {'loc': {'type': 'string', 'description': \"The starting location for the Uber ride, in the format of 'Street Address, City, State (abbr), Country'.\"}, 'type': {'type': 'string', 'description': 'The type of Uber ride the user is requesting.', 'enum': ['plus', 'comfort', 'black']}, 'time': {'type': 'integer', 'description': 'The maximum amount of time the customer is willing to wait for the ride, specified in seconds.'}}}}]\n"}, {"role": "user", "content": "I need a Comfort Uber ride from 2020 Addison Street, Berkeley, CA, USA, and I can wait up to 600 seconds for it."}]] | Python | live_simple | live_simple | [{"uber.ride": {"loc": ["2020 Addison Street, Berkeley, CA, USA"], "type": ["comfort"], "time": [600]}}] |
live_simple_3-2-1 | false | [{"name": "uber.ride", "description": "Finds a suitable Uber ride for customers based on their location, desired ride type, and maximum wait time. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["loc", "type", "time"], "properties": {"loc": {"type": "string", "description": "The starting location for the Uber ride, in the format of 'Street Address, City, State (abbr), Country'."}, "type": {"type": "string", "description": "The type of Uber ride the user is requesting.", "enum": ["plus", "comfort", "black"]}, "time": {"type": "integer", "description": "The maximum amount of time the customer is willing to wait for the ride, specified in seconds."}}}}] | [{"type": "function", "function": {"name": "uber_ride", "description": "Finds a suitable Uber ride for customers based on their location, desired ride type, and maximum wait time. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["loc", "type", "time"], "properties": {"loc": {"type": "string", "description": "The starting location for the Uber ride, in the format of 'Street Address, City, State (abbr), Country'."}, "type": {"type": "string", "description": "The type of Uber ride the user is requesting.", "enum": ["plus", "comfort", "black"]}, "time": {"type": "integer", "description": "The maximum amount of time the customer is willing to wait for the ride, specified in seconds."}}}}}] | {} | {} | [] | [[{"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.ride', 'description': 'Finds a suitable Uber ride for customers based on their location, desired ride type, and maximum wait time. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['loc', 'type', 'time'], 'properties': {'loc': {'type': 'string', 'description': \"The starting location for the Uber ride, in the format of 'Street Address, City, State (abbr), Country'.\"}, 'type': {'type': 'string', 'description': 'The type of Uber ride the user is requesting.', 'enum': ['plus', 'comfort', 'black']}, 'time': {'type': 'integer', 'description': 'The maximum amount of time the customer is willing to wait for the ride, specified in seconds.'}}}}]\n"}, {"role": "user", "content": "I need a 'Plus' type Uber from 221B Baker Street, Berkeley, CA, USA, and I can wait up to 600 seconds for it. "}]] | Python | live_simple | live_simple | [{"uber.ride": {"loc": ["221B Baker Street, Berkeley, CA, USA"], "type": ["plus"], "time": [600]}}] |
live_simple_4-3-0 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "What are the current weather conditions in Tel Aviv, and could you provide that in Fahrenheit, please?"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Tel Aviv, Israel"], "unit": ["fahrenheit", ""]}}] |
live_simple_5-3-1 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "Qual a temperatura atual em Divin\u00f3polis, MG? fahrenheit"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Divin\u00f3polis, MG"], "unit": ["fahrenheit", ""]}}] |
live_simple_6-3-2 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "Can you tell me the weather in fahrenheit so that I decide if I need to wear a jacket today? San Francisco"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["San Francisco, CA"], "unit": ["fahrenheit", ""]}}] |
live_simple_7-3-3 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "Im at Riga, Latvia, Can you tell me the current temperature?"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Riga, Latvia"], "unit": ["fahrenheit", "", "celsius"]}}] |
live_simple_8-3-4 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "I want to know weather conditions? I'm at London, UK in fahr"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["London, UK", "London, England"], "unit": ["fahrenheit", ""]}}] |
live_simple_9-3-5 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "What's weather in Hyderabad in Fahrenheit"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Hyderabad, India"], "unit": ["fahrenheit", ""]}}] |
live_simple_10-3-6 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)' or 'Location, State', such as 'San Francisco, CA' if State exists. 'City, Country' if State for the city doesn't exist. "}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)' or 'Location, State', such as 'San Francisco, CA' if State exists. 'City, Country' if State for the city doesn't exist. "}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)' or 'Location, State', such as 'San Francisco, CA' if State exists. 'City, Country' if State for the city doesn't exist. \"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "Could you tell me the current weather in Yosemite National Park which locates at Mariposa, CA, and make sure to give me the temperature in Celsius?"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Mariposa, CA"], "unit": ["celsius"]}}] |
live_simple_11-3-7 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist. If using state, then use short form like CA."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist. If using state, then use short form like CA."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist. If using state, then use short form like CA.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "Could you tell me the current weather conditions in Naples, Florida?"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Naples, FL", "Naples, Florida"], "unit": ["", "fahrenheit"]}}] |
