Run Text-Generator.io on Docker
Docker provides isolation of system packages and easy installation
Requirements
Quickstart
Download the docker zip file from your account, this requires a self hosted subscription
Start the image as a container (API key required)
This will download the required ~40gb of models if not available into the models directory
docker load -i text-generator.tar
mkdir models
docker run -v $(pwd)/models:/models -p 9000:8080 --gpus all \
-e API_KEY=YOUR_TEXT_GENERATOR_API_KEY \
text-generator-customer:v1
Test the API
The API docs will be available running at localhost:9000/docs
You can use your API key to make requests to the API
Example: Save the image to your own registry
docker tag text-generator-customer:v1 us.gcr.io/PROJECT/REPO/prod-app:v1
docker push us.gcr.io/PROJECT/REPO/prod-app:v1
Guidance
If your not sure about hosting your own Text Generator try the online playground to find use cases, prove out the system live and then transition later to hosting yourself.
If your using another provider like OpenAI hosting yourself can provide large cost savings and changing over the API is an easy migration from OpenAI