English | MP4 | AVC 1920×1080 | AAC 44KHz 2ch | 23 Lessons (2h 38m) | 456 MB
This portfolio project involves building a state-of-the-art LLM-powered Q&A application using LangChain, Pinecone, and OpenAI, all with only basic Python knowledge required! Here’s your opportunity to jump into the world of AI and LLMs.
LLMs (Language Model) such as GPT are great at answering questions about the data they have been trained on… But what if you want to ask them questions about data they were not trained on? For example, perhaps you want to ask them about information after their training date, or about data from unpublished papers? One of the best ways to do this is to input information, even large amounts of information such as books and documents, into the model. And that’s exactly what this project will teach you how to do from scratch!
In this project, you’ll learn how to build advanced applications that utilize LLM using LangChain, Pinecone, OpenAI, and Python! We will build together, step by step, line by line. It will be a hands-on learning experience.
WHY THIS PROJECT IS GREAT?
This project is designed for a portfolio. It will take approximately 3 hours to learn LangChain and build a Q&A application.
LangChain is an open platform that enables developers to work with artificial intelligence by combining large language models (LLMs), such as GPT-4, with external sources of computation and data. This makes it easy to build and deploy scalable and performant artificial intelligence applications. LangChain provides a unique entry point into the field of artificial intelligence for professionals from different domains and enables the deployment of artificial intelligence as a service. It has an almost infinite number of real-world applications.
Table of Contents
1 Project Demo
2 Introduction to LangChain
3 Setting Up The Environment LangChain, Pinecone, and Python-dotenv
4 LLM Models (Wrappers) GPT-3
5 ChatModels GPT-3.5-Turbo and GPT-4
6 Prompt Templates
7 Simple Chains
8 Sequential Chains
9 Introduction to LangChain Agents
10 LangChain Agents in Action
11 Short Recap of Embeddings
12 Introduction to Vector Databases
13 Splitting and Embedding Text Using LangChain
14 Inserting the Embeddings into a Pinecone Index
15 Asking Questions (Similarity Search)
16 Project Introduction
17 Project Introduction
18 Project Introduction
19 Public and Private Service Loaders
20 Chunking Strategies and Splitting the Documents
21 Embedding and Uploading to a Vector Database (Pinecone)
22 Asking and Getting Answers
23 Adding Memory (Chat History)
Resolve the captcha to access the links!