Exemplos em Python: pesquisar, rodar consultas em paralelo, responder com citações

import os
import pathlib

import requests

resp = requests.post(
    "https://llmwebsearch.com/api/v1/search",
    headers={"Authorization": "Bearer " + os.environ["LLMWEBSEARCH_API_KEY"]},
    json={"q": "how to size a postgres connection pool", "max_results": 5, "read": 3},
    timeout=60,
)
resp.raise_for_status()
data = resp.json()
out = pathlib.Path("sources")
out.mkdir(exist_ok=True)
for r in data["results"]:
    if r["content_status"] != "ok":
        print("skip", r["position"], r["content_status"], r["url"])
        continue
    path = out / f"{r['position']:02d}.md"
    path.write_text("Source: " + r["url"] + "\n\n" + r["content"], encoding="utf-8")
    print("saved", path, r["word_count"], "words")
print("credits used:", data["credits_used"])

import asyncio
import os

import httpx

API = "https://llmwebsearch.com/api/v1/search"
HEADERS = {"Authorization": "Bearer " + os.environ["LLMWEBSEARCH_API_KEY"]}
QUESTIONS = [
    "what is connection pooling in postgres",
    "recommended pool size per cpu core",
    "pgbouncer transaction mode limitations",
    "connection pool exhaustion symptoms",
]


async def search(client, sem, q):
    async with sem:
        resp = await client.post(API, json={"q": q, "read": 2, "max_chars": 4000})
        if resp.status_code != 200:
            return q, resp.json().get("error", {}).get("code"), []
        data = resp.json()
        read = [r["url"] for r in data["results"] if r["content_status"] == "ok"]
        return q, "ok", read


async def main():
    sem = asyncio.Semaphore(4)
    async with httpx.AsyncClient(headers=HEADERS, timeout=60) as client:
        for q, status, urls in await asyncio.gather(*(search(client, sem, q) for q in QUESTIONS)):
            print(status, q, urls)


asyncio.run(main())

import os

import requests

SEARCH = "https://llmwebsearch.com/api/v1/search"
KEY = os.environ["LLMWEBSEARCH_API_KEY"]
BUDGET_CHARS = 6000 * 4  # about 6,000 tokens of sources


def sources_for(question):
    resp = requests.post(SEARCH, headers={"Authorization": "Bearer " + KEY},
                         json={"q": question, "max_results": 5, "read": 3}, timeout=60)
    resp.raise_for_status()
    results = resp.json()["results"]
    share = BUDGET_CHARS // max(len(results), 1)
    blocks = []
    for i, r in enumerate(results, start=1):
        if r["content_status"] == "ok":
            body = r["content"][:share]
        else:
            body = "(snippet only) " + r["snippet"]
        blocks.append(f"[{i}] {r['title']} - {r['url']}\n{body}")
    return "\n\n".join(blocks)


def answer(question):
    prompt = ("Answer the question using only the sources below. "
              "Cite them as [1], [2] and so on. Say so if the sources do not answer it.\n\n"
              + sources_for(question) + "\n\nQuestion: " + question)
    resp = requests.post(
        os.environ["LLM_BASE_URL"].rstrip("/") + "/chat/completions",
        headers={"Authorization": "Bearer " + os.environ["LLM_API_KEY"]},
        json={"model": os.environ["LLM_MODEL"], "messages": [{"role": "user", "content": prompt}]},
        timeout=120,
    )
    resp.raise_for_status()
    return resp.json()["choices"][0]["message"]["content"]


print(answer("How should I size a Postgres connection pool?"))