Mydra logo
Artificial Intelligence
DeepLearning.AI logo

DeepLearning.AI

Understanding and Applying Text Embeddings

  • up to 1 hour
  • Beginner

This course provides an in-depth understanding of text embeddings and their applications in various NLP tasks. Learn to use Google Cloud’s Vertex AI to build a question-answering system and gain proficiency in generating and integrating embeddings into common LLM applications.

  • Text embeddings
  • Semantic similarity
  • Text classification
  • Text clustering
  • Outlier detection

Overview

In this course, you will explore the properties of word and sentence embeddings and learn how to use them to measure semantic similarity between texts. You will apply text embeddings for tasks such as classification, clustering, and outlier detection. Additionally, you will learn to modify the text generation behavior of an LLM by adjusting parameters like temperature, top-k, and top-p. The course also covers the application of the open-source ScaNN library for efficient semantic search and building a Q&A system by combining semantic search with an LLM.

  • Web Streamline Icon: https://streamlinehq.com
    Online
    course location
  • Layers 1 Streamline Icon: https://streamlinehq.com
    English
    course language
  • Self-paced
    course format
  • Live classes
    delivered online

Who is this course for?

Data Scientists

Professionals looking to enhance their skills in natural language processing and text embeddings.

Machine Learning Engineers

Engineers who want to apply text embeddings to various NLP tasks such as classification and clustering.

AI Enthusiasts

Individuals with basic Python knowledge interested in learning about text embeddings and their applications.

Gain a comprehensive understanding of text embeddings and their applications in NLP tasks. Learn from industry experts and apply your knowledge to build advanced systems using Google Cloud’s Vertex AI. Ideal for beginners and professionals looking to enhance their skills.

Pre-Requisites

1 / 2

  • Basic Python knowledge

  • Familiarity with natural language processing concepts

What will you learn?

Introduction to Text Embeddings
Learn the basics of text embeddings and their importance in NLP tasks.
Properties of Word and Sentence Embeddings
Explore the properties of embeddings and how they can be used to measure semantic similarity.
Applying Text Embeddings
Use text embeddings for tasks such as classification, clustering, and outlier detection.
Semantic Search with ScaNN
Learn to apply the open-source ScaNN library for efficient semantic search.
Building a Q&A System
Combine semantic search with an LLM to build a question-answering system using Google Cloud’s Vertex AI.
LLM Parameter Tuning
Modify the text generation behavior of an LLM by adjusting parameters like temperature, top-k, and top-p.

Meet your instructors

  • Nikita Namjoshi

    Product Manager | Google.org Fellow, Google

    Nikita Namjoshi is a Product Manager and Google.org Fellow at Woodwell Climate Research Center. She focuses on mapping arctic permafrost thaw for climate action.

  • Andrew Ng

    Founder, DeepLearning.AI

    Andrew Ng is the Founder of DeepLearning.AI and Managing General Partner of AI Fund. He is also the Founder and CEO of Landing AI.

Upcoming cohorts

  • Dates

    start now

Free