Dataset Viewer
id
stringclasses 2
values | dataset
stringclasses 2
values | prompt_text
stringclasses 2
values | answer
stringclasses 2
values | task_type
stringclasses 1
value | tools_available
stringclasses 2
values | conversation_length
int64 3
3
| tool_count
int64 1
1
| has_function_calls
bool 1
class |
|---|---|---|---|---|---|---|---|---|
xlam_sample_0
|
xlam
|
[{"role": "system", "content": "You are an expert in composing functions. Here is a list of functions in JSON format that you can invoke: # Tool\n\nHere is a list of functions in JSON format that you can invoke:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"weather_api\", \"description\": \"Get weather information\", \"parameters\": {\"city\": {\"type\": \"string\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n"}, {"role": "user", "content": "What's the weather in New York?"}, {"role": "assistant", "content": "[{\"name\": \"weather_api\", \"arguments\": {\"city\": \"New York\"}}]"}]
|
[{"name": "weather_api", "arguments": {"city": "New York"}}]
|
function_calling
|
["weather_api"]
| 3 | 1 | true |
toolace_sample_0
|
toolace_single_turn
|
[{"role": "system", "content": "You are an expert in composing functions. Here is a list of functions in JSON format that you can invoke: # Tool\n\nHere is a list of functions in JSON format that you can invoke:\n\n<tools>\n{\"type\": \"function\", \"function\": {\"name\": \"calculator\", \"description\": \"Perform mathematical calculations\", \"parameters\": {\"expression\": {\"type\": \"string\"}}}}\n</tools>\n\nIn each action step, you MUST: \n1. Think about the reasoning process in the mind and enclosed your reasoning within <think> </think> XML tags.\n2. Then, provide a json object with function names and arguments within <tool_call></tool_call> XML tags. i.e., <tool_call>[{\"name\": <function-name>, \"arguments\": <args-json-object>}, {\"name\": <function-name2>, \"arguments\": <args-json-object2>}, ...]</tool_call>\n3. Make sure both the reasoning and the tool call steps are included together in one single reply.\nA complete reply example is: <think>To address the query, I need to send the email to Bob and then buy the banana through walmart. </think> <tool_call> [{\"name\": \"email\", \"arguments\": {\"receiver\": \"Bob\", \"content\": \"I will bug banana through walmart\"}}, {\"name\": \"walmart\", \"arguments\": {\"input\": \"banana\"}}]</tool_call>. Please make sure the type of the arguments is correct. \n"}, {"role": "user", "content": "Calculate 2 + 2"}, {"role": "assistant", "content": "[{\"name\": \"calculator\", \"arguments\": {\"expression\": \"2 + 2\"}}]"}]
|
[{"name": "calculator", "arguments": {"expression": "2 + 2"}}]
|
function_calling
|
["calculator"]
| 3 | 1 | true |
README.md exists but content is empty.
- Downloads last month
- 112