Live data from Hacker News

Show HN: Cognita – open-source RAG framework for modular applications

github.com

21–30 of 36 posts

Re: Show HN: Cognita – open-source RAG framework for modular applications

#24

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.

Re: Show HN: Cognita – open-source RAG framework for modular applications

#25
post #20

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

Re: Show HN: Cognita – open-source RAG framework for modular applications

#26

This product appears to be promising. I'm intrigued to test it out. I appreciate that it focuses solely on addressing the RAG requirement and doesn't attempt to be a one-size-fits-all solution for LLMs.

Indeed! There is no one size fits all, the more you customise the closer you are to your usecase!

Re: Show HN: Cognita – open-source RAG framework for modular applications

#27

Congratulations on the launch! Will give this a try! We were looking for a solution that would help our team test out the LLMs & prompts for repeatability and identifying edge cases. The UI looks interesting, like a playground on top of the RAG framework, allowing the team to test out various prompts / configurations to handle edge cases, without requiring a lot of tech bandwidth!

Yeah! Do give it a try :) Experiment and develop great usecases!

Re: Show HN: Cognita – open-source RAG framework for modular applications

#28

Congrats on the launch! I find it relevant to what I want to do next and put in some time to understand the application vs other stuff e.g. Langchain. And if my understanding is correct, what this tries to do is: For a lot of typical web services, there're non-realtime batch-processing data processors, e.g. search engine's crawler and indexer, or database's OLAP system, Hadoop, spark, etc. Once their processing is do…

Cognita works on top of langchain! For your use case, you might not even need to develop anything just index data and you are good to go

Try out different retrievers and test the accuracy and effectiveness for your use-case.

Post reply on HN