8 Use the Text Classification Service
The text classification service can be used to assign labels and probablilities to text input. The text classification service uses the same container image as the Private AI Services Container Private Large Language Model Service.
The text classification service of the Private AI Services Container helps applications categorize text by using a configured classification model. Applications can use classification results to support tasks such as sentiment analysis, request routing, moderation, or other label-based decision workflows. The service returns model-generated labels with associated probabilities, so applications can evaluate both the predicted class and the confidence of the result.
The text classification service is exposed through models that provide the
TEXT_CLASSIFICATION capability. For vLLM models, the container
administrator declares this capability in the service configuration, and the service
maps the model to the classification endpoint. At runtime, the inference client sends
text to the classification model, and the model returns one or more labels and
probabilities. Endpoint validation ensures that classification requests are served only
by models with the appropriate capability.
- Configure a Text Classification Model
A container administrator can configure a text classification model in the container configuration file. The exact configuration depends on the model type and runtime. - Send a Text Classification Request
Use the/classifyendpoint to classify one or more text inputs.