31–36 of 36 posts
Hello, a very interesting project. Conratulations for putting everything together. I have expressed some thoughts in the discussion sections of Cognita github repo: https://github.com/truefoundry/cognita/discussions/146 It would be great if the maintainers could reply.
Sure! I’ll check those :) Thank you for suggestions hoping for some awesome contributions from you :P
Does a "web" data source only scrape the individual page or linked pages as well? I'm assuming the former. What would be the least painful way to ingest a knowledgebase (say a wiki-like site) from the web?
It can scrape linked pages too by defining the depth but make sure the depth parameter is not too much else it will consume too much memory and time.
Is the "scrape linked pages" configured to be "sandboxed" within a url hierarchy (so adding example.com/foo/ would add all linked pages that are also under example.com/foo/) or not (so it would also include linked pages to other domains or subfolders)?
Congratulations on the launch. I am building GenAI application. Will explore it.
Whatever you do, never say "free software"!!! That "freedom" stuff is commonism...
Interesting, is there any feature roadmap for future reference ?
1. Added VLM-based PDF parser 2. Integrated an intelligent summary query controller. Now, you can input multiple questions at once, and the controller will break them down into individual queries, answering each in a streaming format. Finally, it provides a summary of all responses.
Roadmap / Anticipated Contribution Scope:
1. Enabling hybrid and sparse vector search support 2. Implementing Embedding Quantization support 3. Integrating with GraphDBs and relevant retrievers 4. Enabling RAG Evaluation across various retrievers 5. Implementing RAG Visualization features ...and many other enhancements are awaiting.
Excited for the community's backing! Let's maintain the momentum of open source.