Skip to content

All about RAGs - How to develop RAG based solutions, Origin, Evolution, Use Case

Photo of SUCHETA G DHERE
Hosted By
SUCHETA G D.
All about RAGs - How to develop RAG based solutions, Origin, Evolution, Use Case

Details

Stimulating Talk, Live Demos and Interactive discussions by Founder Mohammed Lokhandwala : Investor TrustTalk, Mechatron, Chemistcraft ++

All About RAGs: Foundations, Evolution, and Hands-On Application Development

## ๐Ÿ‘ฅ Target Audience:

  • Beginners to GenAI
  • Developers new to RAG-based architecture
  • Product/solution architects exploring GenAI integration
  • AI/ML enthusiasts interested in applied use cases

***

## ๐ŸŽฏ Objectives:

  • Understand what RAG is and why it matters
  • Trace the origin and evolution of RAG in the context of GenAI
  • Learn how to build RAG systems step-by-step
  • Explore unique, real-world use cases that RAG uniquely solves
  • Position RAG in todayโ€™s GenAI ecosystem alongside Agents and other paradigms

***

## ๐Ÿงฑ Session Breakdown & Topics:

### ๐ŸŸฆ 1. Setting the Context: Why RAG?

  • The limitations of LLMs (hallucination, knowledge cutoff)
  • Need for real-time, factual grounding
  • Transition from static to retrieval-augmented knowledge flows
  • Intro to retrieval-augmented generation (RAG)

### ๐ŸŸฆ 2. Origins & Evolution of RAG

  • Early use of embeddings and vector search (pre-LLMs)
  • Evolution of toolchains: Pinecone, Weaviate, LangChain, LlamaIndex

### ๐ŸŸฆ 3. Core Components of a RAG Architecture

  • Embedding Models (OpenAI, Cohere, SentenceTransformers)
  • Vector Databases (Chroma, Pinecone, Weaviate, FAISS)
  • Chunking, indexing, retrieval
  • Prompt engineering & context injection
  • Generation via LLM (OpenAI, Anthropic, Mistral, etc.)
  • Evaluation techniques (retrieval precision, groundedness)

### ๐ŸŸฆ 4. Building Your First RAG Application: Hands-On Guide

  • ๐Ÿ”น Use case selection (e.g., internal knowledge assistant, customer FAQ bot)
  • ๐Ÿ”น Data preparation: chunking, metadata, format
  • ๐Ÿ”น Creating embeddings (with open-source or API)
  • ๐Ÿ”น Choosing and using a vector DB
  • ๐Ÿ”น Implementing retrieval and generation logic
  • ๐Ÿ”น UI + deployment (e.g., Streamlit, Gradio, LangChain + FastAPI)
  • ๐Ÿ”น Optional: Add memory, conversation history, feedback loops

### ๐ŸŸฆ 5. Advanced Topics (Briefly Introduce)

  • Hybrid Retrieval (semantic + keyword)
  • Structured RAG (e.g., SQL-based retrieval)
  • Agent-RAG hybrid systems

### ๐ŸŸฆ 6. Use Cases that Only RAG Can Solve Well

  • ๐Ÿ”ธ Legal document assistants grounded in latest court rulings
  • ๐Ÿ”ธ Internal enterprise Q&A systems (doc + intranet)
  • ๐Ÿ”ธ Academic research summarizers across journals
  • ๐Ÿ”ธ Real-time support chatbots referencing dynamic product manuals
  • ๐Ÿ”ธ Domain-specific compliance tools

### ๐ŸŸฆ 7. RAG vs. Agents vs. Fine-tuning

  • When to use RAG vs fine-tuning
  • When to layer Agents on top of RAG
  • RAG is not obsolete: it's foundational for grounding and precision
  • RAGโ€™s role in AI assistants (retrieval for tools, memory, real-time data)
  • We can also add "Conceptual introduction to Agentic and tools"

### ๐ŸŸฆ 8. Best Practices and Pitfalls

  • Chunking strategy & context window size
  • Evaluation metrics (factuality, latency, hallucination rate)
  • Common mistakes (irrelevant retrieval, poor chunking, bad metadata)
  • Cost-performance tradeoffs

***

## ๐Ÿ”ง Suggested Tools & Stack for Demos:

  • LangChain or LlamaIndex
  • OpenAI / Cohere / HuggingFace embeddings
  • ChromaDB / FAISS / Pinecone
  • GitHub starter kits (can be pre-shared)
Photo of Pune Women in Machine Learning & Data Science group
Pune Women in Machine Learning & Data Science
See more events
ClearRoute
WeWork Raheja Woods, Raheja Woods, 8, Central Ave, Kalyani Nagar, Pune, Maharashtra 411006 ยท Pune
Google map of the user's next upcoming event's location
FREE