Hi all! Swirl sends queries to existing search engines, unifies the results and re-ranks them all using large language models. It solves cross-silo information access and search problems in a fraction of the time and effort required to copy, ingest and index data.
Here's a brief video intro: https://youtu.be/sfsBYyu6qDQ
Swirl was written in python atop the django/celery/redis stack with a choice of Sqlite3 or PostgreSQL back-ends. The source code is available under the Apache 2.0 license. The distribution includes zero-code configs for Apache Solr, ChatGPT, Elastic Search, OpenSearch, PostgreSQL, Google BigQuery, RequestsGet, Google PSE, NLResearch.com, Miro, Microsoft 365, Atlassian, YouTrack, GitHub, HubSpot & more. Plug-in your access tokens or use Microsoft 365 to login and users can stop searching and start Swirling!
Links:
We are seeking contributions and feedback from developers working on all kinds of search solutions... thanks!
Top comments (1)
Wow!! Great stuff.