09-20-2024, 10:57 AM
Zero To Hero In Langchain: Build Genai Apps Using Langchain
Published 8/2024
MP4 | Video: h264, 1920x1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 2.49 GB | Duration: 5h 18m
Learn all features of LangChain & build Generative AI applications with Memory, RAG, Tools, Agents etc. using LangChain
[b]What you'll learn[/b]
Discover the core principles of LangChain and its application in building Generative AI models
Master the creation and use of Prompt Templates, including chat prompt templates and few-shot prompt templates, to optimize AI interactions
Develop complex chain structures, such as LLMChains and Sequential Chains, to enhance the functionality of AI-driven applications
Implement dynamic execution flows using LCEL-based Chains and Runnables, including controlling execution flow and dynamic routing
Utilize memory in LangChain to build advanced conversational AI that can remember and recall user interactions across sessions
Create a Retrieval-Augmented Generation (RAG) application, including document reading, chunking, embedding, and data retrieval from a vector database
Design and integrate custom tools and agents, including memory-enabled agents, into your LangChain applications to extend their capabilities
Construct a graphical user interface (GUI) for your Generative AI applications using Streamlit, enabling user-friendly interactions with your AI models
[b]Requirements[/b]
Basic Python knowledge, familiarity with AI concepts, and access to a computer with internet are recommended; no advanced AI experience required.
[b]Description[/b]
Are you ready to transform your ideas into powerful Generative AI applications? Do you want to master a cutting-edge framework that can revolutionize how you interact with AI models? If you're an aspiring AI developer, data scientist, or tech enthusiast eager to build advanced AI applications from scratch, then this course is designed for you."Zero to Hero in LangChain: Build GenAI apps using LangChain" is your comprehensive guide to mastering LangChain, an innovative framework that streamlines the creation of sophisticated AI-driven applications. Whether you're a beginner or someone with some experience in AI, this course will take you on a journey from understanding the basics to implementing complex applications that leverage memory, retrieval-augmented generation (RAG), tools, agents, and more.In this course, you willevelop your first LangChain application and set up a robust development environment.Master the use of Prompt Templates, Chains, and Runnables to create versatile AI interactions.Implement dynamic execution flows and output parsing to enhance your AI models.Harness the power of memory in LangChain to build conversational AI with context retention.Create a fully functional RAG pipeline to maximize the value of your data retrieval processes.Build custom tools and agents, and learn how to integrate them into your applications.Monitor and optimize your applications using LangSmith.Design user-friendly interfaces for your AI apps with Streamlit.Why should you learn LangChain? As the AI landscape rapidly evolves, the ability to build applications that can interact intelligently with vast datasets and maintain coherent conversations is a game-changer. LangChain offers a powerful, flexible framework that simplifies this process, making it accessible even if you're just getting started.Throughout the course, you'll complete hands-on projects that reinforce your learning, ensuring you not only understand the theory but can apply it effectively. From building conversational AI with memory to creating sophisticated RAG applications, you'll gain practical experience in every aspect of LangChain.This course stands out because it not only covers the "how" but also the "why" behind every feature of LangChain. As an expert in the field, I'll guide you through each step, ensuring you gain the skills and confidence needed to build impactful AI applications.Don't miss this opportunity to become a LangChain expert and take your AI skills to the next level. Enroll now and start building the future of AI applications!
