Creating a Chat Tool Using OpenAI Models and Pinecone

Course details

Embeddings and vector databases allow developers to create tools that can retrieve knowledge from custom documents and use it to form more accurate and dynamic conversations. But while cutting-edge AI models like ChatGPT can generate useful conversational responses to many different kinds of queries, the replies are always limited to the data that was available when the model was last trained. In this course, instructor Guil Hernandez offers an overview of text embeddings, vector databases, and retrieval-augmented generation (RAG) to elevate and optimize your AI learning journey. Along the way, test out your new skills in the exercise challenges provided at the end of each section.

Learning objectives
Discover embeddings in the context of generative AI.
Set up and store embeddings in a vector database.
Utilize best practices related to retrieval-augmented generation (RAG).
Generate conversational responses from data retrieved from a vector database using OpenAI models and Pinecone.

Concepts

0. Introduction

01 - Building context-aware AI tools with custom knowledge bases
02 - What you should know about AI and JavaScript
03 - Set up the project

1. Text Embeddings

04 - The importance of embeddings in generative AI
05 - Create embeddings with OpenAI
06 - Pair embeddings with related text
07 - Text chunking for embeddings
08 - Challenge - Chunk text and create embeddings
09 - Solution - Chunk text and create embeddings

2. Vector Databases

10 - The power of vector databases
11 - Set up a vector database with Pinecone
12 - Store embeddings in Pinecone
13 - What is semantic search
14 - Send queries to Pinecone
15 - Challenge - Insert and retrieve data from Pinecone
16 - Solution - Insert and retrieve data from Pinecone

3. Conversational Responses with OpenAI and Pinecone

17 - Retrieval-augmented generation (RAG)
18 - Create replies and manage messages with OpenAI
19 - Form a reply from multiple database matches
20 - Enhance the AI's context awareness
21 - Handling errors

Conclusion

22 - Next steps

Creating a Chat Tool Using OpenAI Models and Pinecone

Authors

Guil Hernandez