rag-web-ui

rag-web-ui: Build Knowledge-Base Q&A with RAG

RAG Web UI is a self-hostable web application for creating question-answering systems over your own documents. It combines document ingestion, vector search, and configurable cloud or local language models, with a web interface and OpenAPI access.

TypeScriptApache-2.0AIRAGLLM
View on GitHub Compare
Stars
3.3k
Forks
373
Stars, last 30 days
+3

Our take

Health score

27/100

How it is scored
Activity
33
Community
34
Issues
21
Pull requests
20

+3 stars in the last 30 days

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

3,303

Forks

376

Change since Nov 16, 2026: +3 stars·0 forks

Overview

RAG Web UI helps teams turn collections of documents into a searchable knowledge base that can answer questions with a large language model. It handles document processing and retrieval, then uses retrieved context to ground responses and provide citations.

It is aimed at developers and organizations that want a web interface and API for a RAG system, while choosing among supported model providers and vector stores. The project describes itself as actively developed and not ready for production use, so it is better suited to learning, prototyping, and evaluation than an assumed production deployment.

Key Features

  • Ingests PDF, DOCX, Markdown, and text documents, with asynchronous processing and incremental updates.
  • Splits and vectorizes documents for retrieval from a knowledge base.
  • Supports multi-turn chat and reference citations in responses.
  • Offers cloud model providers including OpenAI, DeepSeek, and MiniMax, as well as local models through Ollama.
  • Supports ChromaDB and Qdrant as vector database options.
  • Provides an OpenAPI interface for accessing knowledge-base functionality.
  • Uses a separated frontend and backend, with MinIO for object storage.

Use Cases

  • A development team can prototype an internal Q&A assistant grounded in project documentation.
  • An organization can evaluate whether document-based chat fits a support or operations workflow before investing in a production system.
  • Privacy-conscious users can experiment with a local-model setup through Ollama, subject to configuring the required services.
  • Developers can integrate knowledge-base access into another application through the provided OpenAPI interface.

Getting Started

The README documents a Docker Compose setup. Start by cloning the repository and preparing its environment file:

git clone https://github.com/rag-web-ui/rag-web-ui.git
cd rag-web-ui
cp .env.example .env

Then configure the required services and variables before running docker compose up -d --build. See the README for setup details and configuration options.

Alternatives

  • kotaemon: kotaemon is a customizable document-QA web app and toolkit, while rag-web-ui focuses on a self-hostable RAG app with OpenAPI access.
ProjectLanguageLicenseStarsStatus
rag-web-uiTypeScriptApache-2.03.3kNot checked yet
kotaemonPythonApache-2.025.8kQuiet

Considerations

  • The README explicitly says the project is under active development and is not ready for production use.
  • Setup requires Docker Compose, Node.js 18 or newer, Python 3.9 or newer, and 8 GB or more of RAM, according to the README.
  • A working deployment needs supporting services such as MySQL, vector storage, and MinIO, along with suitable model and embedding configuration.
  • The README presents multiple provider and storage options, but does not establish that every combination has equal maturity or operational support.

Found this useful?

Share it with someone who would like rag-web-ui.

Comparisons