Serverless document and media processing with AI chat. Upload documents, images, video, and audio — extract text with OCR or transcription — query using Amazon Bedrock.
QUESTIONS?
Features
- ☁️ Fully serverless architecture (Lambda, Step Functions, S3, DynamoDB)
- 🧠 NEW Amazon Nova multimodal embeddings for text and image vectorization
- 📄 Document processing & vectorization (PDF, images, Office docs, HTML, CSV, JSON, XML, EML, EPUB) → stored in managed knowledge base
- 🎬 NEW Video/audio processing - transcribe speech with AWS Transcribe, searchable by timestamp
- 💬 AI chat with retrieval-augmented context and source attribution
- 📎 Collapsible source citations with optional document downloads
- ⏱️ NEW Media sources with timestamp links - click to play at exact position
- 🔍 Metadata filtering - auto-discover document metadata and filter search results
- 🔄 Knowledge Base reindex - regenerate metadata for existing documents with updated settings
- 🗑️ Document management - reprocess, reindex, or delete documents from the dashboard
- 🌐 Web component for any framework (React, Vue, Angular, Svelte)
- 🚀 One-click deploy
- 💰 $7-10/month (1000 docs, Textract + Haiku)
Live Demo
| Environment | URL | Credentials |
|---|---|---|
| Base Pipeline | dhrmkxyt1t9pb.cloudfront.net | guest@hatstack.fun / Guest@123 |
| Project Showcase | showcase-htt.hatstack.fun | Login as guest |
Base Pipeline: The core document processing tool - upload, OCR, and query documents.
Project Showcase: See RAGStack powering a real application.
Quick Start
Option 1: One-Click Deploy (AWS Marketplace)
REPO IS IN ACTIVE DEVELOPMENT AND WILL CHANGE OFTEN
Deploy directly from the AWS Console - no local setup required:
- Subscribe to RAGStack on AWS Marketplace (free, limited visibility need to be signed in to aws)
- Click here to deploy
- Enter a stack name (lowercase only, e.g., "my-docs") and your admin email
- Click Create Stack (deployment takes ~10 minutes)
After deployment:
- Check your email for the temporary password (from Cognito)
- Go to CloudFormation → your stack → Outputs tab to find the Dashboard URL (
UIUrl)
Option 2: Deploy from Source
For customization or development:
Prerequisites:
- AWS Account with admin access
- Python 3.13+, Node.js 24+
- AWS CLI, SAM CLI (configured)
- Docker (for Lambda layer builds)
git clone https://github.com/HatmanStack/RAGStack-Lambda.git
cd RAGStack-Lambda
# Create virtual environment and install dependencies
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
# Deploy (defaults to us-east-1 for Nova Multimodal Embeddings)
python publish.py \
--project-name my-docs \
--admin-email admin@example.com
Web Component Integration
Use AI chat in any web application (React, Vue, Angular, Svelte, etc.):
<script src="https://your-cdn-url/ragstack-chat.js"></script>
<ragstack-chat
conversation-id="my-app"
header-text="Ask About Documents"
></ragstack-chat>
Load the CDN script once, then use <ragstack-chat> in any framework.
API Access
Server-side integrations use API key authentication. Get your key from Dashboard → Settings.
curl -X POST 'YOUR_GRAPHQL_ENDPOINT' \
-H 'x-api-key: YOUR_API_KEY' \
-H 'Content-Type: application/json' \
-d '{"query": "query { searchKnowledgeBase(query: \"...\") { results { content } } }"}'
Web component uses IAM auth (no API key needed - handled automatically).
Each UI tab shows server-side API examples in an expandable section.
MCP Server (AI Assistant Integration)
Use your knowledge base directly in Claude Desktop, Cursor, VS Code, Amazon Q CLI, and other MCP-compatible tools.
# Install (or use uvx for zero-install)
pip install ragstack-mcp
Add to your AI assistant's MCP config:
{
"ragstack-kb": {
"command": "uvx",
"args": ["ragstack-mcp"],
"env": {
"RAGSTACK_GRAPHQL_ENDPOINT": "YOUR_ENDPOINT",
"RAGSTACK_API_KEY": "YOUR_API_KEY"
}
}
}
Then ask naturally: "Search my knowledge base for authentication docs"
See MCP Server docs for full setup instructions.
Architecture
Upload → OCR → Embeddings → Bedrock KB
↓
Web UI (Dashboard + Chat) ←→ GraphQL API
↓
Web Component ←→ AI Chat with Sources
Usage
Documents
Upload documents in various formats. Auto-detection routes to optimal processor:
| Type | Formats | Processing |
|---|---|---|
| Text | HTML, TXT, CSV, JSON, XML, EML, EPUB, DOCX, XLSX | Direct extraction with smart analysis |
| OCR | PDF, JPG, PNG, TIFF, GIF, BMP, WebP, AVIF | Textract or Bedrock vision OCR (WebP/AVIF require Bedrock) |
| Media | MP4, WebM, MP3, WAV, M4A, OGG, FLAC | AWS Transcribe → 30s segments → searchable with timestamps |
| Passthrough | Markdown (.md) | Direct copy |
Processing time: UPLOADED → PROCESSING → INDEXED (typically 1-5 min for text, 2-15 min for OCR, 5-20 min for media)
Images
Upload JPG, PNG, GIF, WebP with captions. Both visual content and caption text are searchable.
Web Scraping
Scrape websites into the knowledge base. See Web Scraping.
Video & Audio
Upload MP4, WebM, MP3, WAV, M4A, OGG, or FLAC files. Speech is transcribed using AWS Transcribe and segmented into 30-second chunks for search. Sources include timestamps (e.g., "1:30-2:00") with clickable links that play at the exact position.
Features:
- Speaker diarization (identify who said what)
- Configurable language (30+ languages supported)
- Timestamp-linked sources in chat responses
See Configuration for language and speaker settings.
Chat
Ask questions about your content. Sources show where answers came from.
Documentation
- Configuration - Settings, quotas, API keys & document management
- Web Scraping - Scrape websites
- Metadata Filtering - Auto-discover metadata and filter results
- Chat Component - Embed chat anywhere
- Architecture - System design & API reference
- Development - Local dev
- Troubleshooting - Common issues
- Library Reference - Public API for lib/ragstack_common
Development
npm run check # Lint + test all (backend + frontend)
Deployment Options
Direct Deployment
# Full deployment (defaults to us-east-1)
python publish.py --project-name myapp --admin-email admin@example.com
# Skip dashboard build (still builds web component)
python publish.py --project-name myapp --admin-email admin@example.com --skip-ui
# Skip ALL UI builds (dashboard and web component)
python publish.py --project-name myapp --admin-email admin@example.com --skip-ui-all
# Enable demo mode (rate limits: 5 uploads/day, 30 chats/day; disables reindex/reprocess/delete)
python publish.py --project-name myapp --admin-email admin@example.com --demo-mode
Publish to AWS Marketplace (Maintainers)
To update the one-click deploy template:
python publish.py --publish-marketplace
This packages the application and uploads to S3 for one-click deployment.
Note: Currently requires us-east-1 (Nova Multimodal Embeddings). When available in other regions, use
--region <region>.
Acknowledgments
This project was inspired by:
- Accelerated Intelligent Document Processing on AWS - AWS Solutions Library reference architecture
- docs-mcp-server - MCP server for documentation search