中文

LangChain / LangGraph

Curated LangChain / LangGraph tutorials.

All tutorials

LangChain / LangGraph

78 tutorials in this topic

Intermediate

Adaptive RAG: Advanced RAG Tutorial

Adaptive RAG Advanced Tutorial (2026): Route by query difficulty—answer directly without retrieval, single retrieval, or multi-hop iterative retrieval. Lower cost and improve accuracy, with CRAG self-correction variant. Naturally a LangGraph state graph, built on semantic search + reranking.

Advanced

Advanced RAG: Complete Guide 2026 – Beyond Basic Retrieval to Build Production-Grade Knowledge Bases

Basic RAG systems are easy to set up, but making them stable and effective in production is hard. This article dives deep into advanced RAG techniques: hybrid retrieval, reranking, multi-query decomposition, query routing, and systematic evaluation to improve RAG performance.

Intermediate

AI Agent Frameworks Compared: LangChain vs LlamaIndex vs AutoGen vs CrewAI

The AI agent framework landscape has exploded: LangChain, LlamaIndex, AutoGen, CrewAI, LangGraph, Phidata, and dozens of others. This comparison analyzes each framework across production readiness, learning curve, flexibility, performance, and ecosystem maturity. Includes architecture recommendations for different use cases: single-agent tools, multi-agent systems, RAG applications, and enterprise deployments.

Advanced

AI Agent Frameworks: LangChain, AutoGen & CrewAI for Production in 2025

AI agents go beyond chatbots—they use tools, maintain memory, plan multi-step tasks, and collaborate with other agents. This guide compares LangChain, LangGraph, AutoGen, and CrewAI for different use cases, covers reliable agent design patterns, tool calling best practices, memory architectures (short-term, long-term, episodic), handling errors and hallucinations, and deploying production agents with observability.

Advanced

AI Agent Memory Systems: Short-Term and Long-Term Memory

Design and implement memory systems for AI agents including working memory, episodic memory, and semantic memory. Learn how to give agents persistent context and personalization.

Advanced

AI Agents in Production: Architecture Patterns and Reliability Engineering

AI agents—autonomous systems that use tools and make decisions to complete multi-step tasks—are moving into production at enterprise scale. This guide covers reliable agent architecture: tool design and error handling, state management for long-running agents, human-in-the-loop patterns, observability and debugging agents, graceful failure modes, security considerations, and testing strategies for non-deterministic systems.

Intermediate

AI Observability: Tracing and Monitoring LLM Applications

Learn to implement comprehensive observability for LLM applications using LangSmith, Langfuse, and Helicone. Monitor latency, costs, errors, and output quality in real-time.

Intermediate

AI Observability: Monitoring LLMs and ML Models in Production in 2025

Deploying AI without observability is flying blind. This guide covers LLM-specific monitoring with LangSmith, Arize Phoenix, and Weights & Biases, detecting hallucinations and quality degradation, monitoring embedding drift for RAG systems, tracking token costs and latency SLAs, setting up alerting for AI failures, and building dashboards that give engineering and product teams visibility into AI system health.

Intermediate

AI Summarization Pipeline

AI Summarization Pipeline What You'll Build Summarizing long documents efficiently with map-reduce. By the end of this tutorial, you'll have a fully working implementation you can extend for production use. **Time**: ~25 minutes **Difficulty**:

Intermediate

Autonomous Research Agent

Autonomous Research Agent What You'll Build Building agents that autonomously search and synthesize. By the end of this tutorial, you'll have a fully working implementation you can extend for production use. **Time**: ~25 minutes **Difficulty**:

Intermediate

Build an AI Knowledge Graph with Neo4j + LangChain: Step-by-Step Tutorial 2026

Build an AI Knowledge Graph with Neo4j + LangChain Project Overview In this tutorial, you'll build a complete **semantic knowledge base** using Neo4j + LangChain. By the end, you'll have a production-ready application you can deploy and customize.

Intermediate

Build an Document Q&A with LangChain + Pinecone: Step-by-Step Tutorial 2026

Build an Document Q&A with LangChain + Pinecone Project Overview In this tutorial, you'll build a complete **enterprise knowledge base** using LangChain + Pinecone. By the end, you'll have a production-ready application you can deploy and customize

Advanced

Building Bug Fix Agent with AI Agents: Complete Guide 2026

Building Bug Fix Agent with AI Agents 2026 Introduction AI agents that can identify and fix bugs in codebases autonomously are transforming how developers work. This guide shows you how to build a production-ready Bug Fix Agent using Aider + Claude

Advanced

Building Code Review Agent with AI Agents: Complete Guide 2026

Building Code Review Agent with AI Agents 2026 Introduction AI agents that can automatically review pull requests for bugs and quality are transforming how developers work. This guide shows you how to build a production-ready Code Review Agent usin

Advanced

Building Content Writer Agent with AI Agents: Complete Guide 2026

Building Content Writer Agent with AI Agents 2026 Introduction AI agents that can research and write high-quality content at scale are transforming how developers work. This guide shows you how to build a production-ready Content Writer Agent using

Advanced

Building Customer Support Agent with AI Agents: Complete Guide 2026

Building Customer Support Agent with AI Agents 2026 Introduction AI agents that can handle customer inquiries using your knowledge base are transforming how developers work. This guide shows you how to build a production-ready Customer Support Agen

Advanced

Building Data Analysis Agent with AI Agents: Complete Guide 2026

Building Data Analysis Agent with AI Agents 2026 Introduction AI agents that can analyze datasets and generate insights autonomously are transforming how developers work. This guide shows you how to build a production-ready Data Analysis Agent usin

Advanced

Building DevOps Automation Agent with AI Agents: Complete Guide 2026

Building DevOps Automation Agent with AI Agents 2026 Introduction AI agents that can monitor systems and automate infrastructure tasks are transforming how developers work. This guide shows you how to build a production-ready DevOps Automation Agen

Advanced

Building Email Triage Agent with AI Agents: Complete Guide 2026

Building Email Triage Agent with AI Agents 2026 Introduction AI agents that can read, categorize, and draft email responses are transforming how developers work. This guide shows you how to build a production-ready Email Triage Agent using ReAct +

Advanced

Building Financial Analysis Agent with AI Agents: Complete Guide 2026

Building Financial Analysis Agent with AI Agents 2026 Introduction AI agents that can analyze financial data and generate investment reports are transforming how developers work. This guide shows you how to build a production-ready Financial Analys

Advanced

Building Research Assistant Agent with AI Agents: Complete Guide 2026

Building Research Assistant Agent with AI Agents 2026 Introduction AI agents that can search the web and synthesize research on any topic are transforming how developers work. This guide shows you how to build a production-ready Research Assistant

Advanced

Building SQL Query Agent with AI Agents: Complete Guide 2026

Building SQL Query Agent with AI Agents 2026 Introduction AI agents that can translate natural language to SQL and execute queries are transforming how developers work. This guide shows you how to build a production-ready SQL Query Agent using Lang

Advanced

Contextual Compression RAG: Implementation Guide with Pinecone 2026

Contextual Compression RAG: Complete Implementation 2026 Overview Contextual Compression RAG is a specialized retrieval pattern that focuses on compressing retrieved context to fit LLM window. This guide shows you how to build a production-ready sy

Intermediate

Conversational AI with Memory

Conversational AI with Memory What You'll Build Implementing persistent memory in chatbots. By the end of this tutorial, you'll have a fully working implementation you can extend for production use. **Time**: ~25 minutes **Difficulty**: Intermed

Advanced

Corrective RAG: Implementation Guide with Weaviate 2026

Corrective RAG: Complete Implementation 2026 Overview Corrective RAG is a specialized retrieval pattern that focuses on self-correcting retrieval with quality assessment. This guide shows you how to build a production-ready system using Weaviate.

