ADaSci Premium Membership fee will be revised from 1st March 2024. Lock your membership for 1 year at current price.

Diving Deeper into Retrieval-Augmented Generation (RAG) with Vector Databases

4,972.00

  • This is a live workshop, to be held online
  • You will get the workshop joining link after your purchase
  • ADaSci members can register for free

Description

Date: 13th Jan 2024

Time: 10 AM to 1 PM

 

Tired of generic AI responses? Unleash the power of Retrieval-Augmented Generation (RAG) with this hands-on workshop! Dive into how RAG leverages vector databases to retrieve context-rich information, boosting your LLMs to generate precise, human-quality text. Master the fusion of retrieval and generation, crafting responses informed by deep understanding. Leave equipped to build AI systems that adapt to any prompt, generating tailor-made text masterpieces.

Major Outline

  1. Introduction to RAG & Why It Matters
  2. Understanding Vector Databases
  3. Retrieval & Search Strategies
  4. Augmenting LLMs with Retrieved Context
  5. Fine-tuning LLMs for RAG Applications
  6. Building & Deploying RAG Systems
  7. Advanced Topics & Future Trends
  8. Hands-on Lab Sessions

Learning Outcomes

  1. Master the core principles of RAG and its advantages over pure generative models.
  2. Gain hands-on experience with vector databases and retrieval techniques for RAG.
  3. Develop skills for crafting effective prompts and augmenting LLMs with retrieved context.
  4. Understand the tools and strategies for building, deploying, and optimizing RAG systems.

Requirements

  1. Google Colab / Jupyter notebook
  2. Good speed internet connectivity

Instructor

Sachin Tripathi, Manager – AI Research at AIM