> ## Documentation Index > Fetch the complete documentation index at: https://docs.trychroma.com/llms.txt > Use this file to discover all available pages before exploring further. # Embedding Functions > Learn how to use embedding functions in Chroma to create vector representations of your data. Embeddings are numeric representations of your data that capture meaning in a form AI models can work with. They can represent text, images, and eventually audio and video. Chroma stores and indexes embeddings so you can efficiently search for similar content. You can generate them locally with an installed library or remotely through an API. ## Using Embedding Functions Embedding functions can be linked to a collection and used whenever you call `add`, `update`, `upsert` or `query`. For example, this is how you use the OpenAI embedding function: ```python theme={null} # 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. ```python theme={null} 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`. ```python theme={null} 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']) ``` ## Default: all-MiniLM-L6-v2 Chroma's default embedding function uses the [Sentence Transformers](https://www.sbert.net/) [`all-MiniLM-L6-v2`](https://huggingface.co/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`: ```python theme={null} 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`. For example, this is how you use the OpenAI embedding function: Install the `@chroma-core/openai` package: ```bash npm theme={null} npm install @chroma-core/openai ``` ```bash pnpm theme={null} pnpm add @chroma-core/openai ``` ```bash bun theme={null} bun add @chroma-core/openai ``` ```bash yarn theme={null} yarn add @chroma-core/openai ``` Create a collection with the `OpenAIEmbeddingFunction`: ```typescript theme={null} // 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. ```typescript theme={null} 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`. ```typescript theme={null} 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 { // embed the documents somehow return []; } getConfig(): MyEmbeddingConfig { return { model: this.model, }; } validateConfigUpdate(config: Record) { 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](https://github.com/chroma-core/chroma). ## Default: all-MiniLM-L6-v2 Chroma's default embedding function uses the [Sentence Transformers](https://www.sbert.net/) `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, install the `@chroma-core/default-embed` package: ```bash npm theme={null} npm install @chroma-core/default-embed ``` ```bash pnpm theme={null} pnpm add @chroma-core/default-embed ``` ```bash bun theme={null} bun add @chroma-core/default-embed ``` ```bash yarn theme={null} yarn add @chroma-core/default-embed ``` Create a collection without providing an embedding function. It will automatically be set with the `DefaultEmbeddingFunction`: ```typescript theme={null} const collection = await client.createCollection({ name: "my-collection" }); ``` 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. ```rust theme={null} 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?; ``` ## All Embedding Functions 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](../collections/manage-collections) a Chroma collection, to be automatically used when adding and querying data, or you can call them directly yourself. | | Python | Typescript | | ---------------------------------------------------------------------------------------- | ------ | ---------- | | [Cloudflare Workers AI](../../integrations/embedding-models/cloudflare-workers-ai) | ✓ | ✓ | | [Cohere](../../integrations/embedding-models/cohere) | ✓ | ✓ | | [Google Generative AI](../../integrations/embedding-models/google-gemini) | ✓ | ✓ | | [Hugging Face](../../integrations/embedding-models/hugging-face) | ✓ | - | | [Hugging Face Embedding Server](../../integrations/embedding-models/hugging-face-server) | ✓ | ✓ | | [Jina AI](../../integrations/embedding-models/jina-ai) | ✓ | ✓ | | [Mistral](../../integrations/embedding-models/mistral) | ✓ | ✓ | | [Morph](../../integrations/embedding-models/morph) | ✓ | ✓ | | [OpenAI](../../integrations/embedding-models/openai) | ✓ | ✓ | | [Sentence Transformers](../../integrations/embedding-models/sentence-transformer) | ✓ | ✓ | | [Together AI](../../integrations/embedding-models/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](https://www.npmjs.com/package/@chroma-core/all) | | Cloudflare Workers AI | [@chroma-core/cloudflare-worker-ai](https://www.npmjs.com/package/@chroma-core/cloudflare-worker-ai) | | Cohere | [@chroma-core/cohere](https://www.npmjs.com/package/@chroma-core/cohere) | | Google Gemini | [@chroma-core/google-gemini](https://www.npmjs.com/package/@chroma-core/google-gemini) | | Hugging Face Server | [@chroma-core/huggingface-server](https://www.npmjs.com/package/@chroma-core/huggingface-server) | | Jina | [@chroma-core/jina](https://www.npmjs.com/package/@chroma-core/jina) | | Mistral | [@chroma-core/mistral](https://www.npmjs.com/package/@chroma-core/mistral) | | Morph | [@chroma-core/morph](https://www.npmjs.com/package/@chroma-core/morph) | | Ollama | [@chroma-core/ollama](https://www.npmjs.com/package/@chroma-core/ollama) | | OpenAI | [@chroma-core/openai](https://www.npmjs.com/package/@chroma-core/openai) | | Perplexity | [@chroma-core/perplexity](https://www.npmjs.com/package/@chroma-core/perplexity) | | Qwen (via Chroma Cloud) | [@chroma-core/chroma-cloud-qwen](https://www.npmjs.com/package/@chroma-core/chroma-cloud-qwen) | | Sentence Transformers | [@chroma-core/sentence-transformer](https://www.npmjs.com/package/@chroma-core/sentence-transformer) | | Together AI | [@chroma-core/together-ai](https://www.npmjs.com/package/@chroma-core/together-ai) | | Voyage AI | [@chroma-core/voyageai](https://www.npmjs.com/package/@chroma-core/voyageai) | We welcome contributions! If you create an embedding function that you think would be useful to others, please consider [submitting a pull request](https://github.com/chroma-core/chroma).