NVIDIA API client (Python + C++ via pybind11)

Layout

• base64_module.cpp — C++ extension: fast file → base64 encoder
• setup.py — builds the C++ extension into a Python-importable module
• main.py — Python script that calls the NVIDIA chat completions API, using the C++ extension for any file/image encoding

Build the C++ extension

pip install pybind11
python setup.py build_ext --inplace

This produces a fastb64*.so file in this directory that main.py imports directly.

Set your API key

Do not put the key in the source code. Export it as an environment variable instead:

export NVIDIA_API_KEY="nvapi-..."

(If you pasted a key into this chat earlier, treat it as compromised — revoke/regenerate it in your NVIDIA NGC account.)

Run

python main.py

To send an image with the prompt:

call_api("What's in this image?", image_path="photo.png")

The C++ extension handles reading + base64-encoding the file; Python handles the HTTP request and JSON response.

Deploy to Render as a free Web Service

Files added for this: Dockerfile, .dockerignore, requirements.txt, app.py, render.yaml.

app.py is a small Flask app (served by gunicorn in the container) with two routes:

• GET / — health check, used by Render and to confirm the service is live
• POST /chat — body {"prompt": "..."} (optionally "image_path": "..."), calls the NVIDIA API and returns the JSON response

This fits Render's free Web Service tier — no payment info required. The tradeoff: free web services spin down after ~15 min of inactivity and take a few seconds to wake on the next request. Fine for testing/light use; upgrade to a paid instance later if you need it always-on.

Option A — Blueprint (render.yaml), one click:

1. Push this folder to a GitHub/GitLab repo.
2. In Render: New > Blueprint → pick the repo. Render reads render.yaml and creates the nvidia-qwen-web service for you.
3. Go to the new service's Environment tab and set NVIDIA_API_KEY (it's marked sync: false so it isn't committed to your repo).
4. Deploy.

Option B — Manual:

1. Push this folder to a repo.
2. In Render: New > Web Service → pick the repo.
3. Runtime: Docker (Render finds the Dockerfile automatically).
4. Instance type: Free.
5. Add environment variable NVIDIA_API_KEY under the Environment tab.
6. Create the service.

Once deployed, test it:

curl https://<your-service>.onrender.com/
curl -X POST https://<your-service>.onrender.com/chat \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Hello!"}'

Note: main.py checks for NVIDIA_API_KEY at startup, so if it's missing the app will fail to boot with a clear error in the logs rather than run with a broken key — set the env var and redeploy to fix.