nvidia/genmol

Pull and run nvidia/genmol-generate 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>

Pull and run the NVIDIA NIM with the command below. This will download the optimized model for your infrastructure.

Copy Code
export NGC_API_KEY=<PASTE_API_KEY_HERE>
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
docker run -it --rm \
    --runtime=nvidia \
    --gpus=all \
    -e NVIDIA_VISIBLE_DEVICES=0 \
    -e NGC_API_KEY=$NGC_API_KEY \
    --shm-size=2G \
    --ulimit memlock=-1 \
    --ulimit stack=67108864 \
    -p 8000:8000 \
    nvcr.io/nim/nvidia/genmol:1.0.0

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

Copy Code
accept_header='Accept: application/json'
content_type_header='Content-Type: application/json'

data='{
  "smiles": "C124CN3C1.S3(=O)(=O)CC.C4C#N.[*{20-20}]",
  "num_molecules": "30",
  "temperature": "1",
  "noise": "0",
  "step_size":"1",
  "scoring": "QED"
}'

response=$(curl --silent -i -w "
%{http_code}" --request POST \
  --url http://localhost:8000/generate \
  --header "$authorization_header" \
  --header "$accept_header" \
  --header "$content_type_header" \
  --data "$data"
)

echo "$response"

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