nvidia/nvclip

Pull and run nvidia/nvclip using Docker (this will download the full model and run it in your local environment)

Get API KeyCopy Code
$ docker login nvcr.io
Username: $oauthtoken
Password: <PASTE_API_KEY_HERE>

You can choose to provide the optimized profile id for your hardware from here and export it with the command below:

Copy Code
export NIM_MANIFEST_PROFILE=<PROFILE_ID>

Pull and run the NVIDIA NIM with the command below.

Copy Code
export NGC_API_KEY=<PASTE_API_KEY_HERE>
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
docker run -it --rm \
    --gpus all \
    -e NGC_API_KEY=$NGC_API_KEY \
    -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \
    -u $(id -u) \
    -p 8000:8000 \
    -e NIM_MANIFEST_PROFILE=$NIM_MANIFEST_PROFILE
    nvcr.io/nim/nvidia/nvclip:1.0.0

You can now make a local API call using this curl command:

Copy Code
curl -X POST  'http://0.0.0.0:8000/v1/embeddings' \
      -H "Content-Type: application/json" \
      -d '{
        "input": ["The quick brown fox jumped over the lazy dog",
                  "data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAIAAACQd1PeAAAAEElEQVR4nGK6HcwNCAAA//8DTgE8HuxwEQAAAABJRU5ErkJggg==",
                ],
        "model": "nvidia/nvclip-vit-h-14",
        "encoding_format": "float"
      }'

For more details on getting started with this NIM, visit the NVIDIA NIM Docs.