No-code RAG pipeline builder for non-technical users.
Upload files → pick AI → get chatbot. Zero code. Grandma-simple.
Features • Quick Start • Architecture • Screenshots • Roadmap • Contributing
Building a RAG (Retrieval-Augmented Generation) chatbot today requires:
- Writing hundreds of lines of code
- Understanding embeddings, vector databases, chunking strategies
- Setting up infrastructure, APIs, and deployment pipelines
- Weeks of development time
Most people who need RAG chatbots aren't developers.
PipeRAG lets anyone build a production-ready RAG chatbot in 30 seconds:
- 📄 Upload your documents (PDF, DOCX, TXT, MD, CSV)
- ⚡ Auto-pipeline handles chunking, embedding, and storage
- 💬 Chat with your documents instantly
- 🔗 Embed the chatbot anywhere with one
<script>tag
No code. No config. No PhD in AI required.
| Feature | Description |
|---|---|
| 📄 Smart Document Processing | Upload PDF, DOCX, TXT, MD, CSV — auto-parsed and chunked |
| 🔗 Visual Pipeline Builder | Drag-and-drop pipeline configuration (Source → Chunk → Embed → Retrieve → Generate) |
| ⚡ Auto-Pipeline | Zero-config mode: upload → chatbot in 30 seconds |
| 🧬 Multiple Embedding Models | text-embedding-3-small, text-embedding-3-large, ada-002 |
| 💬 Streaming Chat | Real-time SSE streaming responses with conversation memory |
| 🎨 Embeddable Widget | One <script> tag to add a chatbot to any website |
| 🎯 Chunk Preview | See exactly how your documents are split before processing |
| 💳 Billing & Tiers | Free/Pro/Enterprise with Stripe integration |
| 📊 Dashboard & Analytics | Project management, usage tracking, query analytics |
| 🐳 One-Click Deploy | Docker + GitHub Actions + fly.io ready |
┌─────────────────────────────────────────────────────┐
│ Angular 21 SPA │
│ (Signals · Standalone · Tailwind CSS) │
├─────────────────────────────────────────────────────┤
│ .NET 10 Web API │
│ (Clean Architecture · CQRS) │
├──────────┬──────────┬──────────┬────────────────────┤
│ Semantic │ pgvector │ Redis │ PostgreSQL │
│ Kernel │ (vectors)│ (cache) │ (data store) │
└──────────┴──────────┴──────────┴────────────────────┘
- Frontend: Angular 21 (Signals, zoneless, standalone components) + Tailwind CSS
- Backend: .NET 10 + Clean Architecture (Api / Core / Infrastructure)
- AI/ML: Microsoft Semantic Kernel for embeddings + LLM orchestration
- Vector DB: pgvector (runs inside PostgreSQL — no extra service!)
- Cache: Redis for rate limiting + session cache
- Database: PostgreSQL for all relational data
Screenshots coming soon! Run locally to see PipeRAG in action.
- .NET 10 SDK
- Node.js 22+
- Docker (for PostgreSQL + pgvector)
git clone https://github.com/CIKR-Repos/PipeRAG.git
cd PipeRAGdocker compose up -d dbcd src/PipeRAG.Api
dotnet ef database update
dotnet runcd client
npm install
ng serveNavigate to http://localhost:4200 — register an account and start building!
docker compose --profile production up -d- 📄 Document processing (PDF, DOCX, TXT, MD, CSV)
- 🔗 Visual pipeline builder with drag-and-drop
- ⚡ Auto-pipeline (zero-config RAG)
- 💬 Streaming chat with conversation memory
- 🎨 Embeddable chat widget
- 💳 Stripe billing integration
- 🐳 Docker + CI/CD deployment
- 🌐 Multi-language support
- 🔌 API connectors (Notion, Confluence, Google Drive)
- 📱 Mobile-responsive widget
- 🤖 More LLM providers (Anthropic, Ollama, Mistral)
- 📊 Advanced analytics dashboard
- 🔐 SSO / SAML authentication
- 🏢 Multi-tenant / white-label support
We love contributions! Whether it's bug reports, feature requests, or code — all are welcome.
- Fork the repository
- Create a feature branch (
git checkout -b feat/amazing-feature) - Commit your changes (
git commit -m 'feat: add amazing feature') - Push to the branch (
git push origin feat/amazing-feature) - Open a Pull Request
See CONTRIBUTING.md for detailed guidelines.
This project is licensed under the MIT License — see the LICENSE file for details.
- 🐛 Report a Bug
- 💡 Request a Feature
- 💬 Start a Discussion
- ⭐ Star this repo if you find it useful!
Built with ❤️ by CIKR-Repos
