Mastering RAG & Unlocking AI Potential: Build a RAG system using Python, Open-source LLMs & MongoDB Atlas
In this workshop, we will build a ChatBot based on Retrieval Augmented Generation (RAG). The ChatBot will leverage MongoDB Atlas, embedding models, Large Language Models (LLMs) to generate contextualized answers and textual content in accordance to users’ queries based on publicly available sources.
See this talk and many more by getting your ticket to PyCon AU now!
I want a ticket!In this hands-on workshop, attendees will:
- Learn the foundations of Retrieval Augmented Generation (RAG), such as chunking, embedding, and semantic search
- Perform semantic search queries against a MongoDB Atlas collection
- Build a simple RAG system using MongoDB Atlas and open-source LLMs
Add memory to the RAG application:
- In addition to these goals, the lab also offers more advanced content that covers:
- Combining pre-filtering with vector search
- Adding re-ranking to the RAG application
- Stream responses from the RAG application
Attendees will be provided with all the resources required to successfully execute the hands-on portions of the workshop, including a GitHub repository consisting of notebook templates with pseudocode. Attendees will replace the pseudocode with their own code during the workshop.
Throughout my tenure as a software engineer, technical lead, and engineering manager, I have navigated through public and private sectors, and fast-paced startups. Along this journey, I have delved into a broad spectrum of technologies from mobile and web, to data pipelines, cloud infrastructure, and automations. As a developer advocate at MongoDB, I would like to help fellow engineers make better design decisions with not just theoretical knowledge, but also a pragmatic mindset. On any typical day, you might catch me lost in thoughts with a cup of coffee in my hands.