> ## 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.

# OpenCLIP

export const Callout = ({title, children}) => <div className="my-6">
    <div className="relative pr-1.5 pb-1.5">
      <div className="absolute top-1.5 left-1.5 right-0 bottom-0 bg-blue-500 dark:bg-blue-600" />
      <div className="relative border border-black dark:border-gray-500 px-5 py-4 bg-white dark:bg-neutral-900">
        {title && <p className="block mb-2"><strong>{title}</strong></p>}
        {children}
      </div>
    </div>
  </div>;

Chroma provides a convenient wrapper around the OpenCLIP library. This embedding function runs locally and supports both text and image embeddings, making it useful for multimodal applications.

<Tabs>
  <Tab title="Python" icon="python">
    This embedding function relies on several python packages:

    * `open-clip-torch`: Install with `pip install open-clip-torch`
    * `torch`: Install with `pip install torch`
    * `pillow`: Install with `pip install pillow`

    ```python theme={null}
    from chromadb.utils.embedding_functions import OpenCLIPEmbeddingFunction
    import numpy as np
    from PIL import Image

    open_clip_ef = OpenCLIPEmbeddingFunction(
        model_name="ViT-B-32",
        checkpoint="laion2b_s34b_b79k",
        device="cpu"
    )

    # For text embeddings
    texts = ["Hello, world!", "How are you?"]
    text_embeddings = open_clip_ef(texts)

    # For image embeddings
    images = [np.array(Image.open("image1.jpg")), np.array(Image.open("image2.jpg"))]
    image_embeddings = open_clip_ef(images)

    # Mixed embeddings
    mixed = ["Hello, world!", np.array(Image.open("image1.jpg"))]
    mixed_embeddings = open_clip_ef(mixed)
    ```

    You can pass in optional arguments:

    * `model_name`: The name of the OpenCLIP model to use (default: "ViT-B-32")
    * `checkpoint`: The checkpoint to use for the model (default: "laion2b\_s34b\_b79k")
    * `device`: Device used for computation, "cpu" or "cuda" (default: "cpu")
  </Tab>
</Tabs>

<Callout>
  OpenCLIP is great for multimodal applications where you need to embed both text and images in the same embedding space. Visit [OpenCLIP documentation](https://github.com/mlfoundations/open_clip) for more information on available models and checkpoints.
</Callout>