Intermediate

CrewAI Tutorial 2026: Build Multi-Agent Systems That Work Together

Complete tutorial for building multi-agent AI systems using CrewAI in 2026. Covers agent role design, task delegation, crew orchestration, tool integration, and building production workflows where multiple specialized AI agents collaborate on complex tasks.

Advanced

CrewAI vs AutoGen vs LangGraph: Multi-Agent Framework 2026

Comprehensive comparison of CrewAI, AutoGen, and LangGraph for multi-agent AI systems. Covers role-based collaboration, conversation agents, state machines, and production deployment patterns.

Advanced

Cross-Encoder RAG: Implementation Guide with Qdrant 2026

Cross-Encoder RAG: Complete Implementation 2026 Overview Cross-Encoder RAG is a specialized retrieval pattern that focuses on neural reranking for high-precision retrieval. This guide shows you how to build a production-ready system using Qdrant.

Intermediate

Django + LangChain: How to Add AI to Django web apps (2026)

Django + LangChain Integration Guide 2026 Overview This guide shows you exactly how to add AI to Django web apps using Django and LangChain. We cover setup, core integration, and production-ready patterns. Prerequisites - Django environment set u

Beginner

Flowise Complete Tutorial 2026: How to create LangChain flows with drag-and-drop UI

Flowise Complete Tutorial 2026 What is Flowise? **Flowise** is a powerful visual LLM builder that enables you to create LangChain flows with drag-and-drop UI. It has become one of the most popular tools in the AI developer toolkit in 2026. Why Use

Advanced

Graph RAG: Implementation Guide with Neo4j 2026

Graph RAG: Complete Implementation 2026 Overview Graph RAG is a specialized retrieval pattern that focuses on knowledge graph traversal for multi-hop reasoning. This guide shows you how to build a production-ready system using Neo4j. Why Graph RAG

Advanced

Hierarchical Agent System: Complete Tutorial

Hierarchical Agent System Overview Multi-level agent hierarchy with delegation and reporting. This guide covers architecture, implementation, and production deployment of AI agents. Agent Architecture ``` User Input ↓ Agent Orchestrator ↓

Advanced

Hybrid Search RAG: Implementation Guide with Elasticsearch 2026

Hybrid Search RAG: Complete Implementation 2026 Overview Hybrid Search RAG is a specialized retrieval pattern that focuses on combining vector and keyword search for maximum recall. This guide shows you how to build a production-ready system using

Intermediate

LangChain Expression Language (LCEL): Tutorial and Best Practices

LangChain Expression Language (LCEL) What is LangChain? LangChain is a framework for composable chain building. It simplifies building AI applications by providing high-level abstractions over raw LLM APIs. **Best for**: chain composition Install

Advanced

LangChain LCEL: Advanced Patterns for Production AI Applications

LangChain Expression Language (LCEL) is the modern way to build composable LLM pipelines. This guide covers advanced LCEL patterns: parallel execution, streaming, dynamic routing, conditional chains, retry and fallback logic, tool use orchestration, and testing strategies. Includes production patterns for RAG applications, multi-step agents, and complex data transformation pipelines with real performance benchmarks.

Advanced

LangChain in Production: Best Practices, Pitfalls, and Performance Optimization

Production guide for LangChain applications covering caching strategies, error handling, observability with LangSmith, cost optimization, and common anti-patterns to avoid.

Advanced

Building Production RAG Systems with LangChain: From Prototype to 99.9% Uptime

Comprehensive guide to building production-grade RAG systems using LangChain — vector store selection, chunking strategies, retrieval optimization, evaluation frameworks, and monitoring in production.

Intermediate

LangChain ReAct Agent from Scratch

LangChain ReAct Agent from Scratch What You'll Build Building a ReAct agent with tools using LangChain. By the end of this tutorial, you'll have a fully working implementation you can extend for production use. **Time**: ~25 minutes **Difficulty

Advanced

LangChain vs LangGraph 2026 Deep Dive: When to Use Which Framework?

