ollama/server/testdata/tools/xlam.out

40 lines
1.8 KiB
Text
Raw Normal View History

You are a knowledgable assistant. You can answer questions and perform tasks.
### Instruction:
What's the weather like today in Paris?
### Response:
{"tool_calls": [{"name": "get_current_weather", "arguments": {"format":"celsius","location":"Paris, France"}}]}
<|EOT|>
### Response:
The current temperature in Paris, France is 22 degrees Celsius.
<|EOT|>
### Instruction:
[BEGIN OF TASK INSTRUCTION]
You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you will need to make one or more function/tool calls to achieve the purpose.
If none of the functions can be used, point it out and refuse to answer.
If the given question lacks the parameters required by the function, also point it out.
[END OF TASK INSTRUCTION]
[BEGIN OF AVAILABLE TOOLS]
[{"type":"function","function":{"name":"get_current_weather","description":"Get the current weather","parameters":{"type":"object","required":["location","format"],"properties":{"format":{"type":"string","description":"The temperature unit to use. Infer this from the users location.","enum":["celsius","fahrenheit"]},"location":{"type":"string","description":"The city and state, e.g. San Francisco, CA"}}}}}]
[END OF AVAILABLE TOOLS]
[BEGIN OF FORMAT INSTRUCTION]
The output MUST strictly adhere to the following JSON format, and NO other text MUST be included.
The example format is as follows. Please make sure the parameter type is correct. If no function call is needed, please make tool_calls an empty list '[]'.
```
{
"tool_calls": [
{"name": "func_name1", "arguments": {"argument1": "value1", "argument2": "value2"}},
... (more tool calls as required)
]
}
```
[END OF FORMAT INSTRUCTION]
[BEGIN OF QUERY]
What's the weather like today in San Francisco and Toronto?
[END OF QUERY]
### Response: