Skip to main content

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.

Chroma provides a convenient integration with any OpenAI-compatible embedding model deployed on Baseten. Every embedding model deployed with BEI is compatible with the OpenAI SDK. Get started easily with an embedding model from Baseten’s model library, like Mixedbread Embed Large.

​
Using Baseten models with Chroma

This embedding function relies on the openai python package, which you can install with pip install openai. You must set the api_key and api_base, replacing the api_base with the URL from the model deployed in your Baseten account.
Python
import os
import chromadb.utils.embedding_functions as embedding_functions

baseten_ef = embedding_functions.BasetenEmbeddingFunction(
    api_key=os.environ["BASETEN_API_KEY"],
    api_base="https://model-xxxxxxxx.api.baseten.co/environments/production/sync/v1",
)

baseten_ef(input=["This is my first text to embed", "This is my second document"])