用网页搜索 API 在 Python 中构建 deep research agent

import os

import requests

SEARCH = "https://llmwebsearch.com/api/v1/search"
SEARCH_HEADERS = {"Authorization": "Bearer " + os.environ["LLMWEBSEARCH_API_KEY"]}
# Any OpenAI-compatible chat endpoint works here: set your own base URL, key and model name.
LLM_URL = os.environ.get("LLM_BASE_URL", "https://llm.example.com/v1") + "/chat/completions"
LLM_HEADERS = {"Authorization": "Bearer " + os.environ.get("LLM_API_KEY", "")}
MODEL = os.environ.get("LLM_MODEL", "your-model-name")


def ask_llm(prompt):
    body = {"model": MODEL, "messages": [{"role": "user", "content": prompt}]}
    resp = requests.post(LLM_URL, headers=LLM_HEADERS, json=body, timeout=120)
    resp.raise_for_status()
    return resp.json()["choices"][0]["message"]["content"]


def plan_queries(question, n=4):
    text = ask_llm(f"Write {n} short web search queries, one per line, to answer: {question}")
    queries = [line.strip("-*0123456789. ").strip() for line in text.splitlines()]
    return [q for q in queries if q][:n]


def search(query):
    body = {"q": query, "max_results": 5, "read": 3, "max_chars": 5000}
    resp = requests.post(SEARCH, headers=SEARCH_HEADERS, json=body, timeout=60)
    resp.raise_for_status()
    return resp.json()["results"]


def research(question, rounds=2):
    sources = {}  # url -> result, so the same page is never cited twice
    queries = plan_queries(question)
    for _ in range(rounds):
        for query in queries:
            for r in search(query):
                if r.get("content_status") == "ok" and r["url"] not in sources:
                    sources[r["url"]] = r
        notes = "\n".join(f"- {r['title']}" for r in sources.values())
        queries = plan_queries(f"{question}\nAlready found:\n{notes}\nWhat is still missing?", n=2)
    numbered = list(sources.values())[:12]
    context = "\n\n".join(
        f"[{i}] {r['title']} ({r['url']})\n{r['content']}" for i, r in enumerate(numbered, 1)
    )
    prompt = (
        "Answer the question using only the sources below. Cite them as [1], [2]. "
        "Say so when the sources disagree or do not cover a point.\n\n"
        f"Question: {question}\n\nSources:\n{context}"
    )
    return ask_llm(prompt), [r["url"] for r in numbered]


if __name__ == "__main__":
    answer, urls = research("What changed in the EU rules for general-purpose AI models in 2025?")
    print(answer)
    for i, url in enumerate(urls, 1):
        print(f"[{i}] {url}")