live_simple_12-3-8 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist. If using state, then use short form like CA."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist. If using state, then use short form like CA."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist. If using state, then use short form like CA.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "I'm planning a trip to New York, NY in December and will be staying for 5 days. Could you tell me the current weather conditions, and provide the temperature in Celsius?"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["New York, NY"], "unit": ["celsius"]}}] |
live_simple_13-3-9 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "\u6211\u60f3\u77e5\u9053\u4e0a\u6d77\u76ee\u524d\u7684\u5929\u6c14\u72b6\u51b5\uff0c\u53ef\u4ee5\u5e2e\u6211\u67e5\u8be2\u5417\uff1f\u987a\u4fbf\u4f7f\u7528\u6444\u6c0f\u5ea6\u6765\u663e\u793a\u6e29\u5ea6\u3002"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Shanghai, China", "\\u4e0a\\u6d77,\\u4e2d\\u56fd"], "unit": ["celsius"]}}] |
live_simple_14-3-10 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "I have a busy day today. Can you tell me what the temperature is going to be in Bangkok, Thailand. I prefer the fahrenheit unit."}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Bangkok, Thailand"], "unit": ["", "fahrenheit"]}}] |
live_simple_15-3-11 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "I'm at Bengaluru. Tell me the current weather conditions in Chennai, Tamil Nadu in fahrenheit?"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Chennai, Tamil Nadu"], "unit": ["", "fahrenheit"]}}] |
live_simple_16-3-12 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "Could you tell me the current weather in Lang Son in fahrenheit?"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Lang Son, Vietnam"], "unit": ["", "fahrenheit"]}}] |
live_simple_17-3-13 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "weather today in Boston in fahrenheit?"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Boston, MA"], "unit": ["", "fahrenheit"]}}] |
live_simple_18-3-14 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)', such as 'San Francisco, CA' if State for the city exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "Can you tell me the current weather in Moscow, specifying the temperature in Celsius?"}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Moscow, Russia"], "unit": ["celsius"]}}] |
live_simple_19-3-15 | false | [{"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)' or 'Location, State', such as 'San Francisco, CA' or 'Yosemite National Park, CA' if State exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}] | [{"type": "function", "function": {"name": "get_current_weather", "description": "Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["location"], "properties": {"location": {"type": "string", "description": "The location for which to get the weather, in the format of 'City, State (abbr)' or 'Location, State', such as 'San Francisco, CA' or 'Yosemite National Park, CA' if State exists. 'City, Country' if State for the city doesn't exist."}, "unit": {"type": "string", "description": "The unit of temperature for the weather report.", "enum": ["celsius", "fahrenheit"], "default": "fahrenheit"}}}}}] | {} | {} | [] | [[{"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': 'get_current_weather', 'description': 'Retrieves the current weather conditions for a specified city and state. If using state, then use short form like CA. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['location'], 'properties': {'location': {'type': 'string', 'description': \"The location for which to get the weather, in the format of 'City, State (abbr)' or 'Location, State', such as 'San Francisco, CA' or 'Yosemite National Park, CA' if State exists. 'City, Country' if State for the city doesn't exist.\"}, 'unit': {'type': 'string', 'description': 'The unit of temperature for the weather report.', 'enum': ['celsius', 'fahrenheit'], 'default': 'fahrenheit'}}}}]\n"}, {"role": "user", "content": "What's the weather in Quintana Roo, Mexico. Please tell me the answer in the superior units of temperature, by that I mean Celsius."}]] | Python | live_simple | live_simple | [{"get_current_weather": {"location": ["Quintana Roo, Mexico"], "unit": ["celsius"]}}] |
live_simple_20-4-0 | false | [{"name": "change_food", "description": "Modifies the food item based on the customer's request, such as changing ingredients or preparation methods. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["food_item", "modification_request"], "properties": {"food_item": {"type": "string", "description": "The name of the food item to be modified."}, "modification_request": {"type": "string", "description": "Specific request detailing the changes to be made to the food item, such as 'no peanuts' or 'extra spicy'. If there are multiple requests, separate using comma with no space between comma"}}}}] | [{"type": "function", "function": {"name": "change_food", "description": "Modifies the food item based on the customer's request, such as changing ingredients or preparation methods. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["food_item", "modification_request"], "properties": {"food_item": {"type": "string", "description": "The name of the food item to be modified."}, "modification_request": {"type": "string", "description": "Specific request detailing the changes to be made to the food item, such as 'no peanuts' or 'extra spicy'. If there are multiple requests, separate using comma with no space between comma"}}}}}] | {} | {} | [] | [[{"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': 'change_food', 'description': \"Modifies the food item based on the customer's request, such as changing ingredients or preparation methods. