Skip to main content
Set or clear additional context on a language model for inclusion in LLM spans. The context is stored in the model’s metadata and read by FiddlerAgentMiddleware when creating LLM spans. Supports both plain model instances and RunnableBinding. Passing None removes the context so that subsequent spans no longer carry it. This is useful in multi-step agent workflows where context set after a RAG step should not leak into later non-RAG LLM calls.

​
Parameters

​
llm
BaseLanguageModel | RunnableBinding
required
The language model (or binding) to attach context to.
​
context
str | None
default:"None"
The context string to attach, or None to clear.

​
Raises

TypeError – If a RunnableBinding is provided but its bound object is not a BaseLanguageModel.

​
Returns

None Example: default from langchain_openai import ChatOpenAI from fiddler_langchain import set_llm_context model = ChatOpenAI(model=“gpt-4”) set_llm_context(model, “User prefers concise responses”) # Clear context before non-RAG steps set_llm_context(model, None)