GPT Researcher - Keenable

Retriever plugin gpt-researcher-keenable adds Keenable to 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

Install

pip install gpt-researcher-keenable

It needs GPT Researcher 0.16.1 or later.

Select it

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.

Without a key, searches run on the shared public tier at lower rate limits. Set KEENABLE_API_KEY to use your organization’s limits and remove the hourly cap.