Skip to main content

Hugging Face Text Embedding Server

Select a language

Chroma provides a convenient wrapper for HuggingFace Text Embedding Server, a standalone server that provides text embeddings via a REST API. You can read more about it here.

Setting Up The Server

To run the embedding server locally you can run the following command from the root of the Chroma repository. The docker compose command will run Chroma and the embedding server together.

docker compose -f examples/server_side_embeddings/huggingface/docker-compose.yml up -d


docker run -p 8001:80 -d -rm --name huggingface-embedding-server --model-id BAAI/bge-small-en-v1.5 --revision -main

The above docker command will run the server with the BAAI/bge-small-en-v1.5 model. You can find more information about running the server in docker here.


This embedding function relies on the requests python package, which you can install with pip install requests.

from chromadb.utils.embedding_functions import HuggingFaceEmbeddingServer
huggingface_ef = HuggingFaceEmbeddingServer(url="http://localhost:8001/embed")

The embedding model is configured on the server side. Check the docker-compose file in examples/server_side_embeddings/huggingface/docker-compose.yml for an example of how to configure the server.