Your company,
searchable by AI.

# Full RAG loop — embed → retrieve → generate
async def handle_chat_stream(
    query: str,
    conversation_id: UUID,
    user_id: UUID,
):
    # 1. Embed the question
    query_vec = await embedding_service.get_embedding(query)

    # 2. Cosine similarity search (pgvector)
    chunks = await retrieval_service.search_similar_chunks(
        embedding=query_vec,
        user_id=user_id,
        top_k=5,
    )

    # 3. Build context from top-5 chunks
    context = build_source_context(chunks)
    history = await get_last_messages(
        conversation_id, limit=10,
    )

    # 4. Stream answer from Claude
    async for token in ai_service.stream_answer(
        query=query,
        context=context,
        history=history,
    ):
        yield f"data: {token}\n\n"

    # 5. Persist message + sources
    await store_message(
        conversation_id, answer, sources, confidence,
    )