Official package

LangChain

The official LangChain integration for Crawleo. Use real-time web search and crawling as tools in your LangChain agents and pipelines.

PyPI package

What you get

CrawleoSearch

Real-time web search with multiple output formats.

CrawleoCrawler

Extract content from 1-20 URLs per request.

Async support

Async-compatible for concurrent, high-throughput runs.

Tool calling

Works as a standard tool with any LangChain agent.

Clean output

Markdown, HTML, enhanced HTML, or plain text.

Private by default

We don't train AI on your data, and we don't sell it.

Quick start

Installation

pip install -U langchain-crawleo

Set your API key

import os

os.environ["CRAWLEO_API_KEY"] = "your-api-key"

CrawleoSearch - basic usage

from langchain_crawleo import CrawleoSearch

search_tool = CrawleoSearch(max_pages=1, cc="US", markdown=True)

result = search_tool.invoke({"query": "What is the future of AI?"})
print(result)

Use it inside a LangChain agent

from langchain_crawleo import CrawleoSearch, CrawleoCrawler
from langchain.agents import initialize_agent, AgentType
from langchain_openai import ChatOpenAI

search_tool = CrawleoSearch(max_pages=1, cc="US", markdown=True)
crawler_tool = CrawleoCrawler(markdown=True)

llm = ChatOpenAI(model="gpt-4o", temperature=0)

agent = initialize_agent(
    tools=[search_tool, crawler_tool],
    llm=llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True,
)

response = agent.run("Search for SpaceX news and summarize the top result")
print(response)

Parameters

CrawleoSearch

Parameter	Type	Required	Description
`query`	str	Yes	A natural-language search query.
`max_pages`	int	No	Result pages to fetch. Default: 1.
`setLang`	str	No	Interface language, e.g. "en". Default: "en".
`cc`	str	No	Country code, e.g. "US", "GB", "DE".
`device`	str	No	"desktop", "mobile", or "tablet". Default: "desktop".
`markdown`	bool	No	Return content as Markdown. Default: True.

CrawleoCrawler

Parameter	Type	Required	Description
`urls`	list[str]	Yes	URLs to crawl (1-20).
`raw_html`	bool	No	Return raw HTML. Default: False.
`markdown`	bool	No	Return Markdown. Default: False.

Build with real-time web data

Get 500 free credits a month and add Crawleo tools to your LangChain app.

Start free

What you get

CrawleoSearch

Real-time web search with multiple output formats.

CrawleoCrawler

Extract content from 1-20 URLs per request.

Async support

Async-compatible for concurrent, high-throughput runs.

Tool calling

Works as a standard tool with any LangChain agent.

Clean output

Markdown, HTML, enhanced HTML, or plain text.

Private by default

We don't train AI on your data, and we don't sell it.

Quick start

Installation

pip install -U langchain-crawleo

Set your API key

import os

os.environ["CRAWLEO_API_KEY"] = "your-api-key"

CrawleoSearch - basic usage

from langchain_crawleo import CrawleoSearch

search_tool = CrawleoSearch(max_pages=1, cc="US", markdown=True)

result = search_tool.invoke({"query": "What is the future of AI?"})
print(result)

Use it inside a LangChain agent

from langchain_crawleo import CrawleoSearch, CrawleoCrawler
from langchain.agents import initialize_agent, AgentType
from langchain_openai import ChatOpenAI

search_tool = CrawleoSearch(max_pages=1, cc="US", markdown=True)
crawler_tool = CrawleoCrawler(markdown=True)

llm = ChatOpenAI(model="gpt-4o", temperature=0)

agent = initialize_agent(
    tools=[search_tool, crawler_tool],
    llm=llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True,
)

response = agent.run("Search for SpaceX news and summarize the top result")
print(response)

Parameters

CrawleoSearch

Parameter	Type	Required	Description
`query`	str	Yes	A natural-language search query.
`max_pages`	int	No	Result pages to fetch. Default: 1.
`setLang`	str	No	Interface language, e.g. "en". Default: "en".
`cc`	str	No	Country code, e.g. "US", "GB", "DE".
`device`	str	No	"desktop", "mobile", or "tablet". Default: "desktop".
`markdown`	bool	No	Return content as Markdown. Default: True.

CrawleoCrawler

Parameter	Type	Required	Description
`urls`	list[str]	Yes	URLs to crawl (1-20).
`raw_html`	bool	No	Return raw HTML. Default: False.
`markdown`	bool	No	Return Markdown. Default: False.