Chroma

Chroma is a AI-native open-source vector database focused on developer productivity and happiness. Chroma is licensed under Apache 2.0.

This guide provides a quick overview for getting started with Chroma vector stores. For detailed documentation of all Chroma features and configurations head to the API reference.

Chroma Cloud

Chroma Cloud powers serverless vector and full-text search. It’s extremely fast, cost-effective, scalable and painless. Create a DB and try it out in under 30 seconds with \$5 of free credits.

Get started with Chroma Cloud

Overview

Integration details

Class	Package	PY support	Package latest
Chroma	@langchain/community	✅

Setup

To use Chroma vector stores, you’ll need to install the @langchain/community integration package along with the Chroma JS SDK as a peer dependency.

This guide will also use OpenAI embeddings, which require you to install the @langchain/openai integration package. You can also use other supported embeddings models if you wish.

tip

See this section for general instructions on installing integration packages.

• npm
• yarn
• pnpm

yarn add @langchain/community @langchain/openai @langchain/core chromadb

If you want to run Chroma locally, you can run a local Chroma server using the Chroma CLI, which ships with the chromadb package:

chroma run

You can also run a server on Docker, using the official Chroma image:

docker pull chromadb/chroma
docker run -p 8000:8000 chromadb/chroma

Credentials

If you are running Chroma locally, you do not need to provide any credentials.

If you are a Chroma Cloud user, set your CHROMA_TENANT, CHROMA_DATABASE, and CHROMA_API_KEY environment variables.

The Chroma CLI can set these for you. First, login via the CLI, and then use the connect command:

chroma db connect [db_name] --env-file

If you are using OpenAI embeddings for this guide, you’ll need to set your OpenAI key as well:

process.env.OPENAI_API_KEY = "YOUR_API_KEY";

If you want to get automated tracing of your model calls you can also set your LangSmith API key by uncommenting below:

// process.env.LANGSMITH_TRACING="true"
// process.env.LANGSMITH_API_KEY="your-api-key"

Instantiation

Setup your embedding function

First, choose your embedding function. Here we use OpenAIEmbeddings:

import { OpenAIEmbeddings } from "@langchain/openai";

const embeddings = new OpenAIEmbeddings({
  model: "text-embedding-3-small",
});

Running Locally

A simple Chroma instantiation will connect to a Chroma server running locally on http://localhost:8000:

import { Chroma } from "@langchain/community/vectorstores/chroma";

const vectorStore = new Chroma(embeddings, {
  collectionName: "a-test-collection"
});

If you are running your Chroma server using a different configuration, you can specify your host, port and whether to connect using ssl:

import { Chroma } from "@langchain/community/vectorstores/chroma";

const vectorStore = new Chroma(embeddings, {
  collectionName: "a-test-collection",
  host: "your-host-address",
  port: 8080
});

Chroma Cloud

To connect to Chroma Cloud, provide your tenant, database, and chromaCloudAPIKey:

import { Chroma } from "@langchain/community/vectorstores/chroma";

const vectorStore = new Chroma(embeddings, {
  collectionName: "a-test-collection",
  tenant: process.env.CHROMA_TENANT,
  database: process.env.CHROMA_DATABASE,
  chromaCloudAPIKey: process.env.CHROMA_API_KEY
});

Manage vector store

Add items to vector store

import type { Document } from "@langchain/core/documents";

const document1: Document = {
  pageContent: "The powerhouse of the cell is the mitochondria",
  metadata: { source: "https://example.com" }
};

const document2: Document = {
  pageContent: "Buildings are made out of brick",
  metadata: { source: "https://example.com" }
};

const document3: Document = {
  pageContent: "Mitochondria are made out of lipids",
  metadata: { source: "https://example.com" }
};

const document4: Document = {
  pageContent: "The 2024 Olympics are in Paris",
  metadata: { source: "https://example.com" }
}

const documents = [document1, document2, document3, document4];

await vectorStore.addDocuments(documents, { ids: ["1", "2", "3", "4"] });

Delete items from vector store

You can delete documents from Chroma by id as follows:

await vectorStore.delete({ ids: ["4"] });

Query vector store

Once your vector store has been created and the relevant documents have been added you will most likely wish to query it during the running of your chain or agent.

Query directly

Performing a simple similarity search can be done as follows:

const filter = { source: "https://example.com" };

const similaritySearchResults = await vectorStore.similaritySearch("biology", 2, filter);

for (const doc of similaritySearchResults) {
  console.log(`* ${doc.pageContent} [${JSON.stringify(doc.metadata, null)}]`);
}

See this page for more on Chroma filter syntax.

If you want to execute a similarity search and receive the corresponding scores you can run:

const similaritySearchWithScoreResults = await vectorStore.similaritySearchWithScore("biology", 2, filter)

for (const [doc, score] of similaritySearchWithScoreResults) {
  console.log(`* [SIM=${score.toFixed(3)}] ${doc.pageContent} [${JSON.stringify(doc.metadata)}]`);
}

Query by turning into retriever

You can also transform the vector store into a retriever for easier usage in your chains.

const retriever = vectorStore.asRetriever({
  // Optional filter
  filter: filter,
  k: 2,
});
await retriever.invoke("biology");

Usage for retrieval-augmented generation

For guides on how to use this vector store for retrieval-augmented generation (RAG), see the following sections:

• Tutorials: working with external knowledge.
• How-to: Question and answer with RAG
• Retrieval conceptual docs

API reference

For detailed documentation of all Chroma features and configurations head to the API reference

Related

• Vector store conceptual guide
• Vector store how-to guides