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['food_item', 'modification_request'], 'properties': {'food_item': {'type': 'string', 'description': 'The name of the food item to be modified.'}, 'modification_request': {'type': 'string', 'description': \"Specific request detailing the changes to be made to the food item, such as 'no peanuts' or 'extra spicy'. If there are multiple requests, separate using comma with no space between comma\"}}}}]\n"}, {"role": "user", "content": "I would like to order a burger with the following modification verbatim: no onions, extra cheese"}]] | Python | live_simple | live_simple | [{"change_food": {"food_item": ["burger"], "modification_request": ["no onions, extra cheese"]}}] |
live_simple_21-4-1 | false | [{"name": "change_food", "description": "Modifies the food item based on the customer's request, such as changing ingredients or preparation methods. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["food_item", "modification_request"], "properties": {"food_item": {"type": "string", "description": "The name of the food item to be modified."}, "modification_request": {"type": "string", "description": "Specific request detailing the changes to be made to the food item, such as 'no peanuts' or 'extra spicy'. If there are multiple requests, separate using comma with no space between comma"}}}}] | [{"type": "function", "function": {"name": "change_food", "description": "Modifies the food item based on the customer's request, such as changing ingredients or preparation methods. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["food_item", "modification_request"], "properties": {"food_item": {"type": "string", "description": "The name of the food item to be modified."}, "modification_request": {"type": "string", "description": "Specific request detailing the changes to be made to the food item, such as 'no peanuts' or 'extra spicy'. If there are multiple requests, separate using comma with no space between comma"}}}}}] | {} | {} | [] | [[{"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': 'change_food', 'description': \"Modifies the food item based on the customer's request, such as changing ingredients or preparation methods. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['food_item', 'modification_request'], 'properties': {'food_item': {'type': 'string', 'description': 'The name of the food item to be modified.'}, 'modification_request': {'type': 'string', 'description': \"Specific request detailing the changes to be made to the food item, such as 'no peanuts' or 'extra spicy'. If there are multiple requests, separate using comma with no space between comma\"}}}}]\n"}, {"role": "user", "content": "I'd like to modify my order by making the dish called 'chicken dish' to a new spice level 'extra spicy', please."}]] | Python | live_simple | live_simple | [{"change_food": {"food_item": ["chicken dish"], "modification_request": ["extra spicy"]}}] |
live_simple_22-5-0 | false | [{"name": "ChaFod", "description": "Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["TheFod"], "properties": {"TheFod": {"type": "string", "description": "The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').", "enum": ["PIZZA", "BURGER", "SALAD", "SOUP", "STEAK"]}}}}] | [{"type": "function", "function": {"name": "ChaFod", "description": "Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["TheFod"], "properties": {"TheFod": {"type": "string", "description": "The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').", "enum": ["PIZZA", "BURGER", "SALAD", "SOUP", "STEAK"]}}}}}] | {} | {} | [] | [[{"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': 'ChaFod', 'description': \"Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['TheFod'], 'properties': {'TheFod': {'type': 'string', 'description': \"The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').\", 'enum': ['PIZZA', 'BURGER', 'SALAD', 'SOUP', 'STEAK']}}}}]\n"}, {"role": "user", "content": "I need Whopper also known old folks as the burger."}]] | Python | live_simple | live_simple | [{"ChaFod": {"TheFod": ["BURGER"]}}] |
live_simple_23-5-1 | false | [{"name": "ChaFod", "description": "Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["TheFod"], "properties": {"TheFod": {"type": "string", "description": "The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').", "enum": ["PIZZA", "BURGER", "SALAD", "SOUP", "STEAK"]}}}}] | [{"type": "function", "function": {"name": "ChaFod", "description": "Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["TheFod"], "properties": {"TheFod": {"type": "string", "description": "The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').", "enum": ["PIZZA", "BURGER", "SALAD", "SOUP", "STEAK"]}}}}}] | {} | {} | [] | [[{"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': 'ChaFod', 'description': \"Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['TheFod'], 'properties': {'TheFod': {'type': 'string', 'description': \"The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').\", 'enum': ['PIZZA', 'BURGER', 'SALAD', 'SOUP', 'STEAK']}}}}]\n"}, {"role": "user", "content": "Order me pizza"}]] | Python | live_simple | live_simple | [{"ChaFod": {"TheFod": ["PIZZA"]}}] |
