444 Context Retrieval - Scratch PR

[aidando73]

No description provided.

[aidando73]

        user_prompts = [
            "Which family of models was released on October 24, 2024?",
            "What about Llama 3.1 family of models, what is the release date for it?",
        ]

[aidando73]

        user_prompts = [
            "When was the Llama 3.2 family of models released?",
            # "What about Llama 3.1 family of models, what is the release date for it?",
        ]

[aidando73]

The RAG only retrieve the context from llama3.2 model card for first message but did not do retrieval for the second message, the context is still llama3.2 model card from first message.

✅ Is this true? How are we choosing which document to load up? - no it's not true: the context is being loaded up

aidando73/llama-stack#3 (comment)