Agentic AI With Python - Course
Eclasess is a leading IT Training Institute located in Ameerpet, Hyderabad Providing Quality Training and Placements for Students, Freshers and Working Professionals who are looking to start or upgrade their career. We Provide Training and Course Materials with a Free Demo for Agentic AI Training for Freshers.
Agentic AI With Python course content is designed to cover Python core concepts, advanced Python concepts, Generative AI, LangChain, tools, agents, LangGraph, MCP, Azure OpenAI and two end to end projects.
Agentic AI With Python - Course
The course is divided into six modules, starting from Python fundamentals and progressing into agentic AI application development, LangGraph workflows, MCP integrations, Azure OpenAI deployment and practical projects.
- Python Fundamentals
- Introduction to Python
- Python Local Setup using VS Code
- Variables and Data Types
- Typecasting in Python
- Taking User Input in Python
- Operators in Python
- Control Flow and Loops
- If-Else Conditional Statements
- For Loops in Python
- While Loops in Python
- Break, Continue, and Pass Statements
- Strings
- Strings in Python
- String Slicing and Indexing
- String Methods and Functions
- String Formatting and f-Strings
- Functions and Modules
- Defining Functions in Python
- Function Arguments & Return Values
- Lambda Functions in Python
- Modules and Pip - Using External Libraries
- Variable Scope and Docstrings
- Data Structures
- Introduction to Lists
- List Methods
- Tuples and Operations on Tuples
- Sets and Set Methods
- Dictionaries and Dictionary Methods
- Object Oriented Programming
- Introduction to OOP
- Classes and Objects in Python
- Constructors in Python
- Instance and Class Attributes
- Inheritance and Polymorphism
- Method Overriding and Operator Overloading
- Advanced Python Topics
- Decorators in Python
- Getters and Setters
- Static & Class Methods
- Exception Handling and Custom Errors
- Map, Filter and Reduce
- Args and Kwargs
- Working with Files
- File I/O in Python
- Read, Write, and Append Files
- External Libraries
- Package Management
- Requests Module - Working with APIs
- Regular Expressions in Python
- Generative AI
- What is Generative AI?
- What are LLMs?
- Introduction to OpenAI and ChatGPT
- Using ChatGPT for various tasks using manual prompting
- Applications that can be developed using LLMs
- Prompt Engineering Techniques
- Building a ChatGPT-like chatbot UI using Streamlit
- LangChain
- How a Typical AI Enabled App Works
- Why LangChain?
- Using LangChain for the First Time
- Understanding and Creating a First Chain
- Understanding Runnable in Detail
- Chaining Multiple Chains
- Chat vs Completion Style Models
- Implementing a Chat Chain
- Understanding Memory and Types of Memory
- Using LangSmith for Tracing
- Using Chainlit to Develop a Chatbot
- Embeddings, Vector Store & RAG
- Understanding Embeddings
- What is RAG?
- Using Document Loaders and Splitters
- Indexing
- Using Chroma DB as Vector Store
- Understanding Similarity Search
- Retrieving using Retrievers
- RAG with Agents
- RAG with Chains
- Understanding Tools and Agents
- Understanding How Agents Work
- Creating Tools and Agents using Tools
- Understanding Middleware
- Static and Dynamic Models
- Error Handling in Tools using Middleware
- Static and Dynamic Prompts
- Structured Output using Tool Strategy and Provider Strategy
- Understanding Memory
- Memory Management Techniques
- Trimming Messages and Message Summarization
- Using Database Toolkit and Code Execution Tools
- Agent Response Streaming
- Using Tool Runtime to Access State, Context, Store Commands and Stream Writer
- Mail Agent and Human in the Loop
- Implementing Guard Rails
- LangGraph
- Why LangGraph?
- Understanding LangGraph Components
- Understanding State of Graph and Creating State Graph
- Tool Node
- Conditional Branching in Graph
- Adding Memory to Graph
- Graph with Multiple Schemas
- Implementing a Chatbot using State Graph for Summarization
- Parallel Processing in LangGraph
- Dynamic Parallelization in LangGraph
- Multi Agentic Application using Supervisor Pattern
- Subgraphs
- Building SQL Agent
- MCP (Model Context Protocol)
- Why MCP?
- Creating a Custom MCP Server
- Using MCP Servers with Claude Desktop
- Stdio Client
- SSE Client
- Using MCP with LangChain
- Azure OpenAI
- Understanding Azure OpenAI and Azure Studio
- Deploying a Model in Azure OpenAI
- Using Playground in Azure Studio
- Understanding Managed and Serverless Deployments
- Creating Agents with No Code / Low Code
- Deploying Agents to Azure
- Module 6: Two End to End Projects
- Two End to End Projects
To Speak With an Expert
+91 7989781302
- Duration 45 Hours
- Trained Students 9921
- Days 45 Days
- Resume Preparation Yes
- Interview Guidance Yes
