Retrieval-Augmented Generation (RAG) for AI Engineers - Build Production-Ready Applications
Build Production Ready RAG Apps with Python FastAPI ChromaDB and LLMs
Created by Ahmed Sawy
Explore the full process of building a retrieval-augmented generation (RAG) application, from document ingestion to answer generation. Work hands-on with Python, ChromaDB, FastAPI, and modern LLMs. Learn how to design prompts, evaluate results, deploy your app, and handle errors for robust production use.
Packt | Sep 2026 | 363 min
What You Will Learn
You will start by learning the fundamentals of RAG, LLMs, and embeddings, then move on to building document pipelines and question-answering features in Python. As you progress, you'll refactor your project for maintainability, add API endpoints with FastAPI, and create a user interface with Gradio. You'll also evaluate and improve retrieval quality, and strengthen error handling for reliability.
Key Features
- Build document ingestion and retrieval pipelines using Python and ChromaDB
- Develop FastAPI endpoints and a Gradio interface for interactive RAG apps
- Enhance retrieval with hybrid search, reranking, and robust evaluation methods
Target Audience
Ideal for Python developers, AI engineers, and software professionals who want to build practical RAG and LLM-powered applications. If you have basic Python skills and are interested in document retrieval, APIs, and deploying AI solutions, you'll benefit from this course. No prior experience with AI or RAG is required.
