Overview

Google, IBM & Meta Certificates – 40% Off

One Coursera Plus subscription covers most Professional Certificates on Coursera.

In this course, you'll learn how to build AI-powered RAG systems using Python and LangChain. You'll explore key concepts such as document context injection, setting up LLMs, and integrating embeddings. By the end of this course, you'll have the skills to design and implement efficient AI systems. This course teaches you how to build Retrieval Augmented Generation (RAG) systems from scratch using Python and LangChain 1. RAG is one of the most in-demand AI techniques today — it allows language models to answer questions using your own documents, data, and knowledge bases rather than relying solely on their training data. The course is split into two parts. In the first part, you'll build a document context injection system — learning how to load documents, split them into chunks, generate embeddings, and feed relevant context into an LLM to get accurate, grounded answers. This gives you a solid understanding of the core mechanics behind RAG. In the second part, you'll build a full RAG system using LangChain 1.0's retrieval chains. You'll implement vector stores, retrievers, and query pipelines that can search through your documents and generate precise answers with source references. By the end, you'll have a complete, working RAG pipeline that you can adapt to any document set or use case. This course is ideal for Python developers who want to build AI applications that work with private or domain-specific data — whether that's internal company documents, research papers, legal contracts, or any other text-based knowledge base. This course is ideal for developers, data scientists, and AI enthusiasts looking to enhance their understanding of building advanced AI systems with Python and LangChain. Basic knowledge of Python programming is recommended, and familiarity with machine learning concepts will help in grasping the course content quickly. You’ll learn through a hands-on approach, starting with building foundational components and progressing to more advanced techniques in AI development. Each section is designed to equip you with practical skills. By the end, you’ll have the confidence to create and deploy your own AI RAG systems. This course is based on Introduction to Building AI RAGs with Python and LangChain, by PythonHow, Ardit Sulce. This course is licensed and distributed by Packt. All rights reserved. Packt is one of the world's most prolific publishers of cutting-edge technical content. For over two decades we've made it our mission to curate and publish the knowledge of only the very best technical experts. We focus on real-world courses that help our customers get the job done, with coverage that extends across a wide range of established and cutting-edge technical topics. If you're an individual or an organisation that embraces learning by doing, Packt is the perfect fit for you.

Syllabus

Building Document Context Injection System with LangChain 1.0
- This module guides learners through the process of building a document context injection system using LangChain 1.0. Learners will gain hands-on experience with initializing language models, setting up system prompts, loading documents, and implementing continuous conversation capabilities. The focus is on practical skills for integrating document-based context into LLM interactions.
Building a Full RAG System with LangChain 1.0
- This module provides an in-depth exploration of building a Retrieval-Augmented Generation (RAG) system using LangChain 1.0. Learners will gain hands-on experience with setting up LLMs, embeddings, and vector stores, and understand how to retrieve and generate responses from documents effectively.