Skip to main content

🧬 Embeddings

Embeddings are the A.I-native way to represent any kind of data, making them the perfect fit for working with all kinds of A.I-powered tools and algorithms. They can represent text, images, and soon audio and video. 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, which will be used automatically, or you can call them directly yourself.

Google PaLM
Hugging Face
Hugging Face Embedding Server

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

Default: all-MiniLM-L6-v2

By default, Chroma 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 download the model files (this will happen automatically).

from chromadb.utils import embedding_functions
default_ef = embedding_functions.DefaultEmbeddingFunction()

Embedding functions can linked to a collection, which are used whenever you call add, update, upsert or query. You can also be use them directly which can be handy for debugging.

val = default_ef(["foo"])

-> [[0.05035809800028801, 0.0626462921500206, -0.061827320605516434...]]

Sentence Transformers

Chroma can also use any Sentence Transformers model to create embeddings.

sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="all-MiniLM-L6-v2")

You can pass in an optional model_name argument, which lets you choose which Sentence Transformers model to use. By default, Chroma uses all-MiniLM-L6-v2. You can see a list of all available models here.

Custom Embedding Functions

Select a language

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

from chromadb import Documents, EmbeddingFunction, Embeddings

class MyEmbeddingFunction(EmbeddingFunction):
def __call__(self, texts: Documents) -> Embeddings:
# embed the documents somehow
return embeddings

We welcome contributions! If you create an embedding function that you think would be useful to others, please consider submitting a pull request to add it to Chroma's embedding_functions module.