Developing LLM Applications with LangChain

本课程是 Building LLMs with Hugging Face and LangChain 专项课程的一部分

位教师：Edureka

访问权限由 New York State Department of Labor 提供

4个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

1 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

4个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

1 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将获得的技能

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

13 项作业

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

积累特定领域的专业知识

本课程是 Building LLMs with Hugging Face and LangChain 专项课程专项课程的一部分

在注册此课程时，您还会同时注册此专项课程。

向行业专家学习新概念
获得对主题或工具的基础理解
通过实践项目培养工作相关技能
获得可共享的职业证书

该课程共有4个模块

This course introduces the concepts, tools, and practical techniques behind LangChain, the leading framework for building intelligent applications powered by Large Language Models (LLMs). It blends conceptual understanding with hands-on implementation to help you design, build, and deploy context-aware, tool-using AI systems.

Whether you’re a developer, data scientist, or AI practitioner, this course provides a clear roadmap for transforming LLMs into dynamic, reasoning-driven applications that interact with real-world data and APIs. Through guided lessons, structured demonstrations, and project-based learning, you’ll explore how LangChain connects prompts, models, memory, and tools into composable workflows. You’ll learn to build Retrieval-Augmented Generation (RAG) pipelines, integrate LangServe for deployment, and implement LangSmith for observability and evaluation. The course culminates with a capstone Knowledge Assistant project, where you’ll combine RAG, multi-agent systems, and secure API integrations into a fully functional, deployable AI assistant. By the end of this course, you will be able to: • Understand the architecture and components of LangChain for LLM development. • Build multi-step reasoning pipelines and retrieval-augmented generation (RAG) workflows. • Implement memory, tools, and agents to enable contextual, goal-oriented behavior. • Evaluate and optimize LLM applications for performance, safety, and scalability. This course is ideal for AI developers, data scientists, and software engineers seeking to go beyond prompt-based experimentation and build real-world, production-ready LLM applications. A working knowledge of Python and APIs is recommended, but the course provides guided support to help learners of all backgrounds master the LangChain ecosystem. Join us to master the framework that powers today’s most advanced generative AI applications.

Learn the foundations of LangChain and its Expression Language (LCEL) for building modular, composable LLM workflows. This module covers core components such as prompt templates, memory, and chain composition, enabling learners to design structured reasoning pipelines and create their first multi-step LLM chain.

涵盖的内容

15个视频5篇阅读材料4个作业1个讨论话题

15个视频总计67分钟

Specialization Introduction 6分钟
Course Introduction 5分钟
What Is LangChain and how it works with LLMs and LCEL 4分钟
Understanding the LangChain Workflow and Architecture 4分钟
Demonstration: Installing and Setting Up LangChain Environment (Colab + API Keys) 4分钟
Demonstration: Building Your First LLM Chain Using LCEL 6分钟
Prompt Templates and Memory in LangChain 4分钟
Designing Adaptive Prompt Templates for Context Control and Validation 4分钟
Demonstration: Adding Conversation Memory to an LLM Chat Chain 5分钟
Demonstration: Integrating Pydantic with LCEL for Structured Outputs 6分钟
Understanding LCEL and Runnables in LangChain 4分钟
Chain Types in LangChain — Sequential, Router and Custom 4分钟
Designing Modular Reasoning Workflows in LangChain 4分钟
Demonstration: Building a Multi-Step Reasoning Chain for QnA (LCEL) 5分钟
Demonstration: Converting Chains to LCEL-Runnables for Efficient Execution 5分钟

5篇阅读材料总计75分钟

Welcome to Developing LLM Applications and LangChain 15分钟
LangChain Overview, LCEL Basics and Key Concepts 15分钟
Reading: Prompt Design Patterns and Context Retention Techniques 15分钟
Best Practices for Chain Composition and LCEL Integration 15分钟
Summary of LangChain Fundamentals 15分钟

4个作业总计48分钟

Introduction to LangChain - Setup and Core Concepts 6分钟
Practice Quiz : Designing Dynamic AI Contexts 6分钟
Practice Quiz : Building and Combining Chains with LCEL/Runnables 6分钟
Knowledge Check: LangChain Fundamentals 30分钟

1个讨论话题总计10分钟

Introduce Yourself 10分钟

Explore Retrieval-Augmented Generation (RAG) to connect LLMs with external knowledge sources. Learners will build document ingestion and validation pipelines, create embeddings, and evaluate retrieval workflows using LangSmith. By the end, you’ll construct a retrieval-based Q&A system powered by LangChain.

