Serve a Compound Model you own this product

prerequisites
intermediate Python • intermediate ML and AI • basic NumPy • basic Hugging Face
skills learned
use Ray Serve • use FastAPI • NLP text preprocessing • use Hugging Face transformers to transform text
Delio D'Anna
1 week · 4-6 hours per week · INTERMEDIATE

pro $24.99 per month

  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose one free eBook per month to keep
  • exclusive 50% discount on all purchases

lite $19.99 per month

  • access to all Manning books, including MEAPs!

team

5, 10 or 20 seats+ for your team - learn more


Look inside

The company you work for, which provides a news feed aggregator, is plagued with an influx of hoaxes that are putting its reputation in jeopardy. The data science team has already trained a set of complex natural language processing (NLP) models to distinguish real news from fake news. Your task is to build a service, using Ray, that exposes the endpoint that returns the JSON object categorized as either a hoax or news. Then, you’ll optimize the service for performance and speed, enabling it to perform more parallel operations and use as many GPUs as possible. When you’re finished, you’ll have firsthand experience using some of Ray Serve’s advanced features for serving and optimizing a compound model—and you’ll have kept your company’s reputation safe.

This project is designed for learning purposes and is not a complete, production-ready application or solution.

project author

Delio D'Anna

Delio D’Anna holds a degree in computing and mathematical science and earned a postgrad diploma in computing. He’s worked in the software industry for over 10 years, mainly on web applications with languages such as PHP, JavaScript, Python, and JavaFirst, as well as Go. He co-authored a book titled The Go Workshop. His focus remains on microservices, scalability, and domain-driven design. In the last 2 years, he’s been working with Python to put trained models in production and automate training pipelines, with a focus on leveraging the increasingly popular Ray framework and tools for ensuring that several models and inference pipelines can be run in parallel.

prerequisites

This liveProject is for data scientists who want to prepare their ML models for deployment to production, as well as software engineers who need to overcome the challenges of ML applications. To begin these liveProjects you’ll need to be familiar with the following:

TOOLS
  • Intermediate Python (declare variables and functions, loops, branches, import modules, basic object-oriented programming, pickling)
  • Beginner NumPy
  • Beginner Hugging Face
TECHNIQUES
  • Intermediate ML and AI (classification, word tokenization, word embedding)

features

Self-paced
You choose the schedule and decide how much time to invest as you build your project.
Project roadmap
Each project is divided into several achievable steps.
Get Help
While within the liveProject platform, get help from other participants and our expert mentors.
Compare with others
For each step, compare your deliverable to the solutions by the author and other participants.
book resources
Get full access to select books for 90 days. Permanent access to excerpts from Manning products are also included, as well as references to other resources.

choose your plan

team

monthly
annual
$49.99
$499.99
only $41.67 per month
  • five seats for your team
  • access to all Manning books, MEAPs, liveVideos, liveProjects, and audiobooks!
  • choose another free product every time you renew
  • choose twelve free products per year
  • exclusive 50% discount on all purchases
  • Serve a Compound Model project for free