Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Subscribe
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
DSPy: Develop a RAG app using DSPy, Weaviate, and FastAPI
Rating: 3.2 out of 5(5 ratings)
38 students

DSPy: Develop a RAG app using DSPy, Weaviate, and FastAPI

Master Full-Stack RAG App Development with FastAPI, Weaviate, DSPy, and React
Created byFranck Stéphane
Last updated 9/2024
English

What you'll learn

  • Build and Deploy a Full-Stack RAG Application
  • Efficient Data Management with Weaviate
  • Document Parsing and File Handling
  • Implement Advanced Backend Features with FastAPI

Course content

5 sections • 14 lectures • 1h 51m total length

  • Introduction1:40

    In this module, you will learn how to build a retrieval augmented generation (RAG) application using FastAPI, DSPy, and Weaviate. Your application will have a React frontend that you will create.

    The adventure begins...

  • Extra: Learn to build an audio AI assistant3:16

    A quick overview of the architecture of the audio AI assistant you are going to build, as an extra of this course.

  • Building the API with FastAPI10:47

    In this video, I will guide you step by step on how to set up a FastAPI API, and add DSPy service to it.

Requirements

  • Basic Knowledge of Python
  • Familiarity with REST APIs
  • Understanding of Frontend Development
  • Development Environment Setup

Description

Learn to build a comprehensive full-stack Retrieval Augmented Generation (RAG) application from scratch using cutting-edge technologies like FastAPI, Weaviate, DSPy, and React. In this hands-on course, you will master the process of developing a robust backend with FastAPI, handling document uploads and parsing with DSPy, and managing vector data storage using Weaviate. You'll also create a responsive React frontend to provide users with an interactive interface. By the end of the course, you'll have the practical skills to develop and deploy AI-powered applications that leverage retrieval-augmented generation techniques for smarter data handling and response generation.


Here's the structured outline of your course with sections and lectures:


Section 1: Introduction


  1. Lecture 1: Introduction

  2. Lecture 2: Extra: Learn to Build an Audio AI Assistant

  3. Lecture 3: Building the API with FastAPI


Section 2: File Upload


  1. Lecture 4: Basic File Upload Route

  2. Lecture 5: Improved Upload Route


Section 3: Parsing Documents


  1. Lecture 6: Parsing Text Documents

  2. Lecture 7: Parsing PDF Documents with OCR


Section 4: Vector Database, Background Tasks, and Frontend


  1. Lecture 8: Setting Up a Weaviate Vector Store

  2. Lecture 9: Adding Background Tasks

  3. Lecture 10: The Frontend, Finally!


Section 5: Extra - Build an Audio AI Assistant


  1. Lecture 11: What You Will Build

  2. Lecture 12: The Frontend

  3. Lecture 13: The Backend

  4. Lecture 14: The End

Who this course is for:

  • Backend Developers wanting to learn how to build APIs with FastAPI and integrate AI-driven features like document parsing and vector search.
  • Full-Stack Developers seeking to gain practical experience in combining a React frontend with an AI-powered backend.
  • Data Scientists and AI Practitioners who want to explore new ways to implement retrieval-augmented generation models for real-world applications.
  • AI Enthusiasts curious about vector databases like Weaviate and the emerging field of RAG, with the motivation to learn and build AI-based apps from scratch.

Report abuse