Function Calls

For models that supports function calls, you can pass functions information to the model/assistant, just as the original OpenAI does.

The model/assistant will then call the function when they think necessary, and use the result in the conversation.

Here's an example of a function that fetches current weather information for a given location:

functions = [
    {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {
                    "type": "string",
                    "description": "The city and state, e.g. San Francisco, CA",
                },
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["location"],
        },
    }
]

Let's pass it to the assistant or model and request it to generate a response, with OpenAI Python client as gateway:

response = client.chat.completions.create(
    model="YOUR_TASKINGAI_MODEL_ID", 
    messages=[
        {"role": "system", "content": "You can ask me about the latest weather information of a city."},
        {"role": "user", "content": "How's the weather now in Seattle?"}
    ],
    functions=functions,
)

Tool calls compatible with OpenAI

Function call was deprecated in OpenAI API, and tool_calls was introduced as a replacement. TaskingAI's OpenAI-compatible API supports both functions and tool_calls for backward compatibility.

Here's an example of a tool call that calculates the sum of two variables to the model. Note that the schema is different than using functions:

tools = [
  {
    "type": "function",
    "function": {
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA",
          },
          "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
        },
        "required": ["location"],
      },
    }
  }
]

response = client.chat.completions.create(
    model="YOUR_TASKINGAI_MODEL_ID",  
    messages=[
        {"role": "system", "content": "You can ask me about the latest weather information of a city."},
        {"role": "user", "content": "How's the weather now in Seattle?"}
    ],
    tools=tools,
)