rag-web-ui/rag-web-ui

Health v2 · maintenance only

Adoption not part of the score

3270 stars · 367 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

RAG Web UI is a self-hosted intelligent dialogue application that builds Q&A systems over your own knowledge base using Retrieval-Augmented Generation. It handles document ingestion (PDF, DOCX, Markdown, text), chunking, vectorization, and multi-turn chat with citations, supporting cloud LLMs (OpenAI, DeepSeek, MiniMax) or local models via Ollama.

Use cases

• build a chatbot over my own documents
• self-hosted RAG knowledge base Q&A
• chat with PDFs and DOCX files
• deploy a private AI assistant with Ollama
• query my knowledge base via API
• document management with vector search
• multi-turn chat with source citations

When to choose

• you want a ready-made, self-hosted RAG app with a web UI rather than building one from scratch
• you need document upload, chunking, and vectorization out of the box
• you want flexibility to switch between cloud LLMs and local models via Ollama
• you need an OpenAPI interface to access your knowledge base programmatically

When to avoid

• you only need a RAG library or framework to embed in your own code, not a full application
• you need a highly customized retrieval pipeline beyond what its factory-based architecture supports
• you require enterprise-grade multi-tenancy or access controls not provided by the project

Facets

application · maturity active

rag chatbot chat-interface vector-database search-engine llm-inference web-framework api-framework pdf file-upload large-language-models chatbots artificial-intelligence web-development self-hosted self-hosted python cross-platform knowledge-base document-management langchain ollama deepseek chromadb qdrant openai qa-system embeddings retrieval-augmented-generation natural-language-processing docker web-server nodejs

Member repositories

For agents

markdown · JSON · MCP: product_card(name="rag-web-ui/rag-web-ui")