D24
Data & AIIntermediate10 weeks
RAG AI & Automation
Learn to build retrieval-augmented AI systems that ground large language models in real data, then automate business workflows around them end to end.
What you'll learn
Building retrieval pipelines with embeddings and vector databases
Advanced retrieval techniques: hybrid search, re-ranking, and query rewriting
Automating multi-step workflows that combine LLM calls with business systems
Evaluating and deploying RAG systems with production-grade monitoring
Course details
Duration
10 weeks
Best for
Developers comfortable with Python who want to build production-grade AI search and automation systems
On completion
Verified certificate & placement assistance
Course Curriculum
A module-by-module breakdown of what you'll cover in RAG AI & Automation.
01
LLM & API Foundations
Weeks 1–2- Calling LLM APIs with structured JSON output
- Managing tokens, context windows, and rate limits
- Environment and secrets management
- Python fundamentals for AI engineering
02
Embeddings & Vector Search
Week 3- Embedding models and similarity metrics
- Working with Pinecone, Chroma, FAISS, and pgvector
- Index types: HNSW and IVF
- Benchmarking retrieval latency and accuracy
03
Document Processing & Chunking
Weeks 4–5- Parsing PDFs, HTML, and scanned documents
- Fixed vs. semantic chunking strategies
- Metadata tagging and overlap tuning
- Table and image extraction
04
Prompt Engineering for Grounded Answers
Weeks 6–7- System prompts for grounded, citation-backed answers
- Few-shot prompting and hallucination guardrails
- Context window budgeting
- Multi-turn retrieval conversations
05
Advanced Retrieval & Automation
Week 8- Hybrid search combining BM25 and vector retrieval
- Cross-encoder re-ranking and query rewriting
- Building automation workflows with n8n and LangChain/LangGraph
- Tool-calling orchestration and error handling
06
Evaluation & Production Deployment
Weeks 9–10- Scoring faithfulness, relevance, and precision with RAGAS
- Hallucination detection techniques
- Deploying with FastAPI and Docker
- Tracing, cost, and latency monitoring
Tools & Technologies
Hands-on practice with the same tools used by working professionals.
ClaClaude / OpenAI API
PinPinecone / pgvector
LanLangChain
LlaLlamaIndex
n8nn8n
CroCross-encoder rerankers
RAGRAGAS
LanLangfuse / LangSmith
Hands-on Projects
This is project-based learning — you'll build real, portfolio-ready work as you go, not just watch lectures.
Internal knowledge-base assistant — a retrieval-augmented Q&A tool over company docs with source citations
Hybrid search & re-ranking benchmark — compare vector-only search against a BM25 plus re-ranking pipeline
Support-ticket triage automation — auto-classify tickets, retrieve relevant content, and draft replies for human review
Low-hallucination compliance RAG — a citation-strict retrieval system with an explicit 'I don't know' fallback
RAG evaluation harness — a repeatable test suite scoring faithfulness and relevance across model changes
Every course includes a guided internship on top of your project work — so you graduate with real experience, not just a certificate.
Communication & Soft Skills
Built into every course, alongside the technical curriculum.
Communication Skills
Practice explaining technical work clearly to teammates, managers, and clients.
Teamwork & Collaboration
Work in small project teams using real workflows like stand-ups and code reviews.
Problem Solving
Build the habit of breaking down ambiguous problems into clear, solvable steps.
Time Management
Learn to plan, prioritize, and deliver project work against realistic deadlines.
Presentation Skills
Present your project work and results with confidence, as you would to a client.
Resume & Profile Building
Build a strong resume, LinkedIn profile, and project portfolio that recruiters notice.
Interview Preparation
Mock interviews and portfolio reviews to get you ready for real job applications.
Student Reviews
“I'd only used LLM APIs for basic chat before this. Building a hybrid search pipeline and actually measuring the precision gains changed how I think about retrieval.”
Aditya Rao
Backend Developer
“The evaluation module was the highlight for me — learning to score groundedness with RAGAS instead of eyeballing answers made my work feel production-ready.”
Sneha Kulkarni
Data Scientist
