RAG Engineering: Retrieval-Augmented Generation in Production
Design, build and evaluate RAG systems that answer reliably from your own documents, with citations and access control.
- ✓ Instructor-led live sessions, online or in Bengaluru
- ✓ Hands-on labs in every module
- ✓ Capstone project with trainer review
- ✓ Curriculum customisable for corporate teams
- ✓ Certificate of completion
Next batch: Sat, 09 Jan 2027 · 32 hours · 4 days
RAG Engineering: Retrieval-Augmented Generation in Production
Duration: 32 hours · 4 days
Next batch: Sat, 09 Jan 2027
Format: Online live · Bengaluru classroom
Modules: 9 · Topics: 42
Level: Intermediate to Advanced
Fee: ₹14,999
Trusted by leading experts
Upcoming batches
Open batches for individuals; corporate batches on your dates.
| Programme | Starts | Mode | Schedule | Duration | |
|---|---|---|---|---|---|
| RAG Engineering: Retrieval-Augmented Generation in Production | Sat, 09 Jan 2027 | Online live | Weekend (Sat) | 5 Saturdays | Enquire |
| RAG Engineering: Retrieval-Augmented Generation in Production | Wed, 03 Feb 2027 | Online live | Weekday | 4 days | Enquire |
| RAG Engineering: Retrieval-Augmented Generation in Production | Sat, 20 Mar 2027 | Online live | Weekend (Sat) | 5 Saturdays | Enquire |
Soaring demand, and where it takes you
RAG has become one of the most common enterprise GenAI patterns, and teams that can make it accurate and measurable are in high demand.
Become an expert
Roles this programme prepares you for:
Become a RAG Engineer
Designs and tunes retrieval pipelines for LLM applications.
- Design ingestion pipelines for PDFs, HTML and tables
- Choose chunking strategies and embedding models
- Implement hybrid keyword and vector search with re-ranking
About the course
A deep, hands-on course in retrieval-augmented generation: ingesting and chunking documents, embeddings and vector search, hybrid retrieval and re-ranking, prompt assembly with citations, access control and, above all, evaluation. Participants build and measure a production-style RAG system.
Design, build and evaluate RAG systems that answer reliably from your own documents, with citations and access control.
Why should I attend?
Python developers and backend engineers
Data and ML engineers
Search engineers
Technical leads evaluating RAG architectures
Prerequisites
Python; basic understanding of LLMs and prompting; SQL helpful
Level
Intermediate to Advanced
Delivery modes, duration and fee
Online live
Instructor-led virtual classroom; weekday (full-day) or weekend (Saturday) batches
Bengaluru classroom
In-person batches at our Bengaluru training venue
On-site at your office
Private corporate batch anywhere in India, scheduled around your teams
Blended
Live sessions plus guided self-paced labs and mentor check-ins
Duration: 32 hours · 4 days
Course fee (open batch): ₹14,999
Corporate / team batches: per-participant or flat batch pricing on request, based on group size, format and customisation.
What will you learn
- Design ingestion pipelines for PDFs, HTML and tables
- Choose chunking strategies and embedding models
- Implement hybrid keyword and vector search with re-ranking
- Assemble prompts with citations and refusal behaviour
- Evaluate retrieval and answer quality systematically
- Enforce document-level access control
Skills you will gain
Retrieval
Generation
Evaluation
Tools and platforms covered
Python
LangChain
PostgreSQLpgvector
Elasticsearch
Hugging Face
FastAPICourse curriculum
M01 RAG fundamentals
- Why RAG
- Architecture overview
- RAG vs fine-tuning
- Naive vs advanced RAG
- Common failure modes
🧪 Hands-on: Run a baseline RAG app
M02 Ingestion and chunking
- Parsing PDFs and HTML
- Chunk size and overlap
- Metadata enrichment
- Table and image handling
- Deduplication and versioning
🧪 Hands-on: Compare chunking strategies
M03 Embeddings and vector search
- Embedding models
- Vector indexes (HNSW)
- Filtering
- Choosing a vector database
- Index tuning and recall
🧪 Hands-on: Index a corpus in pgvector
M04 Hybrid retrieval and re-ranking
- BM25 plus vectors
- Cross-encoder re-rankers
- Query rewriting
- Multi-query and HyDE
- Parent-child and sentence-window retrieval
🧪 Hands-on: Measure gains from hybrid plus re-ranking
M05 Generation with citations
- Prompt assembly
- Citations and quoting
- Handling no-answer cases
- Answer formatting
- Streaming responses
🧪 Hands-on: Add citations and refusals
M06 Evaluation and access control
- Building test sets
- Retrieval and answer metrics
- Permission-aware retrieval
- Online feedback loops
- Document-level permissions at query time
🧪 Hands-on: Build an evaluation report
M07 Advanced RAG patterns
- Graph RAG concepts
- Agentic retrieval
- Structured data with text-to-SQL
- Multimodal RAG
🧪 Hands-on: Add a text-to-SQL tool alongside document retrieval
M08 Running RAG in production
- Incremental re-indexing
- Caching
- Latency budgets
- Monitoring retrieval quality
🧪 Hands-on: Build an incremental indexer with quality dashboards
M09 Capstone: enterprise knowledge assistant
- Requirements and test set
- Build
- Evaluate and iterate
- Present results
🧪 Hands-on: Deliver a permission-aware, cited assistant with an evaluation report
Hands-on projects
Policy assistant
A cited Q&A assistant over a set of HR or IT policies, with an evaluation report.