LangChain vs LangGraph comparison (2026): Chains handle linear flows, Graphs handle stateful Agents (loops/approval/persistence)—one rule of thumb: does the runtime need to change paths based on results? Includes decision table, combined usage (graph orchestration + chain for single steps), and AgentExecutor migration path.

Advanced

LangChain vs LangGraph Practical Guide: How to Choose Your Agent Framework, Explained Clearly

LangChain and LangGraph come from the same lineage, but their positioning is now completely different. This article compares them through actual code, explaining their core differences, respective strengths, and the recommended tech stack for building production-grade AI Agents in 2026.

Intermediate

LangChain vs LlamaIndex: Which Framework to Choose in 2025?

Comprehensive comparison of LangChain and LlamaIndex for building LLM applications. Compare architecture, use cases, performance, and ecosystem to make the right choice for your project.

Intermediate

LangChain vs LlamaIndex 2026: Which Framework Should You Use for RAG?

Detailed comparison of LangChain and LlamaIndex for building retrieval-augmented generation applications in 2026. Covers architecture differences, performance benchmarks, integration ecosystems, and specific use cases where each framework excels.

Intermediate

LangChain vs LlamaIndex: Side-by-Side Comparison

LangChain vs LlamaIndex Quick Decision Guide (2026): Choose LlamaIndex (data framework) for pure RAG Q&A, LangChain+LangGraph (orchestration framework) for agent/orchestration-heavy tasks; they are composable; avoid both for simple apps. Includes decision table and practical experience.

Advanced

LangChain vs LlamaIndex vs Haystack: RAG Framework 2026

Detailed comparison of LangChain, LlamaIndex, and Haystack for building RAG pipelines. Covers document processing, retrieval strategies, performance benchmarks, and production deployment for 2026.

Beginner

LangChain vs LlamaIndex: Which is Better for RAG applications? (2026)

LangChain vs LlamaIndex for RAG (2026): LlamaIndex is data-first, specialized in retrieval quality, ideal for pure document RAG; LangChain is a general orchestration framework, better when RAG is part of a larger agent application. They can be combined.

Advanced

LangGraph State Machine Agent 2026: Building Controllable Complex AI Workflows

LangGraph state machine agent practical guide (2026): Walk through the core API with an 'expense approval agent with human review'—TypedDict state, conditional edges for branching, interrupt for cross-day pause and approval, checkpointer for resumption via thread_id. Includes production checklist (PostgresSaver, validation, tracing).

Intermediate

LangGraph for Stateful Agents: Tutorial and Best Practices

LangGraph for Stateful Agents What is LangGraph? LangGraph is a framework for stateful agent graphs with cycles. It simplifies building AI applications by providing high-level abstractions over raw LLM APIs. **Best for**: agent orchestration Inst

Advanced

LangGraph Tutorial: Build Stateful AI Agents with Persistent Memory

LangGraph enables AI agents with persistent state, conditional branching, and human-in-the-loop workflows. This tutorial builds a real research agent from scratch with memory, tool use, and error recovery.

Advanced

LangGraph Complete Guide 2026: Build Stateful AI Agents

LangGraph Complete Guide (2026): Build agents as state machines—State+reducer, conditional edges, checkpointer persistence (multi-turn memory/crash recovery/time travel), interrupt for human approval gates, multi-agent supervisor pattern. Includes an honest comparison of when to use it and when not to.

Beginner

LangSmith Complete Tutorial 2026: How to debug, test, and monitor LLM applications

LangSmith Complete Tutorial 2026 What is LangSmith? **LangSmith** is a powerful LLM observability that enables you to debug, test, and monitor LLM applications. It has become one of the most popular tools in the AI developer toolkit in 2026. Why U

Intermediate

LangSmith for LLM Evaluation: Building Systematic Feedback Loops

LangSmith LLM Evaluation Workflow (2026): Trace → Dataset → Evaluator (including LLM-as-judge) → Experiment — the four-piece suite that turns "feels better" into measurable progress. Includes @traceable code, weekly evaluation loops, bias calibration for LLM judges, and comparison vs Langfuse.

