Firecrawl + LlamaIndex

pip install -U llama-index-core llama-index-llms-openai llama-index-embeddings-openai llama-index-readers-web firecrawl-py
export FIRECRAWL_API_KEY="fc-YOUR-API-KEY"
export OPENAI_API_KEY="sk-YOUR-API-KEY"

from firecrawl import Firecrawl
from llama_index.core.tools import FunctionTool

firecrawl = Firecrawl()

def web_search(query: str) -> str:
    """Search the web with Firecrawl and return titles, URLs and descriptions."""
    results = firecrawl.search(query, limit=5)
    return "\n\n".join(f"{r.title}\n{r.url}\n{r.description}" for r in (results.web or []))

search_tool = FunctionTool.from_defaults(fn=web_search)

import asyncio

from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

agent = FunctionAgent(
    tools=[search_tool],
    llm=OpenAI(model="gpt-6-luna"),
    system_prompt="Use web_search for anything current and cite the URLs you used.",
)

async def main():
    response = await agent.run("What did LlamaIndex release this month?")
    print(response)

asyncio.run(main())

import os

from llama_index.core import VectorStoreIndex
from llama_index.readers.web import FireCrawlWebReader

reader = FireCrawlWebReader(
    api_key=os.environ["FIRECRAWL_API_KEY"],
    mode="search",
    params={"limit": 5},
)
documents = reader.load_data(query="LlamaIndex agent workflows")
index = VectorStoreIndex.from_documents(documents)