LLMExtractionStrategy update???

[radiorealm]

I was trying out this code for my school project: https://leonardo467.gumroad.com/l/cstsu

And it seems like the library has changed, because it said "use llmconfig = Llmconfig(provider=...) instead of provider=..."

So here's the part of the code I've changed:

llm_strategy = LLMExtractionStrategy(
        llm_config=LLMConfig(provider="grok/grok-chat"),
        api_token=os.getenv('API_KEY'),
        schema=Product.model_json_schema(),
        extraction_type="schema",
        instruction=INSTRUCTION_TO_LLM,
        chunk_token_threshold=1000,
        overlap_rate=0.0,
        apply_chunking=True,
        input_format="markdown",
        extra_args={"temperature": 0.0, "max_tokens": 800},
    )

And here what it says:

litellm.BadRequestError: LLM Provider NOT provided. Pass in the LLM provider  are trying to call.
You passed model=grok/grok-chat\n Pass model as E.g. For 'Huggingface' inference endpoints pass in
completion(model='huggingface/starcoder',..) Learn more: https://docs.litellm.ai/docs/providers

I've checked the site. I may be blind or stupid, but I dont see how litellm and LLMConfig are connected and, more importantly, how to fix this error.

Since there is no documentation about LLMConfig...

[aravindkarnam]

@radiorealm You are right. There's been some recent patches that were released, related to LLMConfig(which is correct as opposed to LlmConfig), but the documentation didn't catchup. We'll update the docs soon! Thanks for bringing it up!