Vectra: a local vector database

Vectra is a local, file-backed, in-memory vector database with an optional gRPC server for cross-language access. Each index is a folder on disk — queries use MongoDB-style metadata filtering and cosine similarity ranking, with sub-millisecond latency for small indexes.

What's New in Vectra 0.14+

• Browser & Electron support — vectra/browser entry point with IndexedDBStorage and TransformersEmbeddings
• Local embeddings — LocalEmbeddings and TransformersEmbeddings run HuggingFace models with no API key
• Protocol Buffers — opt-in binary format, 40-50% smaller files
• gRPC server — vectra serve exposes 19 RPCs for cross-language access
• FolderWatcher — auto-sync directories into a document index
• Language bindings — vectra generate scaffolds clients for 6 languages
• v0.15: Performance improvements — skip-if-unchanged document upserts, shallow-clone transactional snapshots, heap-based top-K query ranking, parallel metadata loads, and O(N) batch chunk deletion

See the Changelog for breaking changes and migration details.

Install

npm install vectra

Quick Example

import { LocalDocumentIndex, OpenAIEmbeddings } from 'vectra';

const docs = new LocalDocumentIndex({
  folderPath: './my-index',
  embeddings: new OpenAIEmbeddings({
    apiKey: process.env.OPENAI_API_KEY!,
    model: 'text-embedding-3-small',
    maxTokens: 8000,
  }),
});

if (!(await docs.isIndexCreated())) {
  await docs.createIndex({ version: 1 });
}

await docs.upsertDocument('doc://readme', 'Vectra is a local vector database...', 'md');

const results = await docs.queryDocuments('What is Vectra?', { maxDocuments: 5 });
if (results.length > 0) {
  const sections = await results[0].renderSections(2000, 1, true);
  console.log(sections[0].text);
}

Documentation

Full docs at stevenic.github.io/vectra:

Guide	Description
Getting Started	Install, requirements, quick start with both index types
Core Concepts	Index types, metadata filtering, on-disk layout
Embeddings Guide	Choose and configure an embeddings provider
Document Indexing	Chunking, retrieval, hybrid search, FolderWatcher
CLI Reference	All CLI commands, flags, and provider config
API Reference	TypeScript API overview
Best Practices	Performance tuning, troubleshooting
Storage	Pluggable backends, browser/IndexedDB, serialization formats
gRPC Server	Cross-language access and language bindings
Changelog	Breaking changes and migration guides
Tutorials	RAG pipeline, browser app, gRPC, custom storage, folder sync
Samples	Runnable examples: quickstart, RAG, browser, SQLite storage, gRPC, folder watcher

Agent Ready

Vectra ships an llms.txt file that gives coding agents everything they need to integrate Vectra into your project. Point your agent at it and let it do the work:

Read the llms.txt file at https://raw.githubusercontent.com/Stevenic/vectra/main/llms.txt
and then add Vectra support to this project. Use LocalDocumentIndex for document
storage and retrieval.

The llms.txt file covers all exports, index types, CLI commands, gRPC bindings, and on-disk format — enough for any coding agent to scaffold a working integration without browsing docs.

License

MIT License. See LICENSE.

Contributing

See CONTRIBUTING.md for guidelines. Please review our Code of Conduct.