swirl-search

Not just me, but our team is building: https://github.com/swirlai/swirl-search We are trying to build an AI metasearch engine that does RAG and Chat based on your office documents. Without any ETL or a vector database.

You can try: https://github.com/swirlai/swirl-search - doesn't indexes data - has connectors to various apps - metasearch under the hood - re-ranking of search results before RAG

You could try SWIRL Search. I have found API integration from different apps without ETL pretty good. https://github.com/swirlai/swirl-search

Swirl Is an Open-Source Search engine alternative to Algolia, and the likes. But Swirl queries anything with an API then uses Large Language Models to re-rank the unified results without copying any data! If the database has an API it can connect to and provide search functionality. You can use it to generate AI insights over a large and spread-out database. Check the website: https://swirl.today/ GitHub: https://github.com/swirlai/swirl-search

Hello! Great question...we recently had someone ask this in a GitHub Discussion post as well. You might find Sid's replies on this helpful: https://github.com/swirlai/swirl-search/discussions/597

Thanks, yes indeed it's an awesome platform to integrate search. Yes, it can be self-hosted. Integration is easy, you can check in the docs. You can search and get AI based answers from your website. Link to Wiki: https://github.com/swirlai/swirl-search/wiki

Swirl is the Open-Source Platform for Enterprise Search with AI (LLMs and GPT). Swirl can connect to many data sources and provide search functionality. If your product has an API then it can be searched with Swirl. Like, SQL Databases, NoSQL, Slack, Google Bard, Open AI, Huggingface, Spacy, Teams, Outlook, Calendar, ApaceSolr, etc. All the search providers, and all the data siloes. It can then use Chat GPT or any other LLM to perform RAG(Retrieval Augmentated Generation) on your content.

Swirl 2.5 is now available! This version focused on performance. Configured with 12 SearchProviders, 2.5 supports ~15 queries/second on a Standard F16s v2 server (16 vcpus, 32 GiB memory) with a median response time of ~3 seconds. Version 2.5 also includes SearchProviders for HubSpot contact, company, and deal records, plus improvements to the Galaxy search UI. Check out the Release notes for full details: https://github.com/swirlai/swirl-search/releases/tag/v2.5.0 Please star our repo :-) #gratitude

Swirl is a metasearch engine; it adapts queries for each source, sends them out, asynchronously gathers the results, then uses AI (large language models) to re-rank everything. Swirl includes connectors to elastic, solr, opensearch, PostgreSQL, configurations for cloud services like Miro, Google BigQuery, Atlassian, Microsoft 365 etc. Apache 2.0 license. Looking for usage, feedback and contributions. Try it via Docker here: https://github.com/swirlai/swirl-search#try-swirl-now