Quickstart Guide | NVIDIA BioNeMo NIM Documentation

Start NIM

This page assumes you have completed the Prerequisites (client software, NGC account and API key, Docker login to the NGC registry, and accepted license terms).

Export NGC_API_KEY variable.
```
export NGC_API_KEY=<your personal NGC key>
```
Only Personal API Keys or Service API Keys are supported. Legacy API keys are not supported and will result in a failed docker pull.
The NIM container automatically downloads models. To save time and bandwidth, provide a local cache directory. This way the NIM can reuse already downloaded models. Run the following commands to set up the cache directory.
```
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
sudo chmod 0777 -R "$LOCAL_NIM_CACHE"
```
Run the NIM container with the following commands.

If you have not already, visit the ProteinMPNN NGC page and click Accept Terms under the Governing Terms section before pulling the container. See Prerequisites for details.
```
docker run -it \
    --runtime=nvidia \
    --gpus='"device=0"' \
    -p 8000:8000 \
    -e NGC_API_KEY \
    -v "$LOCAL_NIM_CACHE":/home/nvs/.cache/nim \
    nvcr.io/nim/ipd/proteinmpnn:latest
```
This command starts the NIM container and exposes port 8000 for the user to interact with the NIM.
Open a new terminal, leaving the terminal that runs the service open. In the new terminal, wait until the health check endpoint returns {"status":"ready"} before proceeding. This can take a couple of minutes. You can use the following command to query the health check.
```
curl http://localhost:8000/v1/health/ready
```

Run the Python Client Example

Save the following Python example to a file named nim_client.py.

#!/usr/bin/env python3
import requests
import json
from pathlib import Path
def get_reduced_pdb():
    pdb = Path("1R42.pdb")
    if not pdb.exists():
        pdb.write_text(requests.get(f"https://files.rcsb.org/download/{pdb}").text)
    lines = filter(lambda line: line.startswith("ATOM"), pdb.read_text().split("\n"))
    return "\n".join(list(lines)[:200])
r = requests.post(
    url="http://localhost:8000/biology/ipd/proteinmpnn/predict",
    json={
        "input_pdb": get_reduced_pdb(),
        "ca_only": False,
        "use_soluble_model": False,
        "sampling_temp": [0.1],
    },
)
r.raise_for_status()
print(r, "Saving to output.fa:\n", r.text[:200], "...")
Path("output.fa").write_text(json.loads(r.text)["mfasta"])

Run the example.
```
chmod +x nim_client.py
./nim_client.py
```
The NIM saves results to the output.fa file in Multi-FASTA format. You can view the file using the following command.
```
cat output.fa
```

Run the Shell Client Example

Save the following Shell example to a file named nim_client.sh.

#!/usr/bin/env bash
set -e
URL=http://localhost:8000/biology/ipd/proteinmpnn/predict
if [ ! -e 1R42.pdb ]; then curl -O https://files.rcsb.org/download/1R42.pdb; fi
pdb=$(cat 1R42.pdb | grep ^ATOM | head -n 200 | awk '{printf "%s\\n", $0}')
request='{
 "input_pdb": "'"$pdb"'",
 "ca_only": false,
 "use_soluble_model": false,
 "sampling_temp": [0.1]
}'
curl -H 'Content-Type: application/json' \
     -d "$request" "$URL"

Run the example.
```
chmod +x nim_client.sh
./nim_client.sh
```
The NIM displays the results to the terminal in JSON format. You can configure the NIM to display the results, scores, and probabilities in the Multi-FASTA output format.

Stop the Container

When you are done, press Ctrl+C in the terminal running the container. Because the docker run command does not use --rm, Docker keeps the stopped container. Run docker ps -a to find it and docker rm with its container ID to remove it.