Intermediate

LangSmith Tracing: Developer Guide and Quick Start 2026

LangSmith Tracing: Developer Guide 2026 What is LangSmith Tracing? **LangSmith Tracing** enables debug and trace LangChain applications. This guide covers everything you need to get started quickly. Why Use LangSmith Tracing? - Solves the specifi

Intermediate

LangSmith vs Helicone vs Langfuse: Side-by-Side Comparison

LangSmith vs Helicone vs Langfuse Comparison (2026): Helicone is a proxy (change base URL to integrate + caching/rate limiting), Langfuse is an open-source self-hostable tracing + evaluation platform, LangSmith offers zero-config deep tracing within the LangChain ecosystem. Includes decision rules and combined usage.

Intermediate

LangSmith vs Langfuse: Choosing LLM Observability Tools (2026)

LangSmith and Langfuse both provide tracing, evaluation, and monitoring for LLM applications. This article clarifies the most practical differences: open-source vs closed-source, self-hosting capability, pricing, and framework lock-in, helping you decide based on your team's needs.

Beginner

LangSmith vs Langfuse: Which is Better for LLM observability? (2026)

LangSmith vs Langfuse LLM Observability Comparison (2026): Langfuse is open-source, self-hostable, framework-agnostic, with generous free tier; LangSmith is LangChain's official hosted platform with deepest ecosystem integration and strong evaluation tools. Includes selection advice and auto-tracing code.

Intermediate

LlamaIndex Data Ingestion: Tutorial and Best Practices

LlamaIndex Data Ingestion What is LlamaIndex? LlamaIndex is a framework for document pipelines and query engines. It simplifies building AI applications by providing high-level abstractions over raw LLM APIs. **Best for**: RAG Installation ```ba

Intermediate

LlamaIndex Practical Guide: RAG Application Development from Beginner to Production

LlamaIndex is purpose-built for RAG applications, making it the go-to framework for building enterprise knowledge base Q&A systems. This article covers the core architecture, key differences from LangChain, and 5 complete code examples from document loading to production deployment.

Advanced

LlamaIndex Tutorial 2026: Build Production RAG Applications

Complete LlamaIndex tutorial 2026. Covers VectorStoreIndex, persistent Qdrant storage, chat engines, sub-question decomposition, semantic chunking, metadata filtering, and streaming.

Intermediate

LlamaIndex vs LangChain: Which One to Use for Building RAG (2026 Hands-On Comparison)

Everyone says LlamaIndex focuses on retrieval and LangChain leans toward orchestration, but when it comes to actual projects, you still get stuck. This article breaks it down by 'what you want to do,' with real code and pitfalls, helping you make a decision in 10 minutes.

Advanced

Memory-Augmented AI Agent: Complete Tutorial

Memory-Augmented AI Agent Overview Implementing short and long-term memory for AI agents. This guide covers architecture, implementation, and production deployment of AI agents. Agent Architecture ``` User Input ↓ Agent Orchestrator ↓ ┌──

Advanced

Multi-Tool Agent Pipeline: Complete Tutorial

Multi-Tool Agent Pipeline Overview Chaining multiple tools in a sequential agent workflow. This guide covers architecture, implementation, and production deployment of AI agents. Agent Architecture ``` User Input ↓ Agent Orchestrator ↓ ┌─

Advanced

Multi-Vector RAG: Implementation Guide with Weaviate 2026

Multi-Vector RAG: Complete Implementation 2026 Overview Multi-Vector RAG is a specialized retrieval pattern that focuses on storing multiple embedding types per document. This guide shows you how to build a production-ready system using Weaviate.

