RAG Vault

Your documents. Your machine. Your control.

RAG Vault gives AI coding assistants instant access to your private documents—API specs, research papers, internal docs—without ever sending data to the cloud. One command, zero configuration, complete privacy.

Why RAG Vault?

| Pain Point | RAG Vault Solution | |------------|-------------------| | "I don't want my docs on someone else's server" | Everything stays local. No API calls after setup. | | "Semantic search misses exact code terms" | Hybrid search: meaning + exact matches like useEffect | | "Setup requires Docker, Python, databases..." | One npx command. Done. | | "Cloud APIs charge per query" | Free forever. No subscriptions. |

Security

RAG Vault includes security features for production deployment:

• API Authentication — Optional API key via RAG_API_KEY
• Rate Limiting — Configurable request throttling
• CORS Control — Restrict allowed origins
• Security Headers — Helmet.js protection

See SECURITY.md for complete documentation.

Get Started in 30 Seconds

For Cursor

Add to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "local-rag": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "github:RobThePCGuy/rag-vault"],
      "env": {
        "BASE_DIR": "/path/to/your/documents"
      }
    }
  }
}

For Claude Code

Add to .mcp.json in your project directory:

{
  "mcpServers": {
    "local-rag": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "github:RobThePCGuy/rag-vault"],
      "env": {
        "BASE_DIR": "./documents",
        "DB_PATH": "./documents/.rag-db",
        "CACHE_DIR": "./.cache",
        "RAG_HYBRID_WEIGHT": "0.6",
        "RAG_GROUPING": "related"
      }
    }
  }
}

Or add inline via CLI:

claude mcp add local-rag --scope user --env BASE_DIR=/path/to/your/documents -- npx -y github:RobThePCGuy/rag-vault

For Codex

Add to ~/.codex/config.toml:

[mcp_servers.local-rag]
command = "npx"
args = ["-y", "github:RobThePCGuy/rag-vault"]

[mcp_servers.local-rag.env]
BASE_DIR = "/path/to/your/documents"

Install Skills (Optional)

For enhanced AI guidance on query formulation and result interpretation, install the RAG Vault skills:

# Claude Code (project-level - recommended for team projects)
npx github:RobThePCGuy/rag-vault skills install --claude-code

# Claude Code (user-level - available in all projects)
npx github:RobThePCGuy/rag-vault skills install --claude-code --global

# Codex (user-level)
npx github:RobThePCGuy/rag-vault skills install --codex

# Custom location
npx github:RobThePCGuy/rag-vault skills install --path /your/custom/path

Skills teach Claude best practices for:

• Query formulation and expansion strategies
• Score interpretation (< 0.3 = good match, > 0.5 = skip)
• When to use ingest_file vs ingest_data
• HTML ingestion and URL handling

Restart your AI tool, and start talking:

You: "Ingest api-spec.pdf"
AI:  Successfully ingested api-spec.pdf (47 chunks)

You: "How does authentication work?"
AI:  Based on section 3.2, authentication uses OAuth 2.0 with JWT tokens...

That's it. No Docker. No Python. No servers.

Web Interface

RAG Vault includes a full-featured web UI for managing your documents without the command line.

Launch the Web UI

npx github:RobThePCGuy/rag-vault web

Open http://localhost:3000 in your browser.

What You Can Do

• Upload documents — Drag and drop PDFs, Word docs, Markdown, text files
• Search instantly — Type queries and see results with relevance scores
• Preview content — Click any result to see the full chunk in context
• Manage files — View all indexed documents, delete what you don't need
• Switch databases — Create and switch between multiple knowledge bases
• Monitor status — See document counts, memory usage, and search mode
• Export/Import settings — Back up and restore your vault configuration
• Theme preferences — Switch between light, dark, or system theme
• Folder browser — Navigate directories to select documents

REST API

The web server exposes a REST API for programmatic access. Set RAG_API_KEY to require authentication:

# With authentication (when RAG_API_KEY is set)
curl -X POST "http://localhost:3000/api/v1/search" \
  -H "Authorization: Bearer your-api-key" \
  -H "Content-Type: application/json" \
  -d '{"query": "authentication", "limit": 5}'

