ChromaDB JavaScript Client

Chroma is the open-source embedding database. Chroma makes it easy to build LLM apps by making knowledge, facts, and skills pluggable for LLMs.

This package includes all embedding libraries as bundled dependencies, providing a simple installation experience without worrying about dependency management. For a thin client, install chromadb-client

Features

• ✅ Complete TypeScript support
• ✅ All embedding libraries included as bundled dependencies
• ✅ Works in both Node.js and browser environments
• ✅ Simple installation with no peer dependency requirements

Installation

1# npm
2npm install chromadb
3
4# pnpm
5pnpm add chromadb
6
7# yarn
8yarn add chromadb

Getting Started

Chroma needs to be running in order for this client to talk to it. Please see the Usage Guide to learn how to quickly stand this up.

1import { ChromaClient } from "chromadb";
2
3// Initialize the client
4const chroma = new ChromaClient({ path: "http://localhost:8000" });
5
6// Create a collection
7const collection = await chroma.createCollection({ name: "my-collection" });
8
9// Add documents to the collection
10await collection.add({
11  ids: ["id1", "id2"],
12  embeddings: [
13    [1.1, 2.3, 3.2],
14    [4.5, 6.9, 4.4],
15  ],
16  metadatas: [{ source: "doc1" }, { source: "doc2" }],
17  documents: ["Document 1 content", "Document 2 content"],
18});
19
20// Query the collection
21const results = await collection.query({
22  queryEmbeddings: [1.1, 2.3, 3.2],
23  nResults: 2,
24});

Using Embedding Functions

This package includes all embedding libraries as bundled dependencies, so you can use them directly:

1import { ChromaClient, OpenAIEmbeddingFunction } from "chromadb";
2
3const embedder = new OpenAIEmbeddingFunction({
4  openai_api_key: "your-api-key",
5  model_name: "text-embedding-ada-002",
6});
7
8const chroma = new ChromaClient({ path: "http://localhost:8000" });
9const collection = await chroma.createCollection({
10  name: "my-collection",
11  embeddingFunction: embedder,
12});
13
14// Now you can add documents without providing embeddings
15await collection.add({
16  ids: ["id1"],
17  documents: ["Document content"],
18});
19
20// And query with text
21const results = await collection.query({
22  queryTexts: ["similar document"],
23  nResults: 2,
24});

Additional Resources

• 📖 Documentation
• 💬 Community Discord
• 🏠 Homepage
• GitHub Repository

License

Apache 2.0