RAGStack-Lambda

git clone https://github.com/HatmanStack/RAGStack-Lambda.git cd RAGStack-Lambda # Install dependencies uv sync # Deploy (defaults to us-east-1 for Nova Multimodal Embeddings) python publish.py \ --stack-name my-docs \ --admin-email admin@example.com

Resources: RAGStack: Type: AWS::CloudFormation::Stack Properties: TemplateURL: https://ragstack-quicklaunch-public.s3.us-east-1.amazonaws.com/ragstack-template.yaml Parameters: StackPrefix: 'my-app-ragstack' # Required: lowercase prefix AdminEmail: admin@example.com

Server-side integrationsuse 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 componentuses IAM auth (no API key needed - handled automatically).

Each UI tab shows server-side API examples in an expandable section.

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:

Upload → OCR → Embeddings → Bedrock KB ↓ Web UI (Dashboard + Chat) ←→ GraphQL API ↓ Web Component ←→ AI Chat with Sources

Upload documents in various formats. Auto-detection routes to optimal processor:

Processing time: UPLOADED → PROCESSING → INDEXED (typically 1-5 min for text, 2-15 min for OCR, 5-20 min for media)

Upload JPG, PNG, GIF, WebP with captions. Both visual content and caption text are searchable.

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.

- Speaker diarization (identify who said what)
- Configurable language (30+ languages supported)
- Timestamp-linked sources in chat responses

Ask questions about your content. Sources show where answers came from.

npm run check # Lint + test all (backend + frontend)

# Full deployment (defaults to us-east-1) python publish.py --stack-name myapp --admin-email admin@example.com # Skip dashboard build (still builds web component) python publish.py --stack-name myapp --admin-email admin@example.com --skip-ui # Skip ALL UI builds (dashboard and web component) python publish.py --stack-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 --stack-name myapp --admin-email admin@example.com --demo-mode

Publish to AWS Marketplace (Maintainers)

To update the one-click deploy template:

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>.

Interact with The Drive AI files directly from AI assistants like ChatGPT or Claude using the Model Context Protocol (MCP).

Production-ready RAG out of the box to search and retrieve data from your own documents.

A document question-and-answer server powered by Langflow.

Persistent memory for AI agents. Store and retrieve files via 14 MCP tools with OAuth 2.0 auth. Free 10GB tier.

Persistent cloud memory for AI agents via MCP Streamable HTTP. Store, retrieve, and search key-value memories across sessions and devices. Trial account auto-created on first use.

Retrieve files like PDFs from an AWS S3 bucket. Requires AWS credentials for access.

Publish HTML, Markdown, KV, JSON, files to brewpage.app from AI assistants.

An MCP server for interacting with Dropbox files and services.