live_simple_24-5-2 | false | [{"name": "ChaFod", "description": "Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["TheFod"], "properties": {"TheFod": {"type": "string", "description": "The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').", "enum": ["PIZZA", "BURGER", "SALAD", "SOUP", "STEAK"]}}}}] | [{"type": "function", "function": {"name": "ChaFod", "description": "Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["TheFod"], "properties": {"TheFod": {"type": "string", "description": "The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').", "enum": ["PIZZA", "BURGER", "SALAD", "SOUP", "STEAK"]}}}}}] | {} | {} | [] | [[{"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': 'ChaFod', 'description': \"Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['TheFod'], 'properties': {'TheFod': {'type': 'string', 'description': \"The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').\", 'enum': ['PIZZA', 'BURGER', 'SALAD', 'SOUP', 'STEAK']}}}}]\n"}, {"role": "user", "content": "I would like to switch my order from pizza to a BURGER."}]] | Python | live_simple | live_simple | [{"ChaFod": {"TheFod": ["BURGER"]}}] |
live_simple_25-5-3 | false | [{"name": "ChaFod", "description": "Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["TheFod"], "properties": {"TheFod": {"type": "string", "description": "The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').", "enum": ["PIZZA", "BURGER", "SALAD", "SOUP", "STEAK"]}}}}] | [{"type": "function", "function": {"name": "ChaFod", "description": "Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["TheFod"], "properties": {"TheFod": {"type": "string", "description": "The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').", "enum": ["PIZZA", "BURGER", "SALAD", "SOUP", "STEAK"]}}}}}] | {} | {} | [] | [[{"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': 'ChaFod', 'description': \"Changes the selection of food based on the customer's request, ensuring the food name provided is in uppercase as per the requirement. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['TheFod'], 'properties': {'TheFod': {'type': 'string', 'description': \"The name of the food to be changed, provided in uppercase letters only (e.g., 'PIZZA', 'BURGER').\", 'enum': ['PIZZA', 'BURGER', 'SALAD', 'SOUP', 'STEAK']}}}}]\n"}, {"role": "user", "content": "I've changed my mind, can I get a greens instead of what I previously ordered?"}]] | Python | live_simple | live_simple | [{"ChaFod": {"TheFod": ["SALAD"]}}] |
live_simple_26-6-0 | false | [{"name": "uber.ride", "description": "T\u00ecm chuy\u1ebfn \u0111i ph\u00f9 h\u1ee3p cho kh\u00e1ch h\u00e0ng d\u1ef1a tr\u00ean v\u1ecb tr\u00ed, lo\u1ea1i chuy\u1ebfn \u0111i v\u00e0 kho\u1ea3ng th\u1eddi gian kh\u00e1ch h\u00e0ng s\u1eb5n s\u00e0ng ch\u1edd \u0111\u1ee3i l\u00e0m th\u00f4ng s\u1ed1' Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["loc", "type", "time"], "properties": {"loc": {"type": "string", "description": "The starting location of the Uber ride in the format of 'Address, City, State'. For example, '123 Main St, Springfield, IL'."}, "type": {"type": "string", "description": "The type of Uber ride the user is requesting.", "enum": ["plus", "comfort", "black"]}, "time": {"type": "integer", "description": "The maximum amount of time the customer is willing to wait for the ride, in minutes."}}}}] | [{"type": "function", "function": {"name": "uber_ride", "description": "T\u00ecm chuy\u1ebfn \u0111i ph\u00f9 h\u1ee3p cho kh\u00e1ch h\u00e0ng d\u1ef1a tr\u00ean v\u1ecb tr\u00ed, lo\u1ea1i chuy\u1ebfn \u0111i v\u00e0 kho\u1ea3ng th\u1eddi gian kh\u00e1ch h\u00e0ng s\u1eb5n s\u00e0ng ch\u1edd \u0111\u1ee3i l\u00e0m th\u00f4ng s\u1ed1' Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["loc", "type", "time"], "properties": {"loc": {"type": "string", "description": "The starting location of the Uber ride in the format of 'Address, City, State'. For example, '123 Main St, Springfield, IL'."}, "type": {"type": "string", "description": "The type of Uber ride the user is requesting.", "enum": ["plus", "comfort", "black"]}, "time": {"type": "integer", "description": "The maximum amount of time the customer is willing to wait for the ride, in minutes."}}}}}] | {} | {} | [] | [[{"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.ride', 'description': \"T\u00ecm chuy\u1ebfn \u0111i ph\u00f9 h\u1ee3p cho kh\u00e1ch h\u00e0ng d\u1ef1a tr\u00ean v\u1ecb tr\u00ed, lo\u1ea1i chuy\u1ebfn \u0111i v\u00e0 kho\u1ea3ng th\u1eddi gian kh\u00e1ch h\u00e0ng s\u1eb5n s\u00e0ng ch\u1edd \u0111\u1ee3i l\u00e0m th\u00f4ng s\u1ed1' Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['loc', 'type', 'time'], 'properties': {'loc': {'type': 'string', 'description': \"The starting location of the Uber ride in the format of 'Address, City, State'. For example, '123 Main St, Springfield, IL'.\"}, 'type': {'type': 'string', 'description': 'The type of Uber ride the user is requesting.', 'enum': ['plus', 'comfort', 'black']}, 'time': {'type': 'integer', 'description': 'The maximum amount of time the customer is willing to wait for the ride, in minutes.'}}}}]\n"}, {"role": "user", "content": "T\u00f4i c\u1ea7n m\u1ed9t chuy\u1ebfn Uber lo\u1ea1i 'Plus' t\u1eeb \u0111\u1ecba ch\u1ec9 123 \u0110\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc, Berkeley, CA 94704 v\u00e0 t\u00f4i kh\u00f4ng mu\u1ed1n ch\u1edd qu\u00e1 10 ph\u00fat."}]] | Python | live_simple | live_simple | [{"uber.ride": {"loc": ["123 \u0110\u01b0\u1eddng \u0110\u1ea1i h\u1ecdc, Berkeley, CA", "123 University Street, Berkeley, CA"], "type": ["plus"], "time": [10]}}] |
