RAG over User History

from openai import AsyncOpenAI
from maximem_synap import MaximemSynapSDK, ContextType

sdk = MaximemSynapSDK(api_key=...)
openai = AsyncOpenAI()
await sdk.initialize()

async def search_user_history(user_id: str, customer_id: str, query: str, top_k: int = 8):
    """Pure RAG: return raw memory chunks ranked by relevance to `query`."""
    ctx = await sdk.user.context.fetch(
        user_id=user_id,
        customer_id=customer_id,
        search_query=[query],
        max_results=top_k,
        types=[ContextType.FACTS, ContextType.EPISODES],
        mode="accurate",                # graph-aware ranking
    )

    # Sort facts and episodes by relevance using their respective scores
    hits = (
        [(f.confidence, "fact", f.content) for f in ctx.facts] +
        [(e.significance, "episode", e.summary) for e in ctx.episodes]
    )
    hits.sort(key=lambda h: h[0], reverse=True)
    return hits[:top_k]


async def rag_chat(user_id: str, customer_id: str, user_message: str) -> str:
    hits = await search_user_history(user_id, customer_id, user_message)

    citations = "\n".join(f"[{i+1}] ({kind}) {text}" for i, (score, kind, text) in enumerate(hits))
    system_prompt = (
        "Answer the user's question using ONLY the citations below. "
        "Cite by number. If the answer isn't in the citations, say you don't know.\n\n"
        f"Citations:\n{citations}"
    )

    completion = await openai.chat.completions.create(
        model="gpt-4o",
        messages=[
            {"role": "system", "content": system_prompt},
            {"role": "user", "content": user_message},
        ],
    )
    return completion.choices[0].message.content