OpenAI function calling: give the model a search_web tool

import json
import os

import requests
from openai import OpenAI

client = OpenAI()
MODEL = os.environ["OPENAI_MODEL"]  # any model that supports function calling
SEARCH = "https://llmwebsearch.com/api/v1/search"

tools = [
    {
        "type": "function",
        "name": "search_web",
        "description": "Search the live web. Returns numbered sources with URLs; the first `read` include page text. Cite sources as [1], [2].",
        "parameters": {
            "type": "object",
            "properties": {
                "query": {"type": "string", "description": "What to search for, as a person would type it."},
                "read": {"type": "integer", "minimum": 0, "maximum": 10, "description": "How many top results to read in full."},
            },
            "required": ["query"],
            "additionalProperties": False,
        },
    }
]


def search_web(query, read=3):
    resp = requests.post(
        SEARCH,
        headers={"Authorization": "Bearer " + os.environ["LLMWEBSEARCH_API_KEY"]},
        json={"q": query, "max_results": 5, "read": read, "max_chars": 5000},
        timeout=60,
    )
    if resp.status_code != 200:
        return "Search failed: " + resp.json().get("error", {}).get("code", str(resp.status_code))
    parts = []
    for i, r in enumerate(resp.json()["results"], start=1):
        text = r["content"] if r["content_status"] == "ok" else "(snippet only) " + r["snippet"]
        parts.append(f"[{i}] {r['title']} - {r['url']}\n{text}")
    return "\n\n".join(parts)


input_list = [{"role": "user", "content": "How should I size a Postgres connection pool?"}]
for _ in range(5):
    response = client.responses.create(model=MODEL, tools=tools, input=input_list)
    calls = [item for item in response.output if item.type == "function_call"]
    if not calls:
        print(response.output_text)
        break
    input_list += response.output
    for item in calls:
        args = json.loads(item.arguments)
        output = search_web(args["query"], int(args.get("read", 3)))
        input_list.append({"type": "function_call_output", "call_id": item.call_id, "output": output})

import os

import requests
from agents import Agent, Runner
from agents.decorators import tool


@tool
def search_web(query: str, read: int = 3) -> str:
    """Search the live web and return numbered sources with their URLs.

    Args:
        query: What to search for, as a person would type it.
        read: How many top results to read in full, from 0 to 10.
    """
    resp = requests.post(
        "https://llmwebsearch.com/api/v1/search",
        headers={"Authorization": "Bearer " + os.environ["LLMWEBSEARCH_API_KEY"]},
        json={"q": query, "max_results": 5, "read": max(0, min(read, 10)), "max_chars": 5000},
        timeout=60,
    )
    resp.raise_for_status()
    parts = []
    for i, r in enumerate(resp.json()["results"], start=1):
        text = r["content"] if r["content_status"] == "ok" else "(snippet only) " + r["snippet"]
        parts.append(f"[{i}] {r['title']} - {r['url']}\n{text}")
    return "\n\n".join(parts)


agent = Agent(
    name="Researcher",
    instructions="Answer from search_web results only and cite them as [1], [2].",
    tools=[search_web],
)
result = Runner.run_sync(agent, "How should I size a Postgres connection pool?")
print(result.final_output)