live_simple_27-7-0 | false | [{"name": "uber.eat.order", "description": "Place an order for food delivery on Uber Eats by specifying the restaurant and the items with their respective quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["restaurant", "items", "quantities"], "properties": {"restaurant": {"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 for the order."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "A list of quantities for each food item, corresponding by index to the items array."}}}}] | [{"type": "function", "function": {"name": "uber_eat_order", "description": "Place an order for food delivery on Uber Eats by specifying the restaurant and the items with their respective quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["restaurant", "items", "quantities"], "properties": {"restaurant": {"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 for the order."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "A list of quantities for each food item, corresponding by index to the items array."}}}}}] | {} | {} | [] | [[{"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 delivery on Uber Eats by specifying the restaurant and the items with their respective quantities. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['restaurant', 'items', 'quantities'], 'properties': {'restaurant': {'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 for the order.'}, 'quantities': {'type': 'array', 'items': {'type': 'integer'}, 'description': 'A list of quantities for each food item, corresponding by index to the items array.'}}}}]\n"}, {"role": "user", "content": "I want to order five 'burgers' and six 'chicken wings' from uber pitada"}]] | Python | live_simple | live_simple | [{"uber.eat.order": {"restaurant": ["uber pitada"], "items": [["burgers", "chicken wings"]], "quantities": [[5, 6]]}}] |
live_simple_28-7-1 | false | [{"name": "uber.eat.order", "description": "Place an order for food delivery on Uber Eats by specifying the restaurant and the items with their respective quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["restaurant", "items", "quantities"], "properties": {"restaurant": {"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 for the order."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "A list of quantities for each food item, corresponding by index to the items array."}}}}] | [{"type": "function", "function": {"name": "uber_eat_order", "description": "Place an order for food delivery on Uber Eats by specifying the restaurant and the items with their respective quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["restaurant", "items", "quantities"], "properties": {"restaurant": {"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 for the order."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "A list of quantities for each food item, corresponding by index to the items array."}}}}}] | {} | {} | [] | [[{"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 delivery on Uber Eats by specifying the restaurant and the items with their respective quantities. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['restaurant', 'items', 'quantities'], 'properties': {'restaurant': {'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 for the order.'}, 'quantities': {'type': 'array', 'items': {'type': 'integer'}, 'description': 'A list of quantities for each food item, corresponding by index to the items array.'}}}}]\n"}, {"role": "user", "content": "\u6211\u60f3\u5728\u80af\u5fb7\u57fa\u4e7010\u4e2a\u9ea6\u8fa3\u9e21\u817f\u5821\uff0c50\u676f\u53ef\u53e3\u53ef\u4e50\uff0c30\u4e2a\u6cb9\u70b8\u9e21\u7fc5\uff0c90\u6839\u85af\u6761"}]] | Python | live_simple | live_simple | [{"uber.eat.order": {"restaurant": ["\u80af\u5fb7\u57fa", "KFC"], "items": [["\u9ea6\u8fa3\u9e21\u817f\u5821", "\u53ef\u53e3\u53ef\u4e50", "\u6cb9\u70b8\u9e21\u7fc5", "\u85af\u6761"]], "quantities": [[10, 50, 30, 90]]}}] |
live_simple_29-7-2 | false | [{"name": "uber.eat.order", "description": "Place an order for food delivery on Uber Eats by specifying the restaurant and the items with their respective quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["restaurant", "items", "quantities"], "properties": {"restaurant": {"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 for the order."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "A list of quantities for each food item, corresponding by index to the items array."}}}}] | [{"type": "function", "function": {"name": "uber_eat_order", "description": "Place an order for food delivery on Uber Eats by specifying the restaurant and the items with their respective quantities. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["restaurant", "items", "quantities"], "properties": {"restaurant": {"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 for the order."}, "quantities": {"type": "array", "items": {"type": "integer"}, "description": "A list of quantities for each food item, corresponding by index to the items array."}}}}}] | {} | {} | [] | [[{"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 delivery on Uber Eats by specifying the restaurant and the items with their respective quantities. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['restaurant', 'items', 'quantities'], 'properties': {'restaurant': {'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 for the order.'}, 'quantities': {'type': 'array', 'items': {'type': 'integer'}, 'description': 'A list of quantities for each food item, corresponding by index to the items array.'}}}}]\n"}, {"role": "user", "content": "I want to go to McDonald's and buy a pizza."}]] | Python | live_simple | live_simple | [{"uber.eat.order": {"restaurant": ["McDonald's"], "items": [["pizza"]], "quantities": [[1]]}}] |
