[HN Gopher] Show HN: Cognita - open-source RAG framework for mod...
       ___________________________________________________________________
        
       Show HN: Cognita - open-source RAG framework for modular
       applications
        
       Hey HN, exciting news! Our RAG framework, Cognita
       (https://github.com/truefoundry/cognita), born from collaborations
       with diverse enterprises, is now open-source. Currently, it offers
       seamless integrations with Qdrant and SingleStore.  In recent
       weeks, numerous engineers have explored Cognita, providing
       invaluable insights and feedback. We deeply appreciate your input
       and encourage ongoing dialogue (share your thoughts in the comments
       - let's keep this 'open source').  While RAG is undoubtedly
       powerful, the process of building a functional application with it
       can feel overwhelming. From selecting the right AI models to
       organizing data effectively, there's a lot to navigate. While tools
       like LangChain and LlamaIndex simplify prototyping, an accessible,
       ready-to-use open-source RAG template with modular support is still
       missing. That's where Cognita comes in.  Key benefits of Cognita:
       1. Central repository for parsers, loaders, embedders, and
       retrievers. 2. User-friendly UI empowers non-technical users to
       upload documents and engage in Q&A. 3. Fully API-driven for
       seamless integration with other systems.  We invite you to explore
       Cognita and share your feedback as we refine and expand its
       capabilities. Interested in contributing? Join the journey at
       https://www.truefoundry.com/cognita-launch.
        
       Author : supreetgupta
       Score  : 71 points
       Date   : 2024-04-27 16:40 UTC (6 hours ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | esafak wrote:
       | Many of the links are broken and lead to
       | https://www.truefoundry.com/cognita-launch#
       | 
       | I tried on Firefox and Chrome.
       | 
       | I would make the GitHub link more prominent.
       | 
       | Congratulations and good luck.
        
         | supreetgupta wrote:
         | Thanks for highlighting that! Here's the GitHub link:
         | https://github.com/truefoundry/cognita
        
       | namanyayg wrote:
       | Congrats on the launch Supreet! Can you talk about how Cognita
       | compares against competitors like RAGFlow?
        
       | parentheses wrote:
       | Looks like a great product. I'll have to give it a try!
       | 
       | I like that the product seems to solve the RAG need only and not
       | be an "everything framework" for LLMs. It makes for a richer
       | seeming product for RAG while making other aspects of AI apps
       | open for the user to choose their approach.
        
       | adastra22 wrote:
       | What is RAG?
        
         | vintagedave wrote:
         | Retrieval Augmented Generation.
         | 
         | The best explanation I can give as a non-expert is: it's used
         | when you have a general-purpose LLM but want to give it some
         | domain-specific knowledge. The query sent to the LLM is run
         | through what's effectively a search engine that catches
         | relevant terms etc, to find useful snippets of knowledge to
         | send to the LLM alongside the query, so the query is
         | _augmented_ with potentially useful information for answering
         | the query.
        
           | hobs wrote:
           | And really almost always its because the LLMs are really good
           | at summarization and ok at extrapolation and generally lie a
           | lot otherwise.
        
       | b2bsaas00 wrote:
       | What's best practice to integrate this in a Ruby on Rails
       | application?
        
         | F-Lexx wrote:
         | Best practice is to NOT integrate this in a Ruby on Rails
         | application.
        
         | jerpint wrote:
         | It seems to be a python app, so probably set it up as a
         | seperate microservice with its own REST API
        
       ___________________________________________________________________
       (page generated 2024-04-27 23:00 UTC)