Embedding Functions

Embeddings are the way to represent any kind of data, making them the perfect fit for working with all kinds of AI-powered tools and algorithms. They can represent text, images, and soon audio and video. Chroma collections index embeddings to enable efficient similarity search on the data they represent. There are many options for creating embeddings, whether locally using an installed library, or by calling an API. Chroma provides lightweight wrappers around popular embedding providers, making it easy to use them in your apps. You can set an embedding function when you create a Chroma collection, to be automatically used when adding and querying data, or you can call them directly yourself.

	Python	Typescript
Cloudflare Workers AI	✓	✓
Cohere	✓	✓
Google Generative AI	✓	✓
Hugging Face	✓	-
Hugging Face Embedding Server	✓	✓
Jina AI	✓	✓
Mistral	✓	✓
Morph	✓	✓
OpenAI	✓	✓
Sentence Transformers	✓	✓
Together AI	✓	✓

For TypeScript users, Chroma provides packages for a number of embedding model providers. The Chromadb python package ships with all embedding functions included.

Provider	Embedding Function Package
All (installs all packages)	@chroma-core/all
Cloudflare Workers AI	@chroma-core/cloudflare-worker-ai
Cohere	@chroma-core/cohere
Google Gemini	@chroma-core/google-gemini
Hugging Face Server	@chroma-core/huggingface-server
Jina	@chroma-core/jina
Mistral	@chroma-core/mistral
Morph	@chroma-core/morph
Ollama	@chroma-core/ollama
OpenAI	@chroma-core/openai
Qwen (via Chroma Cloud)	@chroma-core/chroma-cloud-qwen
Sentence Transformers	@chroma-core/sentence-transformer
Together AI	@chroma-core/together-ai
Voyage AI	@chroma-core/voyageai

We welcome pull requests to add new Embedding Functions to the community.

Python
TypeScript
Rust

Default: all-MiniLM-L6-v2

Chroma’s default embedding function uses the Sentence Transformers all-MiniLM-L6-v2 model to create embeddings. This embedding model can create sentence and document embeddings that can be used for a wide variety of tasks. This embedding function runs locally on your machine, and may require you to download the model files (this will happen automatically).If you don’t specify an embedding function when creating a collection, Chroma will set it to be the DefaultEmbeddingFunction:

collection = client.create_collection(name="my_collection")

Using Embedding Functions

Embedding functions can be linked to a collection and used whenever you call add, update, upsert or query.

# Set your OPENAI_API_KEY environment variable
from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction

collection = client.create_collection(
    name="my_collection",
    embedding_function=OpenAIEmbeddingFunction(
        model_name="text-embedding-3-small"
    )
)

# Chroma will use OpenAIEmbeddingFunction to embed your documents
collection.add(
    ids=["id1", "id2"],
    documents=["doc1", "doc2"]
)

You can also use embedding functions directly which can be handy for debugging.

from chromadb.utils.embedding_functions import DefaultEmbeddingFunction

default_ef = DefaultEmbeddingFunction()
embeddings = default_ef(["foo"])
print(embeddings) # [[0.05035809800028801, 0.0626462921500206, -0.061827320605516434...]]

collection.query(query_embeddings=embeddings)

Custom Embedding Functions

You can create your own embedding function to use with Chroma; it just needs to implement EmbeddingFunction.

from typing import Dict, Any
from chromadb import Documents, EmbeddingFunction, Embeddings
from chromadb.utils.embedding_functions import register_embedding_function

@register_embedding_function
class MyEmbeddingFunction(EmbeddingFunction):

    def __init__(self, model):
        self.model = model

    def __call__(self, input: Documents) -> Embeddings:
        # embed the documents somehow
        return embeddings

    @staticmethod
    def name() -> str:
        return "my-ef"

    def get_config(self) -> Dict[str, Any]:
        return dict(model=self.model)

    @staticmethod
    def build_from_config(config: Dict[str, Any]) -> "EmbeddingFunction":
        return MyEmbeddingFunction(config['model'])

We welcome contributions! If you create an embedding function that you think would be useful to others, please consider submitting a pull request.

Default: all-MiniLM-L6-v2

npm install @chroma-core/default-embed

Create a collection without providing an embedding function. It will automatically be set with the DefaultEmbeddingFunction:

const collection = await client.createCollection({ name: "my-collection" });

Using Embedding Functions

Embedding functions can be linked to a collection and used whenever you call add, update, upsert or query.Install the @chroma-core/openai package:

npm install @chroma-core/openai

Create a collection with the OpenAIEmbeddingFunction:

// Set your OPENAI_API_KEY environment variable
import { OpenAIEmbeddingFunction } from "@chroma-core/openai";

collection = await client.createCollection({
  name: "my_collection",
  embedding_function: new OpenAIEmbeddingFunction({
    modelName: "text-embedding-3-small",
  }),
});

// Chroma will use OpenAIEmbeddingFunction to embed your documents
await collection.add({
  ids: ["id1", "id2"],
  documents: ["doc1", "doc2"],
});

You can also use embedding functions directly which can be handy for debugging.

import { DefaultEmbeddingFunction } from "@chroma-core/default-embed";

const defaultEF = new DefaultEmbeddingFunction();
const embeddings = await defaultEF.generate(["foo"]);
console.log(embeddings); // [[0.05035809800028801, 0.0626462921500206, -0.061827320605516434...]]

await collection.query({ queryEmbeddings: embeddings });

Custom Embedding Functions

You can create your own embedding function to use with Chroma; it just needs to implement EmbeddingFunction.

export interface MyEmbeddingConfig {
  model: string;
}

export class MyEmbeddingFunction implements EmbeddingFunction {
  public readonly name = "my-embedding-function";
  private readonly model: string;

  constructor(args: { model: string }) {
    this.model = args.model;
  }

  async generate(texts: string[]): Promise<number[][]> {
    // embed the documents somehow
    return [];
  }

  getConfig(): MyEmbeddingConfig {
    return {
      model: this.model,
    };
  }

  validateConfigUpdate(config: Record<string, any>) {
    if ("model" in config) {
      throw new ChromaValueError("Model cannot be updated");
    }
  }

  static buildFromConfig(
    config: MyEmbeddingConfig,
    _client?: ChromaClient,
  ): MyEmbeddingFunction {
    return new MyEmbeddingFunction(config);
  }
}

We welcome contributions! If you create an embedding function that you think would be useful to others, please consider submitting a pull request.

The Rust client expects embeddings to be provided directly. Use your provider SDK to generate embeddings, then pass them to add, query, and other methods.

let embeddings = vec![vec![0.05, 0.06, -0.06]];

collection
    .add(
        vec!["id1".to_string()],
        embeddings,
        Some(vec![Some("doc1".to_string())]),
        None,
        None,
    )
    .await?;

Overview

Run Chroma

Collections

Querying Collections

Embeddings

CLI

Default: all-MiniLM-L6-v2

Using Embedding Functions

Custom Embedding Functions

Default: all-MiniLM-L6-v2

Using Embedding Functions

Custom Embedding Functions

Overview

Run Chroma

Collections

Querying Collections

Embeddings

CLI

​Default: all-MiniLM-L6-v2

​Using Embedding Functions

​Custom Embedding Functions

​Default: all-MiniLM-L6-v2

​Using Embedding Functions

​Custom Embedding Functions

Default: all-MiniLM-L6-v2

Using Embedding Functions

Custom Embedding Functions

Default: all-MiniLM-L6-v2

Using Embedding Functions

Custom Embedding Functions