--- title: Enterprise RAG Platform emoji: ๐Ÿš€ colorFrom: blue colorTo: green sdk: gradio sdk_version: 5.49.1 app_file: app/main.py pinned: false license: mit short_description: Document intelligence for Legal, Research, FinOps full_width: true --- # Enterprise RAG Platform **Turn documents into answers. Instantly.** Upload contracts, research papers, or financial reports โ†’ Ask questions โ†’ Get cited answers in seconds. --- ## โœจ What's New - **Multi-document upload** โ€” Process multiple files at once - **Streaming answers** โ€” Watch responses generate in real-time - **Thinking indicator** โ€” See "๐Ÿ” Analyzing documents..." before streaming starts --- ## How It Works ``` ๐Ÿ“„ Upload โ†’ โœ‚๏ธ Chunk โ†’ ๐Ÿง  Embed โ†’ ๐Ÿ’ฌ Ask โ†’ โœจ Cited Answer ``` **3 steps**: Upload your documents โ†’ Ask questions โ†’ Get answers with page citations. --- ## Try It Now 1. **Select a vertical** โ€” Legal, Research, or FinOps samples pre-loaded 2. **Or upload your own** โ€” PDF, DOCX, TXT supported (batch upload enabled) 3. **Ask anything** โ€” Natural language questions 4. **Get streaming answers** โ€” Watch the AI think and respond in real-time No signup required. Documents auto-deleted after 7 days. --- ## Features | Feature | Description | |---------|-------------| | **Multi-upload** | Upload multiple files at once | | **Streaming** | Real-time token-by-token answers | | **Citations** | Every answer links to source + page | | **3 AI models** | GPT-OSS 120B, Llama 3.3, Gemma 3 | | **Privacy** | Session isolation, 7-day auto-delete | --- ## Run Locally ```bash git clone https://github.com/pkgprateek/rag-document-qa-workflow.git cd rag-document-qa-workflow echo "GROQ_API_KEY=your_key" > .env docker compose up # โ†’ http://localhost:7860 ``` **API Keys:** [Groq](https://console.groq.com/keys) (Required) ยท [OpenRouter](https://openrouter.ai/keys) (Optional) --- ## ๐Ÿ”’ Privacy - Documents processed locally - Session-isolated storage - Auto-deleted after 7 days - Never used for training --- ## Enterprise Pilots **2-week paid pilots** for teams ready to deploy RAG on their infrastructure. ๐Ÿ“… [Book discovery call](https://cal.com/prateekgoel/30m-discovery-call) --- **Built by [Prateek Kumar Goel](https://github.com/pkgprateek)** ยท MIT License