Skip to content

datastaxdevs/workshop-ai-as-api

Repository files navigation

Workshop: AI as an API (W026)

The full course, including hands-on instructions, is on DataStax Academy. There, you will learn how to work in the Interactive Lab.

For best results: (1) Check the course start page. (2) Enroll in the course. (3) Start learning and practicing!

Start the course on DataStax Academy            Start the Interactive Lab on Gitpod

Learn to build your own NLP text classifier and expose it as an API using the following technologies:

  • AI-based text analysis with Tensorflow/Keras;
  • Astra DB, a Database-as-a-Service built on Apache Cassandra®;
  • FastAPI, the high-performance Python framework for creating APIs;
  • Many useful Python libraries and packages including pandas, pydantic, dotenv, sklearn, uvicorn, and more.

During this hands-on workshop, you will:

  • prepare the labeled dataset for model training;
  • train the model to classify any input text;
  • export the trained model and test it interactively;
  • create your free NoSQL database for data storage;
  • set up and start an API exposing the classifier as a reusable class;
  • learn how to speed up the API with DB-based caching;
  • inspect how a streaming response is handled in the API.

Prerequisites:

  • Familiarity with Python;
  • A Github account is required for the hands-on.