ArchestackGitHub ↗ (opens in a new tab)

#1313th of 15 in RAG and knowledge

Kotaemon

Gradio RAG UI with hybrid retrieval, citations and multi-user login

Live demo ↗ (opens in a new tab)Documentation ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
Stars
25.8k
License
Apache-2.0
Last commit
May 2026
Last release
May 2026

Overview

Kotaemon is a Gradio web app for question answering over uploaded documents, with hybrid full-text plus vector retrieval, reranking, citations shown in an in-browser PDF viewer and ReAct or ReWOO agents. It supports OpenAI, Azure, Cohere, Groq, Ollama and GGUF via llama-cpp-python, with Elasticsearch, LanceDB, ChromaDB, Milvus or Qdrant storage. Docker images come in lite, full and ollama variants on port 7860.

Who it is for: small teams wanting document Q&A with a ready UI

Strengths

  • Hybrid retriever plus reranking by default, with low-relevance warnings
  • Citations open in a PDF viewer with highlights and relevance scores
  • Multi-user login with private and public collections
  • GraphRAG options: nano-graphrag, LightRAG or Microsoft GraphRAG

Weaknesses

  • Default login is admin/admin
  • GraphRAG extras cause hnswlib version conflicts that need manual pip fixes
  • Only PDF, HTML, MHTML and XLSX without the larger full image
  • Last commit 2026-05-30; MS GraphRAG indexing works only with OpenAI or Ollama

What it needs

  • no GPU
  • Docker
  • Needs Elasticsearch, LanceDB, ChromaDB, Milvus or Qdrant (optional stores), Unstructured (optional, for .doc/.docx and more)
  • Models: OpenAI, Azure OpenAI, Cohere, Groq, Ollama
  • port 7860

Also in RAG and knowledge

See all 15
Also in RAG and knowledge
RankProjectScore
1LightRAGGraph-plus-vector RAG server with web UI and Ollama-compatible API40.1k stars, MIT76 out of 100
2Open NotebookSelf-hosted NotebookLM alternative with podcasts and 20+ model providers40k stars, MIT75 out of 100
3RAGFlowRAG engine with document parsing, agentic retrieval and citations Live demo ↗ (opens in a new tab)92k stars, Apache-2.072 out of 100
#4WeKnoraEnterprise knowledge base combining RAG Q&A, agents and generated wikis33k stars, custom license68 out of 100
#5SurfSenseOffline NotebookLM alternative that turns documents into decks, reports and podcasts16.3k stars, custom license68 out of 100