Agentic RAG Workshop: From Fundamentals to Real-World Implementations
23 August 2025 | 09:30AM - 05:30PM | La Marvella:- 2nd Block, Jayanagar, Bengaluru
About the workshop
Agentic RAG adds a “brain” to the RAG pipeline – bringing reasoning, tool use, and adaptiveness – which translates to tangible business value in accuracy, flexibility, and user trust
This workshop is a deep dive into Agentic RAG (Retrieval-Augmented Generation) – an emerging approach that combines the power of LLM-based agents with retrieval techniques to build smarter AI applications. Over an 8-hour session (of course including breaks in between), participants will explore how to move beyond “vanilla” RAG pipelines and infuse them with agentic behavior for greater flexibility and intelligence.
The full-day (8-hour) session employs Google Colab notebooks for immersive practice. Participants will work with:
- Azure Document Intelligence for complex document parsing and handling multi-modal content (text + images).
- Chroma Vector DB for semantic storage and retrieval.
- LangChain for application development.
- LangGraph for agent orchestration and complex workflow management.
- Langfuse for agentic tracing, observability, and evaluation.
Big Business Benefits of Agentic RAG
Agentic RAG empowers large-scale, enterprise-ready AI systems by combining retrieval-augmented generation with intelligent, decision-making agents. The result? Smarter, more reliable, and adaptable GenAI solutions.
- Higher Accuracy & Trust – Agents reason, validate, and reduce hallucinations.
- Multi-Modal Intelligence – Combine text, image, and structured data seamlessly.
- Observability & Evaluation – Langfuse for full agent tracing and performance insights.
- Dynamic Multi-Source Retrieval – Use Chroma vector DB + Travily web search + API & DB integrations.
- Autonomous Problem Solving – Complex queries handled via reasoning + tool orchestration.
💡 Think of Agentic RAG as adding a decision-making brain to your RAG pipeline—boosting precision, flexibility, and business value.
Workshop Flow
We will start with the Capstone Project overview—a real-world, multi-modal Agentic RAG application—explaining all the complex concepts we will learn and implement during the day. This includes:
- Multi-source data ingestion (files, web, APIs, images).
- Complex document parsing with Azure Document Intelligence.
- Multi-modal retrieval and reasoning.
- Agent orchestration with LangGraph.
- Observability & evaluation with Langfuse.
Prerequisite:
- Basic Python skills
- Introductory level exposure to LLMs and RAG
- Familiarity with LangChain or similar frameworks
- Exposure to vector databases and embeddings
*Note: These are tentative details and are subject to change.
Modules
Start with a clear understanding of the RAG architecture, its role in grounding LLM outputs, and methods for reducing hallucinations. Then, compare traditional RAG and Agentic RAG side-by-side—covering architectural differences, reasoning capabilities, adaptability, observability, and trade-offs like complexity vs. latency. Learn where each approach shines and when to use which.
Dive into the Reason + Act (ReAct) framework for building agents that interleave reasoning steps with tool usage. Understand the step-by-step decision process of LLMs, how actions are selected, and how observations feed back into reasoning.
Hands-On: Build a ReAct Agent in Colab that queries multiple sources (vector store, API, and a file) to answer a multi-hop question—observing the reasoning trace and decision flow.
Master hybrid search (semantic + keyword), metadata filtering, reranking, and multi-hop strategies to enhance precision and relevance.
Embed LLM agents into workflows. Explore memory, tool use, multi-step logic, and decision orchestration to build dynamic and responsive systems.
Use LangGraph to craft modular, interpretable agent flows—with state transitions, loops, and conditional logic—all within LangChain’s ecosystem.
Introduce Langfuse, a tool for comprehensive agentic tracing and observability. Learn how to instrument your workflow, monitor behavior, and evaluate agent performance in real time.
Explore reusable patterns such as retrieval routers and tool-selectors. Learn decision criteria to pick the right pattern for your use case.
Work through a practical, capstone project—module by module—to build a full Agentic RAG system using diverse data sources. Participants will implement retrieval, reasoning, tool orchestration, tracing, and evaluation collaboratively.
Explore Graph RAG using Neo4j, merging graph-based retrieval with agentic orchestration. Learn how to fuse structured graph queries and robust agent behavior for enhanced context modeling and reasoning.
Certificate of Completion
Receive a digital (blockchain-enabled) and physical certificate to showcase your accomplishment to the world
- Earn your certificate
- Share your achievement
