企業知識庫與 RAG

import os
import requests
from openai import OpenAI

API_KEY = os.environ["TUTUJIN_API_KEY"]
client = OpenAI(base_url="https://www.tutujin.com/v1", api_key=API_KEY)


def embed(texts):
    """Turn document chunks or a question into vectors."""
    resp = client.embeddings.create(model="text-embedding-3-large", input=texts)
    return [d.embedding for d in resp.data]


def rerank(query, docs, top_n=5):
    """Re-score retrieved chunks and keep the most relevant ones."""
    r = requests.post(
        "https://www.tutujin.com/v1/rerank",
        headers={"Authorization": f"Bearer {API_KEY}"},
        json={"model": "qwen3-reranker-8b", "query": query, "documents": docs, "top_n": top_n},
        timeout=30,
    )
    r.raise_for_status()
    return [docs[x["index"]] for x in r.json()["results"]]


def answer(question, chunks):
    context = "\n\n".join(f"[{i + 1}] {c}" for i, c in enumerate(chunks))
    resp = client.chat.completions.create(
        model="deepseek-v4.1-flash",
        messages=[
            {"role": "system", "content": "Answer only from the given sources and cite them like [1]. If the sources do not say, reply that you do not know."},
            {"role": "user", "content": f"Sources:\n{context}\n\nQuestion: {question}"},
        ],
        temperature=0.2,
    )
    return resp.choices[0].message.content


# candidates = your_vector_db.search(embed([question])[0], k=20)
# print(answer(question, rerank(question, candidates)))