涵盖的内容

12个视频4篇阅读材料4个作业

12个视频总计56分钟

Why Context Matters in LLM Responses 4分钟
Embeddings, Vectors and LCEL in RAG 4分钟
Demonstration: Creating Text Embeddings Using Hugging Face or OpenAI Models 5分钟
Demonstration: Setting Up a Vector Store with FAISS 5分钟
Working with Document Loaders and Text Splitters 4分钟
Document Processing and Validation Workflow in LangChain 3分钟
Demonstration: Loading and Splitting Text Files for Indexing 5分钟
Demonstration: Validating Documents with Pydantic and LCEL 6分钟
Designing the Retrieval Workflow 3分钟
Observability and Evaluation in RAG Pipelines Using LangSmith 3分钟
Demonstration: Building Vector Stores to Retreiver Chain 6分钟
Demonstration: Querying Your Documents with a Context-Aware LLM 6分钟

4篇阅读材料总计60分钟

Overview of RAG Architecture and LCEL for RAG 15分钟
LangChain Document Loader Reference and Validation Patterns 15分钟
Evaluating RAG Performance, Observability with LangSmith 15分钟
Summary of Building Context-Aware Applications - RAG and Document Pipelines 15分钟

4个作业总计48分钟

Practice Quiz : Retrieval-Augmented Generation Concepts 6分钟
Parctice Quiz: Loading, Preprocessing, and Validating Documents 6分钟
Practice Quiz : Building and Evaluating a Retrieval Pipeline 6分钟
Knowledge Check: Building Context-Aware Applications - RAG and Document Pipelines 30分钟

Discover how to build dynamic, decision-making AI systems using LangChain agents and LangServe. This module focuses on creating tool-using agents, integrating secure APIs, and deploying workflows as production-ready services. Learners will complete the capstone Knowledge Assistant, combining chains, RAG, and multi-agent communication protocols.

涵盖的内容

15个视频4篇阅读材料4个作业

15个视频总计77分钟

What Are Agents and How They Use Tools 3分钟
Deploying and Managing Agents via LangServe APIs 3分钟
Demonstration: Creating a Simple Tool-Using Agent 6分钟
Demonstration: Adding Your RAG Pipeline as a Tool 7分钟
LangGraph Overview — Connecting Agents with Workflow Graphs (Brief Introduction) 3分钟
Connecting APIs and Tracking Agents with LangSmith 3分钟
Demonstration: Connecting to a Weather API for Real-Time Updates 6分钟
Demonstration: Building Smarter Agents with Memory and Decision Flow - I 5分钟
Demonstration: Building Smarter Agents with Memory and Decision Flow - II 4分钟
Capstone Overview and Architecture Planning 4分钟
Demonstration: Building AI Financial Agents with Python 7分钟
Demonstration: Advanced Tools for AI Trading Systems 6分钟
Demonstration: AI Trading Agents in Action 7分钟
Demonstration: AI Orchestration with Python 4分钟
Demonstration: Interactive AI Financial Dashboard with Streamlit 7分钟

4篇阅读材料总计60分钟

LangChain Agent Types, LangServe Concepts 15分钟
Secure API Integration, Key Management, and Observability with LangSmith 15分钟
MCP, ACP, ANP, and A2A Protocol Reference Notes 15分钟
Summary of Connecting Agents and Tools 15分钟

4个作业总计48分钟

Practice Quiz : Understanding LangChain Agents and LangServe 6分钟
Practice Quiz : Integrating APIs, LangGraph, and Observability 6分钟
Practice Quiz : Building and Testing Your Knowledge Assistant 6分钟
Knowledge Check: Connecting Agents and Tools 30分钟

Deploy, refine, and optimize your multi-agent Knowledge Assistant for real-world use. This module emphasizes fine-tuning, performance monitoring, and best practices for scalable LangServe deployments. Learners reflect on their project, review key takeaways, and prepare for advanced experimentation with custom and fine-tuned LLMs.