mirror of
https://github.com/mastra-ai/mastra.git
synced 2026-11-17 08:44:46 +00:00
Co-authored-by: LekoArts <lekoarts@gmail.com> Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com> Co-authored-by: LekoArts <16143594+LekoArts@users.noreply.github.com> |
History
|
|
|---|---|---|
| .. | ||
| src | ||
| CHANGELOG.md | ||
| docker-compose.yaml | ||
| lint-staged.config.js | ||
| package.json | ||
| README.md | ||
| tsconfig.build.json | ||
| tsconfig.json | ||
| tsdown.config.ts | ||
| turbo.json | ||
| vitest.config.ts | ||
@mastra/chroma
Vector store implementation for Chroma using the official chromadb client with added dimension validation, collection management, and document storage capabilities.
Installation
npm install @mastra/chroma
Usage
import { ChromaVector } from '@mastra/chroma';
const vectorStore = new ChromaVector({ id: 'chroma-vectors' });
// Create a new collection
await vectorStore.createIndex({ indexName: 'myCollection', dimension: 3, metric: 'cosine' });
// Add vectors with documents
const vectors = [
[0.1, 0.2, 0.3],
[0.3, 0.4, 0.5],
];
const metadata = [{ text: 'doc1' }, { text: 'doc2' }];
const documents = ['full text 1', 'full text 2'];
const ids = await vectorStore.upsert({
indexName: 'myCollection',
vectors,
metadata,
documents, // store original text
});
// Query vectors with document filtering
const results = await vectorStore.query({
indexName: 'myCollection',
queryVector: [0.1, 0.2, 0.3],
topK: 10, // topK
filter: { text: { $eq: 'doc1' } }, // metadata filter
includeVector: false, // includeVector
documentFilter: { $contains: 'specific text' }, // document content filter
});
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.