Building Generative AI Apps with LangChain
Duration
2 Days
Level
Intermediate Level
Design and Tailor this course
As per your team needs
This course provides an overview into the world of generative artificial intelligence (Gen AI) and the use of large language models (LLMs). As a participant, you’ll explore the key concepts, techniques, and best practices involved in working with popular large language models.
LangChain is an open-source framework that allows developers working with AI to combine 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 and can even work with confidential enterprise data securely.
This course also facilitates entry into the AI field for individuals from diverse backgrounds and enables the deployment of AI as a service. In this course, we’ll go over LangChain components, LLM wrappers, Chains, and Agents. We’ll also dive deep into embeddings and vector databases such as Pinecone that enable scaling Gen AI apps.
This course on Generative AI and LangChain is designed to benefit individuals in various roles who are interested in working with LLMs:
- Developers and AI professionals Learn LangChain to integrate LLMs with external resources for scalable AI applications.
- Data scientists: Apply LangChain for custom document processing and analysis.
- Product managers & AI Enthusiasts: Understand Generative AI capabilities and LangChain applications for informed decisions.
- Getting Started – AI vs ML vs Generative AI
- Understanding Generative AI
- Key Step In Generative AI For Text – Predicting Next Word
- Exploring Predictive Machine Learning vs Generative AI
- Introduction to LangChain
- Setting Up the Environment: LangChain, Pinecone, and Python-dotenv
- LLM Models (Wrappers): GPT-3
- ChatModels: GPT-3.50
- Prompt Templates
- Simple Chains
- Sequential Chains
- Introduction to LangChain Agents
- LangChain Agents in Action
- Short Recap of Embeddings
- Introduction to Vector Databases
- Diving into Pinecone, Part 2
- Splitting and Embedding Text Using LangChain
- Inserting the Embeddings into a Pinecone Index • Asking Questions (Similarity Search)
- Project Introduction
- Loading Your Custom (Private) PDF Documents
- Loading Different Document Formats
- Public and Private Service Loaders
- Chunking Strategies and Splitting the Documents
- Embedding and Uploading to a Vector Database (Pinecone)
- Asking and Getting Answers
- Adding Memory (Chat History)
- Project Introduction
- Summarizing Using a Basic Prompt
- Summarizing using Prompt Templates
- Summarizing Using StuffDocumentsChain
- Summarizing Large Documents Using map_reduce
- map_reduce With Custom Prompts
- Summarizing Using the refine CombineDocumentChain
- refine With Custom Prompts
- Summarizing Using LangChain Agents
- Programming in Python.
- Fundamental concepts in AI or ML.
- Familiarity with using command-line tools.
