Skip to main content
Tool package Give any LangChain agent web search and page fetch with the KeenableSearch and KeenableFetch tools. langchain-keenable is a partner package, listed in the provider index of the LangChain docs. → langchain-keenable on PyPI The demo installs the package with pip, then calls KeenableSearch().invoke, which returns live web results.

Install

Use the tools

Search the web, then fetch the first result:
Each search result has a url, which you pass to KeenableFetch to get the page.
Set KEENABLE_API_KEY to remove the hourly request cap. If you don’t set a key, calls run on the shared keyless tier, which allows 1,000 requests per hour per IP address. See Rate limits.

LlamaIndex

Give LlamaIndex agents web search and page reading with the Keenable ToolSpec.

Haystack

Add web search and page fetch to Haystack pipelines with the Keenable components.

LazyLLM

Search the web from LazyLLM with KeenableSearch, a built-in search tool that works without an API key. Install LazyLLM from its main branch.

Tool calling

Give an LLM web search and page fetch as tools. Pass the SDK’s TOOLS to any OpenAI-compatible chat completions client and run each call with run_tool_call.