# TensorFlow Serving

TensorFlow Serving is an application that takes trained Artificial Intelligence models and makes them available for use. It is open source and self-hosted, installable on Docker Hub.

Canonical page: https://ourlocalhost.com/app/6650/tensorflow-serving

## Description

TensorFlow Serving is an application that takes trained Artificial Intelligence models and makes them available for use. It acts as a bridge, allowing websites or mobile apps to send data to the AI and receive instant predictions or decisions in return without needing to understand the underlying code.

## Platform availability

Available on 0 of 6 install platforms.

## Links

- Docker Hub: https://hub.docker.com/r/tensorflow/serving
- GitHub: https://github.com/tensorflow/serving
- Official website: http://www.tensorflow.org/serving
- Documentation: http://www.tensorflow.org/install

## Common questions

### Can TensorFlow Serving serve models that are not TensorFlow models?

It has out-of-the-box integration with TensorFlow models. It can also be extended to serve other types of models and data.

### Does it support different versions of a model for clients?

It manages model lifetimes and provides clients with versioned access to models.

### Is TensorFlow Serving used for training or inference?

It handles the inference aspect of machine learning by taking models after training and serving them. It is not described in the source as a training system.

### What client-facing API is documented for accessing the server?

The documentation lists a Server API and a REST Client API.

---
Source: Our Local Host (https://ourlocalhost.com/app/6650/tensorflow-serving), the self-hosted and open-source app directory.