[FEATURE] Provide Custom LLM Support

[mvenkatsriram]

Feature Area

Core functionality

Is your feature request related to a an existing bug? Please link it here.

NA

Describe the solution you'd like

We have Enterprise LLM Gateway which encapsulates External Endpoints of several LLMs. Instead of API Key based authentication, we have JWT based authentication.

When I try to inherit the crewai.LLM class and override call method and removed the dependency of litellm. When We tried the sample research agent. we get the following error

Error:
AuthenticationError: litellm.AuthenticationError: AuthenticationError: OpenAIException - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable

Is there a way CrewAI provides a functionality similar to langchain_core.language_models.chat_models.BaseChatModel

Describe alternatives you've considered

NA

Additional context

No response

Willingness to Contribute

I could provide more detailed specifications

[lorenzejay]

cc: @bhancockio

[TaylorPzreal]

provider not worked, it's seems that 'provider' does not transfter to litellm.

I got the error "Error during LLM call: litellm.AuthenticationError: AuthenticationError: OpenAIException - The api_key client option must be set either by passing api_key to the client or by setting the OPENAI_API_KEY environment variable"

LLM(
            provider="custom",
            model="custom-gpt-4", 
            base_url="https://xxx",
            api_key=os.getenv("API_KEY"),
            temperature=0.5,
            timeout=480,
            context_window=4096,
            max_tokens=4000,
        )