live_simple_30-8-0 | false | [{"name": "aws.lexv2_models.list_exports", "description": "Lists the exports for a bot, bot locale, or custom vocabulary within Amazon Lex. This data is retained for a duration of 7 days. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["botId", "botVersion"], "properties": {"botId": {"type": "string", "description": "The unique identifier for the bot as assigned by Amazon Lex."}, "botVersion": {"type": "string", "description": "The specific version of the bot for which to list the exports."}, "sortBy": {"type": "string", "description": "Determines the field to sort the list of exports by. Can be sorted by 'LastUpdatedDateTime' in ascending or descending order.", "enum": ["ASC", "DESC"], "default": "ASC"}, "filterName": {"type": "string", "description": "The name of the field to filter the exports by. Possible values are 'Bot', 'BotLocale', or 'CustomVocabulary'.", "default": null}, "filterOperator": {"type": "string", "description": "The operator to use for filtering. Use 'EQ' for equality or 'CO' for containing the specified value.", "enum": ["EQ", "CO"], "default": "EQ"}, "filterValue": {"type": "string", "description": "The value to use for filtering the exports based on the filterName.", "default": null}, "maxResults": {"type": "integer", "description": "The maximum number of exports to return in each page of results. If there are fewer results than the max page size, only the actual number of results are returned.", "default": 50}, "nextToken": {"type": "string", "description": "A token to retrieve the next page of results if the response from the ListExports operation contains more results than specified in the maxResults parameter.", "default": null}, "localeId": {"type": "string", "description": "Specifies the locale of the resources that should be exported. If not specified, both bot locales and custom vocabularies are exported.", "default": null}}}}] | [{"type": "function", "function": {"name": "aws_lexv2_models_list_exports", "description": "Lists the exports for a bot, bot locale, or custom vocabulary within Amazon Lex. This data is retained for a duration of 7 days. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["botId", "botVersion"], "properties": {"botId": {"type": "string", "description": "The unique identifier for the bot as assigned by Amazon Lex."}, "botVersion": {"type": "string", "description": "The specific version of the bot for which to list the exports."}, "sortBy": {"type": "string", "description": "Determines the field to sort the list of exports by. Can be sorted by 'LastUpdatedDateTime' in ascending or descending order.", "enum": ["ASC", "DESC"], "default": "ASC"}, "filterName": {"type": "string", "description": "The name of the field to filter the exports by. Possible values are 'Bot', 'BotLocale', or 'CustomVocabulary'.", "default": null}, "filterOperator": {"type": "string", "description": "The operator to use for filtering. Use 'EQ' for equality or 'CO' for containing the specified value.", "enum": ["EQ", "CO"], "default": "EQ"}, "filterValue": {"type": "string", "description": "The value to use for filtering the exports based on the filterName.", "default": null}, "maxResults": {"type": "integer", "description": "The maximum number of exports to return in each page of results. If there are fewer results than the max page size, only the actual number of results are returned.", "default": 50}, "nextToken": {"type": "string", "description": "A token to retrieve the next page of results if the response from the ListExports operation contains more results than specified in the maxResults parameter.", "default": null}, "localeId": {"type": "string", "description": "Specifies the locale of the resources that should be exported. If not specified, both bot locales and custom vocabularies are exported.", "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': 'aws.lexv2_models.list_exports', 'description': 'Lists the exports for a bot, bot locale, or custom vocabulary within Amazon Lex. This data is retained for a duration of 7 days. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['botId', 'botVersion'], 'properties': {'botId': {'type': 'string', 'description': 'The unique identifier for the bot as assigned by Amazon Lex.'}, 'botVersion': {'type': 'string', 'description': 'The specific version of the bot for which to list the exports.'}, 'sortBy': {'type': 'string', 'description': \"Determines the field to sort the list of exports by. Can be sorted by 'LastUpdatedDateTime' in ascending or descending order.\", 'enum': ['ASC', 'DESC'], 'default': 'ASC'}, 'filterName': {'type': 'string', 'description': \"The name of the field to filter the exports by. Possible values are 'Bot', 'BotLocale', or 'CustomVocabulary'.\", 'default': None}, 'filterOperator': {'type': 'string', 'description': \"The operator to use for filtering. Use 'EQ' for equality or 'CO' for containing the specified value.\", 'enum': ['EQ', 'CO'], 'default': 'EQ'}, 'filterValue': {'type': 'string', 'description': 'The value to use for filtering the exports based on the filterName.', 'default': None}, 'maxResults': {'type': 'integer', 'description': 'The maximum number of exports to return in each page of results. If there are fewer results than the max page size, only the actual number of results are returned.', 'default': 50}, 'nextToken': {'type': 'string', 'description': 'A token to retrieve the next page of results if the response from the ListExports operation contains more results than specified in the maxResults parameter.', 'default': None}, 'localeId': {'type': 'string', 'description': 'Specifies the locale of the resources that should be exported. If not specified, both bot locales and custom vocabularies are exported.', 'default': None}}}}]\n"}, {"role": "user", "content": "Could you help me retrieve the list of exports for my bot using the identifier 'my-bot-id' and focusing on version 'v2' sort in ascending? I want max 50 results"}]] | Python | live_simple | live_simple | [{"aws.lexv2_models.list_exports": {"botId": ["my-bot-id"], "botVersion": ["v2"], "sortBy": ["", "ASC"], "filterName": ["", null], "filterOperator": ["", "EQ"], "filterValue": ["", null], "maxResults": ["", 50], "nextToken": ["", null], "localeId": ["", null]}}] |
