You can use Roboflow Inference with Chroma to calculate multi-modal text and image embeddings with CLIP. through the RoboflowEmbeddingFunction class. Inference can be used through the Roboflow cloud, or run on your hardware.

Roboflow Cloud Inference#

To run Inference through the Roboflow cloud, you will need an API key. Learn how to retrieve a Roboflow API key.

You can pass it directly on creation of the RoboflowEmbeddingFunction:

Alternatively, you can set your API key as an environment variable:

Then, you can create the RoboflowEmbeddingFunction without passing an API key directly:

Local Inference#

You can run Inference on your own hardware.

To install Inference, you will need Docker installed. Follow the official Docker installation instructions for guidance on how to install Docker on the device on which you are working.

Then, you can install Inference with pip:

With Inference installed, you can start an Inference server. This server will run in the background. The server will accept HTTP requests from the RoboflowEmbeddingFunction to calculate CLIP text and image embeddings for use in your application:

To start an Inference server, run:

Your Inference server will run at http://localhost:9001.

Then, you can create the RoboflowEmbeddingFunction:

This function will calculate embeddings using your local Inference server instead of the Roboflow cloud.

For a full tutorial on using Roboflow Inference with Chroma, refer to the Roboflow Chroma integration tutorial.