Logo
Deploy Now

SaaS Alternative

Perplexity

Categories

AI LLM Knowledge Base RAG Search Document Management

Stars

25,714

Forks

2,145

Watchers

129

Developer links

Last Updated: 08-25-2026 03:04 AM (UTC)

Kotaemon

Kotaemon is a document QA platform that combines advanced RAG techniques with a clean Gradio-based web interface for chatting with your documents. Built by Cinnamon, the Python backend supports any LLM provider including OpenAI, Azure OpenAI, Cohere, Groq, and local models via Ollama and llama-cpp-python, with a model management panel for configuring LLM and embedding providers from the UI. The default hybrid RAG pipeline combines full-text keyword retrieval with vector similarity search and applies re-ranking to ensure optimal result quality, while multi-modal document parsing extracts content from tables and figures alongside text. Advanced citations link every answer to specific source passages with relevance scores, viewable directly in the built-in PDF viewer with highlighted text spans. GraphRAG indexing via NanoGraphRAG, LightRAG, or Microsoft GraphRAG builds knowledge graphs from document collections for relationship-aware retrieval. Agent-based reasoning supports question decomposition for multi-hop queries using ReAct and ReWOO strategies. Multi-user authentication organizes documents into private and public collections with sharing and collaboration features. The platform supports Docker deployment in lite, full, and Ollama-bundled variants, runs on port 7860, and stores application data in a persistent volume. MCP tool integration enables external system connections for extended retrieval capabilities. On RepoCloud, deploy Kotaemon on a dedicated VPS with Docker, root SSH access, and complete control over your document AI infrastructure, all under the Apache 2.0 license.

Kotaemon
Kotaemon
Kotaemon
Kotaemon
Kotaemon

Benefits

  • Hybrid RAG with Re-Ranking
  • Default pipeline combines full-text keyword retrieval with vector similarity search and applies re-ranking to ensure optimal document retrieval quality for accurate question answering.
  • Multi-Provider LLM Support
  • Connects to OpenAI, Azure OpenAI, Cohere, Groq, and local models via Ollama and llama-cpp-python with a UI-based model management panel for configuring providers and embedding models.
  • Advanced Citations with PDF Preview
  • Every answer includes detailed citations with relevance scores linked to source passages, viewable directly in a built-in PDF viewer with highlighted text spans for verification.
  • GraphRAG Knowledge Graph Indexing
  • Builds knowledge graphs from document collections using NanoGraphRAG, LightRAG, or Microsoft GraphRAG for relationship-aware retrieval that captures entity connections beyond simple keyword matching.

Features

  • Hybrid Document Retrieval
  • Combines full-text keyword search with vector similarity retrieval and re-ranking using configurable retrieval settings adjustable from the web interface.
  • Multi-Modal Document Parsing
  • Extracts and processes content from tables, figures, and text across PDF and document files with selectable multi-modal parsing options in the UI.
  • Agent-Based Reasoning
  • Supports question decomposition for complex multi-hop queries using ReAct and ReWOO agent strategies that break queries into sub-questions for comprehensive answers.
  • Collection Management
  • Multi-user authentication with private and public document collections, sharing capabilities, and collaboration features for organizing team knowledge bases.
  • GraphRAG Indexing
  • Build knowledge graphs from document collections using NanoGraphRAG, LightRAG, or Microsoft GraphRAG for entity-relationship-aware retrieval beyond vector search.