0
Fork 0
mirror of https://github.com/mastra-ai/mastra.git synced 2026-11-17 08:44:46 +00:00
mastra/stores/mongodb
dane-ai-mastra[bot] a5859ee2b9
chore: version packages (alpha) (#30430)
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
History 2026-11-16 14:09:31 +01:00
..
src fix(mongodb): retire older live observational memory records when startup races a rollover (#30452) 2026-11-15 14:56:31 -08:00
.gitignore MongoDBVector for Vector Database support (#3823) 2025-04-25 10:06:15 -07:00
CHANGELOG.md chore: version packages (alpha) (#30430) 2026-11-16 14:09:31 +01:00
docker-compose.yaml chore(deps): update docker images (major) (#19788) 2026-11-11 17:08:49 -08:00
lint-staged.config.js refactor(lint): replace ESLint with type-aware oxlint (#27476) 2026-10-18 10:38:35 -07:00
package.json chore: version packages (alpha) (#30430) 2026-11-16 14:09:31 +01:00
README.md docs: point store READMEs at the new integrations vector pages (#28970) 2026-10-30 11:31:23 +01:00
tsconfig.build.json chore: fix go-to-definition using tsc declaration maps (#6089) 2025-07-30 15:41:00 -07:00
tsconfig.json chore: migrate package builds to tsdown (#19829) 2026-07-28 12:32:21 +02:00
tsdown.config.ts fix(memory): make observational memory reflection, buffering, and activation lossless across processes (#25906) 2026-10-11 16:17:22 -07:00
turbo.json chore: migrate package builds to tsdown (#19829) 2026-07-28 12:32:21 +02:00
vitest.config.ts feat(mongodb): Automated Embedding for MongoDBVector (server-side embeddings) (#24383) 2026-09-24 15:34:28 +01:00

@mastra/mongodb

MongoDB Atlas Search implementation for Mastra, providing vector similarity search and index management using MongoDB Atlas Local or Atlas Cloud.

Installation

npm install @mastra/mongodb

Usage

Vector Store

import { MongoDBVector } from '@mastra/mongodb';

const vectorDB = new MongoDBVector({
  id: 'mongodb-vector',
  uri: 'mongodb://mongodb:mongodb@localhost:27018/?authSource=admin&directConnection=true',
  dbName: 'vector_db',
});

// Connect to MongoDB
await vectorDB.connect();

// Create a new vector index (collection)
await vectorDB.createIndex({
  indexName: 'my_vectors',
  dimension: 3,
  metric: 'cosine', // or 'euclidean', 'dotproduct'
});

// Upsert vectors
const ids = await vectorDB.upsert({
  indexName: 'my_vectors',
  vectors: [
    [0.1, 0.2, 0.3],
    [0.3, 0.4, 0.5],
  ],
  metadata: [{ text: 'doc1' }, { text: 'doc2' }],
});

// Query vectors
const results = await vectorDB.query({
  indexName: 'my_vectors',
  queryVector: [0.1, 0.2, 0.3],
  topK: 10,
  filter: { text: 'doc1' },
  includeVector: false,
});

// Clean up
await vectorDB.disconnect();

Documentation

Changelog

See the package changelog for version history and release notes.

Support

We have an open community Discord. Come and say hello and let us know if you have any questions or need any help getting things running.