live_simple_31-8-1 | false | [{"name": "aws.lexv2_models.list_exports", "description": "Lists the exports for a bot, bot locale, or custom vocabulary within Amazon Lex. This data is retained for a duration of 7 days. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["botId", "botVersion"], "properties": {"botId": {"type": "string", "description": "The unique identifier for the bot as assigned by Amazon Lex."}, "botVersion": {"type": "string", "description": "The specific version of the bot for which to list the exports."}, "sortBy": {"type": "string", "description": "Determines the field to sort the list of exports by. Can be sorted by 'LastUpdatedDateTime' in ascending or descending order.", "enum": ["ASC", "DESC"], "default": "ASC"}, "filterName": {"type": "string", "description": "The name of the field to filter the exports by. Possible values are 'Bot', 'BotLocale', or 'CustomVocabulary'.", "default": null}, "filterOperator": {"type": "string", "description": "The operator to use for filtering. Use 'EQ' for equality or 'CO' for containing the specified value.", "enum": ["EQ", "CO"], "default": "EQ"}, "filterValue": {"type": "string", "description": "The value to use for filtering the exports based on the filterName.", "default": null}, "maxResults": {"type": "integer", "description": "The maximum number of exports to return in each page of results. If there are fewer results than the max page size, only the actual number of results are returned.", "default": 50}, "nextToken": {"type": "string", "description": "A token to retrieve the next page of results if the response from the ListExports operation contains more results than specified in the maxResults parameter.", "default": null}, "localeId": {"type": "string", "description": "Specifies the locale of the resources that should be exported. If not specified, both bot locales and custom vocabularies are exported.", "default": null}}}}] | [{"type": "function", "function": {"name": "aws_lexv2_models_list_exports", "description": "Lists the exports for a bot, bot locale, or custom vocabulary within Amazon Lex. This data is retained for a duration of 7 days. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["botId", "botVersion"], "properties": {"botId": {"type": "string", "description": "The unique identifier for the bot as assigned by Amazon Lex."}, "botVersion": {"type": "string", "description": "The specific version of the bot for which to list the exports."}, "sortBy": {"type": "string", "description": "Determines the field to sort the list of exports by. Can be sorted by 'LastUpdatedDateTime' in ascending or descending order.", "enum": ["ASC", "DESC"], "default": "ASC"}, "filterName": {"type": "string", "description": "The name of the field to filter the exports by. Possible values are 'Bot', 'BotLocale', or 'CustomVocabulary'.", "default": null}, "filterOperator": {"type": "string", "description": "The operator to use for filtering. Use 'EQ' for equality or 'CO' for containing the specified value.", "enum": ["EQ", "CO"], "default": "EQ"}, "filterValue": {"type": "string", "description": "The value to use for filtering the exports based on the filterName.", "default": null}, "maxResults": {"type": "integer", "description": "The maximum number of exports to return in each page of results. If there are fewer results than the max page size, only the actual number of results are returned.", "default": 50}, "nextToken": {"type": "string", "description": "A token to retrieve the next page of results if the response from the ListExports operation contains more results than specified in the maxResults parameter.", "default": null}, "localeId": {"type": "string", "description": "Specifies the locale of the resources that should be exported. If not specified, both bot locales and custom vocabularies are exported.", "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': 'aws.lexv2_models.list_exports', 'description': 'Lists the exports for a bot, bot locale, or custom vocabulary within Amazon Lex. This data is retained for a duration of 7 days. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['botId', 'botVersion'], 'properties': {'botId': {'type': 'string', 'description': 'The unique identifier for the bot as assigned by Amazon Lex.'}, 'botVersion': {'type': 'string', 'description': 'The specific version of the bot for which to list the exports.'}, 'sortBy': {'type': 'string', 'description': \"Determines the field to sort the list of exports by. Can be sorted by 'LastUpdatedDateTime' in ascending or descending order.\", 'enum': ['ASC', 'DESC'], 'default': 'ASC'}, 'filterName': {'type': 'string', 'description': \"The name of the field to filter the exports by. Possible values are 'Bot', 'BotLocale', or 'CustomVocabulary'.\", 'default': None}, 'filterOperator': {'type': 'string', 'description': \"The operator to use for filtering. Use 'EQ' for equality or 'CO' for containing the specified value.\", 'enum': ['EQ', 'CO'], 'default': 'EQ'}, 'filterValue': {'type': 'string', 'description': 'The value to use for filtering the exports based on the filterName.', 'default': None}, 'maxResults': {'type': 'integer', 'description': 'The maximum number of exports to return in each page of results. If there are fewer results than the max page size, only the actual number of results are returned.', 'default': 50}, 'nextToken': {'type': 'string', 'description': 'A token to retrieve the next page of results if the response from the ListExports operation contains more results than specified in the maxResults parameter.', 'default': None}, 'localeId': {'type': 'string', 'description': 'Specifies the locale of the resources that should be exported. If not specified, both bot locales and custom vocabularies are exported.', 'default': None}}}}]\n"}, {"role": "user", "content": "Could you retrieve the list of exports for my bot with ID 'B12345' and for version 'v1'? I'm interested in seeing them in descending order by the last updated date."}]] | Python | live_simple | live_simple | [{"aws.lexv2_models.list_exports": {"botId": ["B12345"], "botVersion": ["v1"], "sortBy": ["DESC"], "filterName": ["", null], "filterOperator": ["", "EQ"], "filterValue": ["", null], "maxResults": ["", 50], "nextToken": ["", null], "localeId": ["", null]}}] |
