Build an LLM-powered Q&A App using LangChain, OpenAI and Python
WHAT IS THIS PROJECT?
LLMs like GPT are great at answering questions about data they've been trained on...but what if you want to ask it questions about data it hasn't been trained on? For example, maybe you want to ask them about information from after their training cut-off date, or information from non-public documents? One of the best ways to do this is inputting the information, even large amounts of information such books and documents, into the model. And that's exactly what this project will teach you from scratch!
In this project you'll learn how to build state-of-the-art LLM-powered applications with LangChain, Pinecone, OpenAI, and Python! We'll build together, step-by-step, line-by-line. This will be a learning-by-doing experience.
WHY IS THIS PROJECT AWESOME?
This is a portfolio project. It requires about 3 hours to both learn LangChain and build the Q&A application.
LangChain is an open-source framework that allows developers working with AI to combine large language models (LLMs) like GPT-4 with external sources of computation and data. It makes it easy to build and deploy AI applications that are both scalable and performant. LangChain is a great entry point into the AI field for individuals from diverse backgrounds and enables the deployment of AI as a service. It has a virtually infinite number of practical use cases.
Watch Online Build an LLM-powered Q&A App using LangChain, OpenAI and Python
# | Title | Duration |
---|---|---|
1 | Project Demo | 05:25 |
2 | Introduction to LangChain | 07:16 |
3 | Setting Up The Environment: LangChain, Pinecone, and Python-dotenv | 11:02 |
4 | LLM Models (Wrappers): GPT-3 | 06:14 |
5 | ChatModels: GPT-3.5-Turbo and GPT-4 | 04:42 |
6 | Prompt Templates | 05:11 |
7 | Simple Chains | 05:50 |
8 | Sequential Chains | 08:08 |
9 | Introduction to LangChain Agents | 04:01 |
10 | LangChain Agents in Action | 05:29 |
11 | Short Recap of Embeddings | 01:53 |
12 | Introduction to Vector Databases | 06:58 |
13 | Splitting and Embedding Text Using LangChain | 09:20 |
14 | Inserting the Embeddings into a Pinecone Index | 07:54 |
15 | Asking Questions (Similarity Search) | 07:54 |
16 | Project Introduction | 06:09 |
17 | Loading Your Custom (Private) PDF Documents | 07:28 |
18 | Loading Different Document Formats | 05:13 |
19 | Public and Private Service Loaders | 04:38 |
20 | Chunking Strategies and Splitting the Documents | 06:39 |
21 | Embedding and Uploading to a Vector Database (Pinecone) | 11:18 |
22 | Asking and Getting Answers | 10:34 |
23 | Adding Memory (Chat History) | 09:06 |