# Search documents (no auth required if RAG_API_KEY is not set)
curl -X POST "http://localhost:3000/api/v1/search" \
  -H "Content-Type: application/json" \
  -d '{"query": "authentication", "limit": 5}'

# List all files
curl "http://localhost:3000/api/v1/files"

# Upload a document
curl -X POST "http://localhost:3000/api/v1/files/upload" \
  -F "[email protected]"

# Delete a file
curl -X DELETE "http://localhost:3000/api/v1/files" \
  -H "Content-Type: application/json" \
  -d '{"filePath": "/path/to/spec.pdf"}'

# Get system status
curl "http://localhost:3000/api/v1/status"

# Health check (for load balancers)
curl "http://localhost:3000/api/v1/health"

Reader API Endpoints

For programmatic document reading and cross-document discovery:

# Get all chunks for a document (ordered by index)
curl "http://localhost:3000/api/v1/documents/chunks?filePath=/path/to/doc.pdf"

# Find related chunks for cross-document discovery
curl "http://localhost:3000/api/v1/chunks/related?filePath=/path/to/doc.pdf&chunkIndex=0&limit=5"

# Batch request for multiple chunks (efficient for UIs)
curl -X POST "http://localhost:3000/api/v1/chunks/batch-related" \
  -H "Content-Type: application/json" \
  -d '{"chunks": [{"filePath": "/path/to/doc.pdf", "chunkIndex": 0}], "limit": 3}'

Real-World Examples

Search Your Codebase Documentation

You: "Ingest all the markdown files in /docs"
AI:  Ingested 23 files (847 chunks total)

You: "What's the retry policy for failed API calls?"
AI:  According to error-handling.md, failed requests retry 3 times
     with exponential backoff: 1s, 2s, 4s...

Index Web Documentation

You: "Fetch https://docs.example.com/api and ingest the HTML"
AI:  Ingested "docs.example.com/api" (156 chunks)

You: "What rate limits apply to the /users endpoint?"
AI:  The API limits /users to 100 requests per minute per API key...

Build a Personal Knowledge Base

You: "Ingest my research papers folder"
AI:  Ingested 12 PDFs (2,341 chunks)

You: "What do recent studies say about transformer attention mechanisms?"
AI:  Based on attention-mechanisms-2024.pdf, the key finding is...

Search Exact Technical Terms

RAG Vault's hybrid search catches both meaning and exact matches:

You: "Search for ERR_CONNECTION_REFUSED"
AI:  Found 3 results mentioning ERR_CONNECTION_REFUSED:
     1. troubleshooting.md - "When you see ERR_CONNECTION_REFUSED..."
     2. network-errors.pdf - "Common causes include..."

Pure semantic search would miss this. RAG Vault finds it.

How It Works

Document → Parse → Chunk by meaning → Embed locally → Store in LanceDB
                         ↓
Query → Embed → Vector search → Keyword boost → Quality filter → Results

Smart chunking: Splits by meaning, not character count. Keeps code blocks intact.

Hybrid search: Vector similarity finds related content. Keyword boost ranks exact matches higher.

Quality filtering: Groups results by relevance gaps instead of arbitrary top-K cutoffs.

Local everything: Embeddings via Transformers.js. Storage via LanceDB. No network after model download.

Supported Formats

| Format | Extension | Notes | |--------|-----------|-------| | PDF | .pdf | Full text extraction, header/footer filtering | | Word | .docx | Tables, lists, formatting preserved | | Markdown | .md | Code blocks kept intact | | Text | .txt | Plain text | | JSON | .json | Converted to searchable key-value text | | HTML | via ingest_data | Auto-cleaned with Readability |

Configuration

Environment Variables

| Variable | Default | What it does | |----------|---------|--------------| | BASE_DIR | Current directory | Only files under this path can be accessed | | DB_PATH | ./lancedb/ | Where vectors are stored | | MODEL_NAME | Xenova/all-MiniLM-L6-v2 | HuggingFace embedding model | | WEB_PORT | 3000 | Port for web interface |