live_simple_32-9-0 | false | [{"name": "answer.string", "description": "Parses the response provided by a Large Language Model (LLM) and returns the answer. If the LLM does not provide an answer, it returns an empty string. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["answer"], "properties": {"answer": {"type": "string", "description": "The answer generated by the Large Language Model in plain text. If the model does not generate an answer, this parameter should be an empty string."}}}}] | [{"type": "function", "function": {"name": "answer_string", "description": "Parses the response provided by a Large Language Model (LLM) and returns the answer. If the LLM does not provide an answer, it returns an empty string. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["answer"], "properties": {"answer": {"type": "string", "description": "The answer generated by the Large Language Model in plain text. If the model does not generate an answer, this parameter should be an empty string."}}}}}] | {} | {} | [] | [[{"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.string', 'description': 'Parses the response provided by a Large Language Model (LLM) and returns the answer. If the LLM does not provide an answer, it returns an empty string. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['answer'], 'properties': {'answer': {'type': 'string', 'description': 'The answer generated by the Large Language Model in plain text. If the model does not generate an answer, this parameter should be an empty string.'}}}}]\n"}, {"role": "user", "content": "Sure, here is the answer to the question:\\n\\n**Logistic regression is not present in the text, therefore I cannot answer this question.**"}]] | Python | live_simple | live_simple | [{"answer.string": {"answer": ["Logistic regression is not present in the text, therefore I cannot answer this question."]}}] |
live_simple_33-10-0 | false | [{"name": "answer.string", "description": "Parses the generated answer from a Large Language Model (LLM) and returns an empty string if the answer indicates that no answer was found. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["answer"], "properties": {"answer": {"type": "string", "description": "The response provided by the LLM in plain text. If the response contains the phrase 'answer not found', this function will return an empty string instead."}}}}] | [{"type": "function", "function": {"name": "answer_string", "description": "Parses the generated answer from a Large Language Model (LLM) and returns an empty string if the answer indicates that no answer was found. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["answer"], "properties": {"answer": {"type": "string", "description": "The response provided by the LLM in plain text. If the response contains the phrase 'answer not found', this function will return an empty string instead."}}}}}] | {} | {} | [] | [[{"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.string', 'description': 'Parses the generated answer from a Large Language Model (LLM) and returns an empty string if the answer indicates that no answer was found. Note that the provided function is in Python 3 syntax.', 'parameters': {'type': 'dict', 'required': ['answer'], 'properties': {'answer': {'type': 'string', 'description': \"The response provided by the LLM in plain text. If the response contains the phrase 'answer not found', this function will return an empty string instead.\"}}}}]\n"}, {"role": "user", "content": "Sure, here is the answer to the question:\\n\\n**Logistic regression is not present in the text, therefore I cannot answer this question.**"}]] | Python | live_simple | live_simple | [{"answer.string": {"answer": ["Logistic regression is not present in the text, therefore I cannot answer this question."]}}] |
live_simple_34-11-0 | false | [{"name": "answer.string", "description": "Parses the answer generated from a Language Learning Model (LLM) and checks for its validity. Returns an empty string if the LLM output is 'answer not found'. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "dict", "required": ["answer"], "properties": {"answer": {"type": "string", "description": "The text response from the LLM in plain text. This should be the raw output provided by the model."}}}}] | [{"type": "function", "function": {"name": "answer_string", "description": "Parses the answer generated from a Language Learning Model (LLM) and checks for its validity. Returns an empty string if the LLM output is 'answer not found'. Note that the provided function is in Python 3 syntax.", "parameters": {"type": "object", "required": ["answer"], "properties": {"answer": {"type": "string", "description": "The text response from the LLM in plain text. This should be the raw output provided by the model."}}}}}] | {} | {} | [] | [[{"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.string', 'description': \"Parses the answer generated from a Language Learning Model (LLM) and checks for its validity. Returns an empty string if the LLM output is 'answer not found'. Note that the provided function is in Python 3 syntax.\", 'parameters': {'type': 'dict', 'required': ['answer'], 'properties': {'answer': {'type': 'string', 'description': 'The text response from the LLM in plain text. This should be the raw output provided by the model.'}}}}]\n"}, {"role": "user", "content": "I asked my language model about logistic regression, and it replied with '**Logistic regression is not present in the text, therefore I cannot answer this question.**' Valid?"}]] | Python | live_simple | live_simple | [{"answer.string": {"answer": ["Logistic regression is not present in the text, therefore I cannot answer this question."]}}] |
End of preview. Expand
in Data Studio
README.md exists but content is empty.
- Downloads last month
- 53