Cinnamon/kotaemon

Cinnamon/kotaemon

An open-source RAG-based tool for chatting with documents.

113 followers

This project serves as a functional RAG UI for both end users who want to do QA on their documents and developers who want to build their own RAG pipeline.
Cinnamon/kotaemon gallery image
Free
Launch Team
Checkmarx Developer Assist for AI IDEs
Security linter for vibe coding: fix vulns as you build
Promoted

What do you think? …

Jim H.
Hunter
📌
Host your own document QA (RAG) web-UI. Support multi-user login, organize your files in private / public collections, collaborate and share your favorite chat with others. Organize your LLM & Embedding models. Support both local LLMs & popular API providers (OpenAI, Azure, Ollama, Groq). Hybrid RAG pipeline. Sane default RAG pipeline with hybrid (full-text & vector) retriever + re-ranking to ensure best retrieval quality. Multi-modal QA support. Perform Question Answering on multiple documents with figures & tables support. Support multi-modal document parsing (selectable options on UI). Advance citations with document preview. By default the system will provide detailed citations to ensure the correctness of LLM answers. View your citations (incl. relevant score) directly in the in-browser PDF viewer with highlights. Warning when retrieval pipeline return low relevant articles. Support complex reasoning methods. Use question decomposition to answer your complex / multi-hop question. Support agent-based reasoning with ReAct, ReWOO and other agents. Configurable settings UI. You can adjust most important aspects of retrieval & generation process on the UI (incl. prompts). Extensible. Being built on Gradio, you are free to customize / add any UI elements as you like. Also, we aim to support multiple strategies for document indexing & retrieval. GraphRAG indexing pipeline is provided as an example.
Lukas Ksiezak
@zephyrion @owenfar RAG, conceptually is a way of passing additional data to LLM. In case of this product it’s a document you want can chat about.
AnnaHo
This document QA web-UI is incredibly robust with its hybrid RAG pipeline and multi-modal support! I’m curious—will future updates introduce advanced collaboration features like real-time editing or feedback on shared collections for teams?
Jim H.
Hunter
@annaho2000 Thanks for your support! I'll pass along your suggestions to the development team. Let's keep an eye on this project together. Hoping it brings you an awesome user experience and the maximum amount of assistance!
Kyrylo Silin
Hey Zephyrion, How does the hybrid RAG pipeline you mentioned compare with using just vector retrieval? Are there any specific cases where one performs better than the other? Congrats on the launch!
Jim H.
Hunter
@kyrylosilin In most cases, the workflow of RAG, after targeted optimization, tends to yield better results than those achieved by simply using vector retrieval. Thanks for your support!!
Andy Hwang
This looks pretty solid for document QA! I like the multi-user support and the hybrid retrieval approach. One thing that could make it even better is adding a mobile app for on-the-go access. Also, it'd be cool to see some pre-built templates or use cases to help new users get started quickly. Overall, though, it seems like a versatile tool for both casual users and developers.
Jim H.
Hunter
@andyroamer Thanks for your support! I'll pass along your suggestions to the development team. Let's keep an eye on this project together. Hoping it brings you an awesome user experience and the maximum amount of assistance!
Tony Carter
This sounds incredible! 🌟 A document QA web-UI with support for multiple users, private/public collections, and advanced hybrid RAG pipelines is exactly what many teams need. The multi-modal QA support and detailed citations with document preview are game-changers for ensuring accuracy and thoroughness. Love the flexibility in configuring settings and the potential for customization through Gradio. Can't wait to see how it enhances our document management processes. Amazing work! 🚀📄 @zephyrion
Jim H.
Hunter
@tony_creator Clearly, you have a keen eye for product insights. Thanks for your support and feedback!
Daniel Harrison
This looks like a super useful tool, especially for managing docs and QA. Quick question though—can we set manual checkpoints during the document processing to review results before final output? Would love to have that control. Congrats on the launch!
Jim H.
Hunter
@danielharrison Extremely valuable feedback, I'll definitely discuss your perspective with the dev team. Thanks for your support!
Alexander William Hawkins
This looks super interesting, Zephyrion! Got a few questions tho - can users collaborate in real-time while using the document QA feature? And how does the system handle multi-modal parsing if the docs have a lot of images and tables?Anyways,congrats on the launch.
Jim H.
Hunter
@alexanderwilliamhawkins Glad to see you enjoying this tool, thanks for the support!
123
Next
Last