For proper deployment, you must set up a deployment space and then select and configure a specific deployment type.
Refer to these topics:
- Creating an online deployment. Create an online (also called Web service) deployment to load a model or Python code when the deployment is created to generate predictions online, in real time.
- Creating a batch deployment. A batch deployment processes input data from a file, data connection, or connected data in a storage bucket, and writes the output to a file.
- Deploying Python functions. Deploying functions gives you the ability to hide details (such as credentials), preprocess data before you pass it to models, handle errors, and include calls to multiple models, all within the deployed function instead of in your application.. You can deploy a Natural Language Processing model by using Python functions or Python scripts. Both online and batch deployments are supported.
- Deploying scripts. Deploy Python scripts.
- Creating a deployment job. From a deployment space, you can create, schedule, run, and manage jobs that process data for batch deployments, Python functions, and scripts.
- Getting the deployment endpoint URL. To send payload data to a model or function deployment for analysis, you need to know the endpoint URL of the deployment.
Parent topic: Deploying and managing models