Overview
Section 1: Introduction
Lecture 1 Introduction
Lecture 2 What is LangChain and Why it is used
Lecture 3 Demonstration of LangChain based Applications
Lecture 4 Setting up the development environment
Section 2: Getting Started
Lecture 5 Creating your first LangChain Application
Lecture 6 Difference between LLM models and Chat models
Lecture 7 Model parameters for customizing the LLM Models
Lecture 8 Image generation and other tools
Section 3: Prompt Templates
Lecture 9 Introduction to Prompt Templates in LangChain
Lecture 10 Creating a Prompt Template
Lecture 11 Chat prompt template
Lecture 12 Few shot prompt template
Section 4: Chains
Lecture 13 Introduction to Chains in LangChain
Lecture 14 LLMChain - General Purpose Chain
Lecture 15 Utility Chains - LLM Math Chain
Lecture 16 Sequential Chains
Section 5: LCEL based Chains and Runnables
Lecture 17 Pipe operator
Lecture 18 Understanding Runnables - Theory lecture
Lecture 19 Runnable Parallel, Runnable Passthrough and Runnable Lambda
Lecture 20 Example: Controlling execution flow using LCEL
Lecture 21 Understanding dynamic routing of flow
Lecture 22 Implementing dynamic routing
Section 6: Output Parsing
Lecture 23 Introduction to Output Parsers
Lecture 24 Stroutputparser - String Output
Lecture 25 Structured Output Parser
Lecture 26 CSV and DateTime Parser
Section 7: Memory in LangChain
Lecture 27 Introduction to memory in LangChain
Lecture 28 Conversation Buffer Memory
Lecture 29 Customizing memory - memory key and adding messages
Lecture 30 Conversation Chain
Lecture 31 Conversation Buffer Window Memory
Lecture 32 Conversation Summary Memory
Lecture 33 Runnable with Message History
Section 8: Retrieval Augmented Generation using LangChain (RAG)
Lecture 34 Understanding RAG concepts
Lecture 35 Reading the documents - RAG step 1
Lecture 36 Creating chunks - RAG step 2
Lecture 37 Embedding - RAG step 3
Lecture 38 Storing in Vector Database - RAG step 4
Lecture 39 Retrieving and building complete RAG application
Section 9: Tools and Agents
Lecture 40 Introduction to Tools and Agents
Lecture 41 Making your own custom tool
Lecture 42 In-built tools - DuckDuckGo Search and Wikipedia
Lecture 43 Agents in LangChain
Lecture 44 Creating Agent with memory
Section 10: LangSmith for monitoring our Application
Lecture 45 Introduction to LangSmith
Lecture 46 Running application and monitoring using LangSmith
Section 11: Creating Graphical UI using Streamlit
Lecture 47 What is Streamlit
Lecture 48 Making GUI for our GenAI app in Streamlit
Section 12: Conclusion
Lecture 49 About your certificate
Lecture 50 Bonus lecture
Aspiring AI developers who want to build and deploy advanced Generative AI applications using LangChain,Data scientists aiming to enhance their AI models with memory, retrieval-augmented generation (RAG), and custom tool integrations,Software engineers looking to master LangChain for creating dynamic and interactive AI-driven applications,Tech enthusiasts eager to explore the latest frameworks and techniques for developing cutting-edge AI solutions,AI researchers interested in applying LangChain's features to improve conversational AI and data retrieval systems,Product managers who want to understand the capabilities of LangChain to lead AI-driven product development effectively
[b]What you'll learn[/b]
Discover the core principles of LangChain and its application in building Generative AI models
Master the creation and use of Prompt Templates, including chat prompt templates and few-shot prompt templates, to optimize AI interactions
Develop complex chain structures, such as LLMChains and Sequential Chains, to enhance the functionality of AI-driven applications
Implement dynamic execution flows using LCEL-based Chains and Runnables, including controlling execution flow and dynamic routing
Utilize memory in LangChain to build advanced conversational AI that can remember and recall user interactions across sessions
Create a Retrieval-Augmented Generation (RAG) application, including document reading, chunking, embedding, and data retrieval from a vector database
Design and integrate custom tools and agents, including memory-enabled agents, into your LangChain applications to extend their capabilities
Construct a graphical user interface (GUI) for your Generative AI applications using Streamlit, enabling user-friendly interactions with your AI models
[b]Requirements[/b]
Basic Python knowledge, familiarity with AI concepts, and access to a computer with internet are recommended; no advanced AI experience required.
[b]Description[/b]
Are you ready to transform your ideas into powerful Generative AI applications? Do you want to master a cutting-edge framework that can revolutionize how you interact with AI models? If you're an aspiring AI developer, data scientist, or tech enthusiast eager to build advanced AI applications from scratch, then this course is designed for you."Zero to Hero in LangChain: Build GenAI apps using LangChain" is your comprehensive guide to mastering LangChain, an innovative framework that streamlines the creation of sophisticated AI-driven applications. Whether you're a beginner or someone with some experience in AI, this course will take you on a journey from understanding the basics to implementing complex applications that leverage memory, retrieval-augmented generation (RAG), tools, agents, and more.In this course, you willevelop your first LangChain application and set up a robust development environment.Master the use of Prompt Templates, Chains, and Runnables to create versatile AI interactions.Implement dynamic execution flows and output parsing to enhance your AI models.Harness the power of memory in LangChain to build conversational AI with context retention.Create a fully functional RAG pipeline to maximize the value of your data retrieval processes.Build custom tools and agents, and learn how to integrate them into your applications.Monitor and optimize your applications using LangSmith.Design user-friendly interfaces for your AI apps with Streamlit.Why should you learn LangChain? As the AI landscape rapidly evolves, the ability to build applications that can interact intelligently with vast datasets and maintain coherent conversations is a game-changer. LangChain offers a powerful, flexible framework that simplifies this process, making it accessible even if you're just getting started.Throughout the course, you'll complete hands-on projects that reinforce your learning, ensuring you not only understand the theory but can apply it effectively. From building conversational AI with memory to creating sophisticated RAG applications, you'll gain practical experience in every aspect of LangChain.This course stands out because it not only covers the "how" but also the "why" behind every feature of LangChain. As an expert in the field, I'll guide you through each step, ensuring you gain the skills and confidence needed to build impactful AI applications.Don't miss this opportunity to become a LangChain expert and take your AI skills to the next level. Enroll now and start building the future of AI applications!