Hybrid search service
A search API combining keyword and semantic retrieval.
Why train with us
Built around your stack
Labs and examples adapted to the tools, cloud and data your team actually uses.
Practice-first
Every module ends in a lab, and the course ends with a reviewed capstone.
Practitioner-led
Delivered by Karthick Selvam and vetted specialist trainers from our network.
Visible progress
Attendance, lab completion and assessment results shared with your L&D team.
Certificate of completion
Participants who complete the labs and capstone receive a Learning Dots certificate of completion for RAG Engineering: Retrieval-Augmented Generation in Production. [confirm certificate wording / sample image]
Learner reviews
“[Verified learner review for this course]”
“[Verified learner review for this course]”
Meet your trainer
Karthick Selvam
Founder · Data Engineering Corporate Trainer, Bengaluru
[Trainer bio, experience and areas of expertise]
Frequently asked questions
Which vector database do you use?
Labs use PostgreSQL with pgvector by default; the concepts transfer to other vector stores.
Is this suitable for beginners?
Participants should be comfortable with Python and basic APIs.
Can the curriculum be customised for our team?
Yes. Modules, depth, duration and labs can be tailored to your stack and goals.
What delivery formats are available?
Online live instructor-led sessions, Bengaluru classroom, or on-site at your office.
How do we enquire or book?
Use the enquiry form on this page or the Enquire button next to any batch.
What does it cost?
The open-batch fee is ₹14,999 per participant plus GST. Corporate batches are priced on group size, format and customisation.
How long is the course?
32 hours · 4 days. Corporate batches can be split into half-day sessions.
A closer look
About this course
A deep, hands-on course in retrieval-augmented generation: ingesting and chunking documents, embeddings and vector search, hybrid retrieval and re-ranking, prompt assembly with citations, access control and, above all, evaluation. Participants build and measure a production-style RAG system.
What is RAG Engineering: Retrieval-Augmented Generation in Production?
Design, build and evaluate RAG systems that answer reliably from your own documents, with citations and access control.
Who this course is for
Python developers and backend engineers, Data and ML engineers, Search engineers, Technical leads evaluating RAG architectures.
What you will be able to do
Design ingestion pipelines for PDFs, HTML and tables. Choose chunking strategies and embedding models. Implement hybrid keyword and vector search with re-ranking. Assemble prompts with citations and refusal behaviour. Evaluate retrieval and answer quality systematically. Enforce document-level access control.
Career paths
Roles this course supports include RAG Engineer, AI Search Engineer, GenAI Application Developer. RAG has become one of the most common enterprise GenAI patterns, and teams that can make it accurate and measurable are in high demand.
AI & GenAI guides
Generative AI vs Traditional AI: What Is the Difference?
Traditional AI mostly predicts or classifies. Generative AI produces new content. Both have a place in the enterprise.
What Is Prompt Engineering?
Prompt engineering is the practice of writing instructions that get reliable, useful output from a language model.
What Is ChatGPT and How Does It Relate to Other AI Assistants?
ChatGPT is a conversational AI assistant from OpenAI, built on large language models. It is one of several similar assistants.
How to Compare AI Assistants for Your Team
Several general-purpose AI assistants compete for enterprise use. Rather than chasing rankings, evaluate them against your own needs.