RAG Workshop
From Zero to Production
One-day intensive, hands-on workshop. Build production-ready Retrieval-Augmented Generation pipelines with Python, LangChain, OpenAI & ChromaDB.
Inclusive of all materials, exercises & lifetime access to recordings
What You'll Learn
6 comprehensive modules taking you from RAG fundamentals to production-grade systems — with hands-on exercises in every module.
RAG Architecture
Understand the complete Retrieve-Augment-Generate pipeline from first principles.
Document Processing
Master chunking strategies, metadata enrichment, and handling real-world document formats.
Embeddings & Vector Stores
Choose the right embedding model, build indexes with ChromaDB, Pinecone & pgvector.
Production RAG Pipeline
Build an end-to-end Q&A bot with prompt engineering, conversation memory, and retrieval tuning.
Advanced Retrieval
HyDE, hybrid search, reranking, parent-child chunking, and agentic RAG patterns.
Evaluation & Production
RAGAS metrics, benchmarking, latency optimization, caching, and observability.
Detailed Schedule
9 hours of intensive, hands-on learning — lecture, demo & exercise in every module.
Curriculum Deep Dive
Every module follows a Lecture → Demo → Hands-On Exercise format. You'll write real code in every session.
RAG Foundations
- •Why RAG beats fine-tuning for most use cases
- •Core architecture: Retrieve → Augment → Generate
- •Key components: documents, chunks, embeddings, vector stores, LLM
- •Naive RAG vs. Advanced RAG taxonomy
"Break the LLM" — See firsthand why RAG matters by testing an LLM with and without context.
Document Processing & Chunking
- •Loading PDFs, DOCX, HTML, Markdown, CSV, web pages
- •5 splitting strategies: fixed-size, recursive, sentence, semantic, structure-aware
- •Chunk size & overlap tuning for optimal recall
- •Metadata as a retrieval superpower
"Chunk Lab" — Apply 3 chunking strategies to a 20-page PDF and compare retrieval quality.
Embeddings & Vector Stores
- •How semantic similarity works with vectors
- •Comparing embedding models: OpenAI, BGE, Nomic
- •Vector store options: ChromaDB, Pinecone, FAISS, pgvector, Weaviate
- •Batch embedding, upsert, and index management
"Build Your Index" — Embed a dataset with two models and compare retrieval results.
Building Your First RAG Pipeline
- •End-to-end query pipeline: embed → retrieve → prompt → generate
- •Prompt engineering for grounded answers
- •Top-k, score thresholds, and MMR for diversity
- •Conversation memory for multi-turn Q&A
"End-to-End RAG" — Build a working Q&A bot and benchmark it against 10 test questions.
Advanced Retrieval Techniques
- •HyDE, Multi-Query, Step-Back Prompting, Query Decomposition
- •Hybrid search: semantic + BM25 with Reciprocal Rank Fusion
- •Cross-encoder reranking (Cohere, BGE, FlashRank)
- •Parent-child chunking, sentence windows, multi-vector indexing
- •Intro to Agentic RAG: tool-calling agents that decide when to retrieve
"Advanced Retrieval Showdown" — Implement HyDE + reranking and measure precision improvement.
Evaluation & Production Readiness
- •RAGAS metrics: Faithfulness, Relevancy, Precision, Recall
- •Building benchmark datasets and LLM-as-evaluator
- •Common failure modes and targeted fixes
- •Production: latency, caching, cost, security, observability
- •Architecture patterns: multi-index, RAG+SQL, RAG+Knowledge Graph
"Evaluate & Iterate" — Run RAGAS, get a baseline, make one improvement, measure the delta.
Your Instructor
Sridhar Jammalamadaka
Founder, Future Proof India | AI Architect
- •16 years in IT with deep expertise in enterprise AI, cloud architecture, and scalable systems
- •AI Architect — former Software Architect at Oracle, M.Tech from IIIT Bangalore
- •Trained 1,400+ professionals in Agentic AI, RAG, and LLM Engineering
- •Built 30+ AI agents and 50+ AI chatbots for enterprise clients across healthcare, finance, and legal domains
- •Trainer at IIIT Bangalore Executive Education & AI Consultant serving India, Dubai, and USA
- •Weekly Agentathon organizer — participants build and ship an AI agent every Saturday
Who Is This For?
Software Engineers
Want to add RAG capabilities to your applications and understand the full pipeline.
Tech Leaders & Architects
Need to evaluate RAG solutions, make architecture decisions, and lead AI initiatives.
Data Scientists & ML Engineers
Looking to move beyond model training into building retrieval-augmented AI systems.
AI Enthusiasts
Have basic Python skills and want to learn the most in-demand AI engineering skill of 2026.
What's Included
Prerequisites
Invest in Your AI Career
One day that transforms your ability to build production AI systems.
- ✓Full-day live workshop (9 hours)
- ✓All 6 hands-on exercises with code
- ✓Workshop recording (lifetime access)
- ✓Certificate of completion
- ✓1-week post-workshop support
- ✓Private WhatsApp group access
WhatsApp us to complete registration. GST included. Refund available up to 24 hours before the event.
Frequently Asked Questions
Is this workshop online or offline?+
Will I get a recording?+
What if I'm a complete beginner in AI?+
What tools do I need?+
Can I get a refund?+
Will I be able to build a RAG app after this?+
Ready to Master RAG?
28 March 2026 · 10 AM – 7 PM IST · Live Online
Limited seats to ensure hands-on attention for every participant.
Register Now — ₹10,000Questions? Reach out to us:
📧 connect@futureproofindia.com · 📱 WhatsApp: +91 63603 19758