Classmethods

WARNING:llama_index.core.chat_engine.types:Encountered exception writing response to history: Error code: 400 - {'error': {'message': '\'define_function(name: str, description: str, arguments: str, packages: str, code: str) -> str\\n\\n        Define a function to add to the context of the conversation. Necessary Python packages must be declared.\\n        Once defined, the assistant may decide to use this function, respond with a normal message.\\n\\n        Parameters:\\n        name (str): The name of the function to define. This will be used as the identifier for the function in the conversation context.\\n        description (str): A short description of the function. This should clearly explain the purpose and functionality of the function.\\n        arguments (str): JSON schema of arguments encoded as a string. This schema defines the expected arguments for the function.\\n                         Example format: \\\'{ "url": { "type": "string", "description": "The URL" }}\\\'. The schema should specify the type\\n                         and description for each argument.\\n\\n\\n        Returns:\\n        str: A message indicating that a function has been successfully added to the context of the conversation, along with its description.\\n        \' is too long - \'tools.0.function.description\' (request id: 2024040908542331434894662876070)', 'type': 'invalid_request_error', 'param': '', 'code': None}}

tool_specs = [t.metadata.to_openai_tool() for t in tools]

response = client.chat.completions.create(
    messages=message_dicts,
    stream=False,
    tools=tool_specs,
    model=model,
    temperature=temperature,
    ....
)