Overview
Section 1: Introduction
Lecture 1 Introduction
Lecture 2 What is LangChain and Why it is used
Lecture 3 Demonstration of LangChain based Applications
Lecture 4 Setting up the development environment
Section 2: Getting Started
Lecture 5 Creating your first LangChain Application
Lecture 6 Difference between LLM models and Chat models
Lecture 7 Model parameters for customizing the LLM Models
Lecture 8 Image generation and other tools
Section 3: Prompt Templates
Lecture 9 Introduction to Prompt Templates in LangChain
Lecture 10 Creating a Prompt Template
Lecture 11 Chat prompt template
Lecture 12 Few shot prompt template
Section 4: Chains
Lecture 13 Introduction to Chains in LangChain
Lecture 14 LLMChain - General Purpose Chain
Lecture 15 Utility Chains - LLM Math Chain
Lecture 16 Sequential Chains
Section 5: LCEL based Chains and Runnables
Lecture 17 Pipe operator
Lecture 18 Understanding Runnables - Theory lecture
Lecture 19 Runnable Parallel, Runnable Passthrough and Runnable Lambda
Lecture 20 Example: Controlling execution flow using LCEL
Lecture 21 Understanding dynamic routing of flow
Lecture 22 Implementing dynamic routing
Section 6: Output Parsing
Lecture 23 Introduction to Output Parsers
Lecture 24 Stroutputparser - String Output
Lecture 25 Structured Output Parser
Lecture 26 CSV and DateTime Parser
Section 7: Memory in LangChain
Lecture 27 Introduction to memory in LangChain
Lecture 28 Conversation Buffer Memory
Lecture 29 Customizing memory - memory key and adding messages
Lecture 30 Conversation Chain
Lecture 31 Conversation Buffer Window Memory
Lecture 32 Conversation Summary Memory
Lecture 33 Runnable with Message History
Section 8: Retrieval Augmented Generation using LangChain (RAG)
Lecture 34 Understanding RAG concepts
Lecture 35 Reading the documents - RAG step 1
Lecture 36 Creating chunks - RAG step 2
Lecture 37 Embedding - RAG step 3
Lecture 38 Storing in Vector Database - RAG step 4
Lecture 39 Retrieving and building complete RAG application
Section 9: Tools and Agents
Lecture 40 Introduction to Tools and Agents
Lecture 41 Making your own custom tool
Lecture 42 In-built tools - DuckDuckGo Search and Wikipedia
Lecture 43 Agents in LangChain
Lecture 44 Creating Agent with memory
Section 10: LangSmith for monitoring our Application
Lecture 45 Introduction to LangSmith
Lecture 46 Running application and monitoring using LangSmith
Section 11: Creating Graphical UI using Streamlit
Lecture 47 What is Streamlit
Lecture 48 Making GUI for our GenAI app in Streamlit
Section 12: Conclusion
Lecture 49 About your certificate
Lecture 50 Bonus lecture
Aspiring AI developers who want to build and deploy advanced Generative AI applications using LangChain,Data scientists aiming to enhance their AI models with memory, retrieval-augmented generation (RAG), and custom tool integrations,Software engineers looking to master LangChain for creating dynamic and interactive AI-driven applications,Tech enthusiasts eager to explore the latest frameworks and techniques for developing cutting-edge AI solutions,AI researchers interested in applying LangChain's features to improve conversational AI and data retrieval systems,Product managers who want to understand the capabilities of LangChain to lead AI-driven product development effectively