Text Embeddings (custom)

Weaviate's integration with the Hugging Face Transformers library allows you to access their models' capabilities directly from Weaviate.

Configure a Weaviate vector index to use the Transformers integration, and configure the Weaviate instance with a model image, and Weaviate will generate embeddings for various operations using the specified model in the Transformers inference container. This feature is called the vectorizer.

This page shows how to build a custom Transformers model image and configure Weaviate with it, for users whose desired model is not available in the pre-built images.

Once a custom image is built and configured, usage patterns are identical to the pre-built images.

You can build a custom Transformers model image to use with Weaviate. This can be a public model from the Hugging Face model hub, or a compatible private or local model.

Embedding (also called 'feature extraction') models from the Hugging Face model hub can be used with Weaviate by building a custom Docker image.

The steps to build a custom image are:

• Create a Dockerfile that downloads the model.
• Build and tag the Dockerfile.
• Use the image in your Weaviate instance.

The Dockerfile to create depends on whether you are using a public model from the Hugging Face model hub, or a private or local model.

FROM semitechnologies/transformers-inference:custom
RUN MODEL_NAME=distilroberta-base ./download.py

FROM semitechnologies/transformers-inference:custom
COPY ./my-model /app/models/model

Tag the Dockerfile with a name, for example my-inference-image:

docker build -f my-inference-image.Dockerfile -t my-inference-image .

If you want to use the image in a different environment, you can push it to a Docker registry:

docker push my-inference-image

Specify the image in your Weaviate configuration, such as in docker-compose.yml, using the chosen local Docker tag (e.g. my-inference-image), or the image from the registry.

When using a custom image, you may set the USE_SENTENCE_TRANSFORMERS_VECTORIZER environment variable to use the sentence-transformers vectorizer instead of the default vectorizer from the transformers library.

Once you have built and configured the custom Transformers model image, continue on to the Transformers embeddings integrations guide to use the model with Weaviate.

Following the above example, set the image parameter in the text2vec-transformers service as the name of the custom image, e.g. my-inference-image.

Once the inference container is configured and running, you can send queries it directly to test its functionality.

First, expose the inference container. If deployed using Docker, forward the port by adding the following to the text2vec-transformers service in your docker-compose.yml:

services:
  weaviate:
    # Additional settings not shown
  text2vec-transformers:
    # Additional settings not shown
    ports:
      - "9090:8080"  # Add this line to expose the container

Once the container is running and exposed, you can send REST requests to it directly, e.g.:

curl localhost:9090/vectors -H 'Content-Type: application/json' -d '{"text": "foo bar"}'

If the container is running and configured correctly, you should receive a response with the vector embedding of the input text.

• Hugging Face Model Hub

Have a question or feedback? Here's how to reach us.