Any examples on how to use the library without having to use the .patch method?

[Mistobaan]

Any examples on how to use the library without having to use the .patch method?

[jxnl]

patch is the minimally invasive option imo.

if you wante a group i'd do: https://jxnl.github.io/instructor/concepts/union/

[pawel-krzych]

@Mistobaan you can call OpenAI API endpoint directly and set functions and function_call in this way:

from instructor.function_calls import OpenAISchema, openai_schema

if not issubclass(response_model, OpenAISchema):
    response_model = openai_schema(response_model)
payload["functions"] = [response_model.openai_schema]
payload["function_call"] = {"name": response_model.openai_schema["name"]}

response_model is a class inheriting the BaseModel from Pydantic.

Then from the response:

            message = response["choices"][0]["message"]
            function_call = message["function_call"]
            arguments_str = function_call["arguments"]
            arguments_str = arguments_str.replace("\n", "").replace(",}", "}")
            arguments = json.loads(arguments_str, strict=False)
            response = response_model(**arguments)
            response = response.model_dump()