> ## Documentation Index
> Fetch the complete documentation index at: https://docs.keenable.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# GPT Researcher

> gpt-researcher-keenable, a retriever plugin that gives GPT Researcher Keenable web search with no API key.

*Retriever plugin*

`gpt-researcher-keenable` adds Keenable to [GPT Researcher](https://github.com/assafelovic/gpt-researcher) as a retriever. GPT Researcher discovers it through its plugin entry point, so nothing in GPT Researcher itself changes, and it works without an API key.

→ [gpt-researcher-keenable on PyPI](https://pypi.org/project/gpt-researcher-keenable/)

## Install

```bash theme={"system"}
pip install gpt-researcher-keenable
```

It needs GPT Researcher 0.16.1 or later.

## Select it

```bash theme={"system"}
export RETRIEVER=keenable
```

It combines with the built-in retrievers like any other name, for example `RETRIEVER=keenable,arxiv`.

## How results are used

* Each result gives GPT Researcher a title, a URL and a short preview of the page; GPT Researcher then scrapes the pages it keeps, as it does with its built-in web retrievers.
* `MAX_SEARCH_RESULTS_PER_QUERY` is passed through as the number of results (1 to 50).
* With `query_domains`, the search is restricted to the first domain.
* A network or API failure is logged and returns no results, so one retriever cannot stop a research run.

<Note>
  Without a key, searches run on the shared public tier at [lower rate limits](/rate-limits). Set `KEENABLE_API_KEY` to use your organization's limits and remove the hourly cap.
</Note>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.