Home » Mastering LLM Agents with RAG, LangChain and Prompt Engineering

Mastering LLM Agents with RAG, LangChain and Prompt Engineering

Seminar for Tech Audience - Recommended to Attend with Laptops

Main Speaker

Valeria Aynbinder

Learning Tracks

AI, Data

Course ID

52027

Date

15-07-2025

Time

Daily seminar
9:00-16:30

Location

Daniel Hotel, 60 Ramat Yam st. Herzliya

Overview

Unlock the secrets to crafting intelligent and engaging chatbots and agents! This one-day, hands-on seminar is tailored for developers eager to harness the power of Large Language Models (LLMs). Explore Retrieval-Augmented Generation (RAG), LangChain and advanced prompt engineering techniques to design chatbots that deliver meaningful and effective conversations. Through practical exercises and expert guidance, gain the skills to integrate multi-agent workflows and tools into your chatbot solutions for dynamic user experiences.

Who Should Attend

Prerequisites

Expertise in modern programming language: This seminar is designed for developers with a strong foundation in one of modern programming languages, Python preferred.

Note: this seminar primarily uses Python and its libraries and frameworks for hands-on exercises and demos.

Familiarity with LLMs: Basic understanding of Large Language Models is recommended.

Course Contents

Large Language Models (LLMs):

Overview of LLM capabilities and potential applications.
Introduction to key architectures (e.g., Transformer-based models).
Understanding and mitigating LLM limitations and biases.

Retrieval-Augmented Generation (RAG):

Core principles of RAG for dynamic chatbot interactions.
Components of RAG: Retriever and Generator models.
Advantages of integrating RAG into chatbot development.
Hands-on Lab: Build a basic RAG-enabled chatbot.

LangChain:

Overview of LangChain functionalities and its role in conversation design.
Techniques for managing multi-step dialogues and contextual understanding.
Hands-on Lab: Extend chatbot capabilities using LangChain.

Prompt Engineering:

The significance of well-designed prompts in guiding LLM responses.
Techniques for creating precise, context-aware, and goal-oriented prompts.
Advanced approaches: Incorporating user intent, context, and specific outputs.
Examples of effective prompts for diverse chatbot scenarios.

Agents and Tool Building:

Introduction to agents and their applications in chatbots.
Utilizing agents to interact with external tools and APIs dynamically.

Building Multi-Agent Workflows with LangGraph:

Designing and orchestrating agent-based workflows.
Leveraging LangGraph for seamless integration of tasks across agents.
Use cases of multi-agent systems in chatbots (e.g., scheduling, recommendations).
Hands-on Lab: Develop a chatbot leveraging agents and LangGraph workflows.