Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
as-cle-bertย 
posted an update 2 days ago
Post
1441
๐‘๐€๐†๐œ๐จ๐จ๐ง๐Ÿฆ - ๐€๐ ๐ž๐ง๐ญ๐ข๐œ ๐‘๐€๐† ๐ญ๐จ ๐ก๐ž๐ฅ๐ฉ ๐ฒ๐จ๐ฎ ๐›๐ฎ๐ข๐ฅ๐ ๐ฒ๐จ๐ฎ๐ซ ๐ฌ๐ญ๐š๐ซ๐ญ๐ฎ๐ฉ

GitHub ๐Ÿ‘‰ https://github.com/AstraBert/ragcoon

Are you building a startup and you're stuck in the process, trying to navigate hundreds of resources, suggestions and LinkedIn posts?๐Ÿ˜ถโ€๐ŸŒซ๏ธ
Well, fear no more, because ๐—ฅ๐—”๐—š๐—ฐ๐—ผ๐—ผ๐—ป๐Ÿฆ is here to do some of the job for you:

๐Ÿ“ƒ It's built on free resources written by successful founders
โš™๏ธ It performs complex retrieval operations, exploiting "vanilla" hybrid search, query expansion with an ๐—ต๐˜†๐—ฝ๐—ผ๐˜๐—ต๐—ฒ๐˜๐—ถ๐—ฐ๐—ฎ๐—น ๐—ฑ๐—ผ๐—ฐ๐˜‚๐—บ๐—ฒ๐—ป๐˜ approach and ๐—บ๐˜‚๐—น๐˜๐—ถ-๐˜€๐˜๐—ฒ๐—ฝ ๐—พ๐˜‚๐—ฒ๐—ฟ๐˜† ๐—ฑ๐—ฒ๐—ฐ๐—ผ๐—บ๐—ฝ๐—ผ๐˜€๐—ถ๐˜๐—ถ๐—ผ๐—ป
๐Ÿ“Š It evaluates the ๐—ฟ๐—ฒ๐—น๐—ถ๐—ฎ๐—ฏ๐—ถ๐—น๐—ถ๐˜๐˜† of the retrieved context, and the ๐—ฟ๐—ฒ๐—น๐—ฒ๐˜ƒ๐—ฎ๐—ป๐—ฐ๐˜† and ๐—ณ๐—ฎ๐—ถ๐˜๐—ต๐—ณ๐˜‚๐—น๐—ป๐—ฒ๐˜€๐˜€ of its own responses, in an auto-correction effort

RAGcoon๐Ÿฆ is ๐—ผ๐—ฝ๐—ฒ๐—ป-๐˜€๐—ผ๐˜‚๐—ฟ๐—ฐ๐—ฒ and relies on easy-to-use components:

๐Ÿ”นLlamaIndex is at the core of the agent architecture, provisions the integrations with language models and vector database services, and performs evaluations
๐Ÿ”น Qdrant is your go-to, versatile and scalable companion for vector database services
๐Ÿ”นGroq provides lightning-fast LLM inference to support the agent, giving it the full power of ๐—ค๐˜„๐—ค-๐Ÿฏ๐Ÿฎ๐—• by Qwen
๐Ÿ”นHugging Face provides the embedding models used for dense and sparse retrieval
๐Ÿ”นFastAPI wraps the whole backend into an API interface
๐Ÿ”น๐— ๐—ฒ๐˜€๐—ผ๐—ฝ by Google is used to serve the application frontend

RAGcoon๐Ÿฆ can be spinned up locally - it's ๐——๐—ผ๐—ฐ๐—ธ๐—ฒ๐—ฟ-๐—ฟ๐—ฒ๐—ฎ๐—ฑ๐˜†๐Ÿ‹, and you can find the whole code to reproduce it on GitHub ๐Ÿ‘‰ https://github.com/AstraBert/ragcoon

But there might be room for an online version of RAGcoon๐Ÿฆ: let me know if you would use it - we can connect and build it together!๐Ÿš€