Cinnamon/kotaemon

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

113 followers

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.

Free

Launch tags:Productivity•Artificial Intelligence•GitHub

Launch Team

Unblocked AI Code Review — High-signal comments based on your team's context

High-signal comments based on your team's context

Promoted

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.

Report

1yr ago

@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.

Report

1yr ago

Stella AI

Liked the mindmap feature, can we also use different AI models if needed or use our own API key?

Report

1yr ago

DiffSense

Really cool! I wonder if there are some projects in the wild that already use this?

Report

1yr ago

Telebugs

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!

Report

1yr ago

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!!

Report

1yr ago

Congratulations on the launch! I'm really intrigued by how this project caters to both end users and developers. It seems like the dual functionality of serving as a QA tool for documents while also allowing developers to build their own RAG pipeline opens up a lot of possibilities. I'm particularly interested in how user-friendly the interface is for non-technical users. Plus, will there be customizable features to allow users to tailor the QA process to their specific needs? Overall, this looks like an exciting tool that could streamline document management and improve QA processes significantly. Looking forward to seeing where this project goes!

Report

1yr ago

Congrats on the launch! Love the hybrid RAG pipeline and multi-modal support—how does it handle complex documents with lots of figures and tables? Looking forward to trying it out

Report

1yr ago

Picture Picker—Collect,Create,Edit Image

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?

Report

1yr ago

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!

Report

1yr ago

1 2 3