RAG チャットボット API — 本番環境の Claude 搭載ナレッジベースアシスタント

from openai import OpenAI
client = OpenAI(api_key="sk-kn-...", base_url="https://api.kunavo.com/v1")

def chat(question: str, history: list[dict]) -> dict:
    chunks = hybrid_retrieve(question, k=5)  # vector + BM25
    context = "\n\n---\n\n".join(
        f"[doc:{c['id']}] {c['text']}" for c in chunks
    )
    resp = client.chat.completions.create(
        model="claude-sonnet-5",
        messages=[
            {"role": "system", "content": [{
                "type": "text",
                "text": (
                    "Answer only from Context. Cite [doc:N] for each claim. "
                    "If Context doesn't answer, say 'I don't have that.' "
                    "Be concise, no throat-clearing."
                ),
                "cache_control": {"type": "ephemeral"},
            }]},
            *history,
            {"role": "user", "content": f"# Context\n{context}\n\n# Q\n{question}"},
        ],
        max_tokens=600,
    )
    answer = resp.choices[0].message.content
    cited_ids = parse_citations(answer)  # extract [doc:N] references
    return {"answer": answer, "sources": [c for c in chunks if c["id"] in cited_ids]}