Skip to content

Latest commit

 

History

History
49 lines (31 loc) · 2.38 KB

Challenge-03.md

File metadata and controls

49 lines (31 loc) · 2.38 KB
Raw

Challenge 03 - Grounding, Chunking, and Embedding

< Previous Challenge - Home - Next Challenge >

Pre-requisites

  • Azure Cognitive Search resource for indexing and retrieving relevant information
  • Azure OpenAI service for Generative AI Models and Embedding Models
  • Add required credentials of above resources in .env file
  • Install the required libraries in the requirements.txt file via pip install -r requirements.txt

Introduction

When working with large language models, it is important to understand how to ground them with the right data. In addition, you will take a look at how to deal with token limits when you have a lot of data. Finally, you will experiment with embeddings. This challenge will teach you all the fundamental concepts - Grounding, Chunking, Embedding - before you see them in play in Challenge 4. Below are brief introductions to the concepts you will learn.

Grounding is a technique used when you want the model to return reliable answers to a given question. Chunking is the process of breaking down a large document. It helps limit the amount of information we pass into the model. An embedding is an information dense representation of the semantic meaning of a piece of text.

Description

Questions you should be able to answer by the end of the challenge:

  • Why is grounding important and how can you ground a LLM model?
  • What is a token limit?
  • How can you deal with token limits? What are techniques of chunking?
  • What do embedding help accomplish?

You will run the following three Jupyter notebooks for this challenge. You can find them in the /Notebooks folder of Resources.zip file.

  • CH-03-A-Grounding.ipynb
  • CH-03-B-Chunking.ipynb
  • CH-03-C-Embeddings.ipynb

Success Criteria

To complete this challenge successfully, you should be able to:

  • Verify that you are able to ground a model through the system message
  • Demonstrate various chunking techniques
  • Demonstrate how to create embeddings

Additional Resources