Search courses ranked by devsSee how

2 recommendations
2recommends

Learn RAG

Guil Hernandez
Guil Hernandez
Scrimba
Scrimba
Recommended

Extra perks unlocked via skillcraft.ai link

This course will teach you how to craft and use embeddings in vector databases. Start off by getting the hang of embeddings and why they're key in AI's thinking process. Then you'll get hands-on practice, as you'll be chunking text documents, generating embeddings, and plugging them into vector databases using tools like Supabase. As you build out your app, you will use similarity searches to find the relevant embeddings in your vector database. Finally, you'll combine these results with the ChatCompletions API from OpenAI to create human-like chat responses. This course is a mix of theory and interactive challenges. By the end, you won't just get the tech stuff; you'll actually have built a proof-of-concept AI Movie Recommendation engine that you can add to your portfolio.

Instructor

Guil Hernandez

Guil Hernandez

Lifelong learner, enthusiastic about changing lives through tech. Enjoys water sports and exploring the South Florida waters.

Course details

Duration

1 hour 34 minutes

Format

video

Certificate

Included

Pricing

Subscription

What you'll learn

Understand embeddings and their role in AI systems

Chunking text documents for optimal processing

Generating embeddings from text data

Working with vector databases using Supabase

Prerequisites

Intermediate JavaScript understanding

Experience working with APIs

Async JavaScript knowledge

Basic understanding of databases

Who this course is for

Developers wanting to improve LLM accuracy

Engineers building AI-powered applications

Developers interested in vector databases

Anyone looking to reduce AI hallucinations

Curriculum

Your next big step in AI engineering

2:58

What are embeddings?

6:13

Set up environment variables

1:34

Create an embedding

5:46

Challenge: Pair text with embedding

4:22

Vector databases

3:00

Set up your vector database

3:13

Store vector embeddings

5:47

Semantic search

4:54

Query embeddings using similarity search

9:53

Create a conversational response using OpenAI

8:13

Chunking text from documents

9:36

Challenge: Split text, get vectors, insert into Supabase

5:39

Error handling

3:00

Query database and manage multiple matches

6:08

AI chatbot proof of concept

6:22

Retrieval-augmented generation (RAG)

1:38

Solo Project: PopChoice

4:32

You made it to the finish line!

1:38

Notice something missing?

Help us improve this course information for the community

Suggest an edit
Loading reviews...