Search Tuning

| Variable | Default | What it does | |----------|---------|--------------| | RAG_HYBRID_WEIGHT | 0.6 | Keyword boost strength. 0 = semantic-only, higher = stronger boost for exact keyword matches | | RAG_GROUPING | — | similar = top group only, related = top 2 groups | | RAG_MAX_DISTANCE | — | Filter out results below this relevance threshold |

Security (optional)

| Variable | Default | What it does | |----------|---------|--------------| | RAG_API_KEY | — | API key for authentication | | CORS_ORIGINS | localhost | Allowed origins (comma-separated, or *) | | RATE_LIMIT_WINDOW_MS | 60000 | Rate limit time window (ms) | | RATE_LIMIT_MAX_REQUESTS | 100 | Max requests per window |

Advanced

| Variable | Default | What it does | |----------|---------|--------------| | ALLOWED_SCAN_ROOTS | Home directory | Directories allowed for database scanning | | JSON_BODY_LIMIT | 5mb | Max request body size | | REQUEST_TIMEOUT_MS | 30000 | API request timeout | | REQUEST_LOGGING | false | Enable request audit logging |

Copy .env.example for a complete configuration template.

For code-heavy content, try:

"env": {
  "RAG_HYBRID_WEIGHT": "0.8",
  "RAG_GROUPING": "similar"
}

Frequently Asked Questions

Yes. After the embedding model downloads (~90MB), RAG Vault makes zero network requests. Everything runs on your machine. Verify with network monitoring.

Yes, after the first run. The model caches locally.

Transformers.js runs on CPU. GPU support is experimental but unnecessary for most use cases—queries return in ~1 second even with 10,000 chunks.

Yes. Set MODEL_NAME to any compatible HuggingFace model. But you must delete DB_PATH and re-ingest—different models produce incompatible vectors.

Recommended upgrade: For better quality and multilingual support, use EmbeddingGemma:

"MODEL_NAME": "onnx-community/embeddinggemma-300m-ONNX"

This 300M parameter model scores 68.36 on MTEB benchmarks and supports 100+ languages, making it ideal for mixed-language or high-quality retrieval needs.

Other specialized models:

• Scientific: sentence-transformers/allenai-specter
• Code: jinaai/jina-embeddings-v2-base-code

Copy the DB_PATH directory (default: ./lancedb/).

Troubleshooting

| Problem | Solution | |---------|----------| | No results found | Documents must be ingested first. Run "List all ingested files" to check. | | Model download failed | Check internet connection. Model is ~90MB from HuggingFace. | | File too large | Default limit is 100MB. Set MAX_FILE_SIZE higher or split the file. | | Path outside BASE_DIR | All file paths must be under BASE_DIR. Use absolute paths. | | MCP tools not showing | Verify config syntax, restart your AI tool completely (Cmd+Q on Mac). | | 401 Unauthorized | API key required. Set RAG_API_KEY or use correct header format. | | 429 Too Many Requests | Rate limited. Wait for reset or increase RATE_LIMIT_MAX_REQUESTS. | | CORS errors | Add your origin to CORS_ORIGINS environment variable. |

Development

git clone https://github.com/RobThePCGuy/rag-vault.git
cd rag-vault
pnpm install

# Run tests
pnpm test

# Type check + lint + format
pnpm check:all

# Build
pnpm build

# Run MCP server locally
pnpm dev

# Run web server locally
pnpm web:dev

Project Structure

src/
├── server/      # MCP tool handlers
├── vectordb/    # LanceDB + hybrid search
├── chunker/     # Semantic text splitting
├── embedder/    # Transformers.js wrapper
├── parser/      # PDF, DOCX, HTML parsing
├── web/         # Express server + REST API
└── __tests__/   # Test suites

web-ui/          # React frontend

Documentation

• SECURITY.md — Security configuration and best practices
• .env.example — Complete environment variable template

License

MIT — free for personal and commercial use.

Acknowledgments

Built with Model Context Protocol, LanceDB, and Transformers.js.

Started as a fork of mcp-local-rag by Shinsuke Kagawa. Now it’s its own thing. Huge credit to upstream contributors for the foundation, I’ve been iterating hard from there. Local-first dev tools, all the way.