Intermediate

n8n + LangChain: How to Build AI workflows in n8n (2026)

n8n + LangChain Integration Guide 2026 Overview This guide shows you exactly how to build AI workflows in n8n using n8n and LangChain. We cover setup, core integration, and production-ready patterns. Prerequisites - n8n environment set up - LangC

Intermediate

Node.js + LangChain.js: How to Build Node.js AI applications (2026)

Node.js + LangChain.js Integration Guide 2026 Overview This guide shows you exactly how to build Node.js AI applications using Node.js and LangChain.js. We cover setup, core integration, and production-ready patterns. Prerequisites - Node.js envi

Beginner

OpenAI Assistants vs LangGraph: Which is Better for building AI agents? (2026)

OpenAI Assistants vs LangGraph for building AI Agents (2026): Assistants is managed and worry-free (threads/tools/retrieval) but locks you into OpenAI; LangGraph is open-source, model-agnostic, and builds agents as state graphs with controllable branching/loops/human-in-the-loop.

Advanced

Parent Document RAG: Implementation Guide with Chroma 2026

Parent Document RAG: Complete Implementation 2026 Overview Parent Document RAG is a specialized retrieval pattern that focuses on retrieving small chunks with large parent context. This guide shows you how to build a production-ready system using C

Advanced

Planning and Execution Agent: Complete Tutorial

Planning and Execution Agent Overview Agent with high-level planning and step-by-step execution. This guide covers architecture, implementation, and production deployment of AI agents. Agent Architecture ``` User Input ↓ Agent Orchestrator

Advanced

Python AI Development Stack 2026: FastAPI + LangChain + Supabase

Complete guide to building production AI applications with FastAPI, LangChain, and Supabase in 2026. Covers project setup, async AI endpoints, RAG pipeline, vector search, and deployment.

Intermediate

Build a Production RAG Application with LlamaIndex and Qdrant

Complete guide to building a production RAG application using LlamaIndex for orchestration, Qdrant for vector storage, and comprehensive evaluation with LlamaIndex evaluation modules.

Advanced

RAG Knowledge Base Pitfall Guide: Full Analysis of Chunking Strategies, Embedding Models, and Retrieval Tuning

Deep dive into common failure modes of RAG systems and their fixes. Covers document preprocessing, chunking strategy selection, embedding model evaluation, hybrid retrieval tuning, and Reranker configuration—helping you boost RAG answer accuracy from 60% to over 90%.

Advanced

Build a Production RAG System with LlamaIndex and Pinecone

Most RAG tutorials only show the happy path. This guide builds a production-ready RAG system covering chunking strategies, embedding selection, reranking, evaluation, and edge case handling.

Advanced

RAPTOR RAG: Implementation Guide with Pinecone 2026

RAPTOR RAG: Complete Implementation 2026 Overview RAPTOR RAG is a specialized retrieval pattern that focuses on hierarchical document summarization for better context. This guide shows you how to build a production-ready system using Pinecone. Why

Advanced

Research Agent with Citations: Complete Tutorial

Research Agent with Citations Overview Autonomous research agent that cites sources accurately. This guide covers architecture, implementation, and production deployment of AI agents. Agent Architecture ``` User Input ↓ Agent Orchestrator

Advanced

Self-Healing Agent: Complete Tutorial

Self-Healing Agent Overview Agent that detects and recovers from its own errors. This guide covers architecture, implementation, and production deployment of AI agents. Agent Architecture ``` User Input ↓ Agent Orchestrator ↓ ┌───────────

Advanced

Self-Query RAG: Implementation Guide with Qdrant 2026

Self-Query RAG: Complete Implementation 2026 Overview Self-Query RAG is a specialized retrieval pattern that focuses on AI-generated metadata filters for precise retrieval. This guide shows you how to build a production-ready system using Qdrant.

Advanced

Time-Aware RAG: Implementation Guide with Pinecone 2026

Time-Aware RAG: Complete Implementation 2026 Overview Time-Aware RAG is a specialized retrieval pattern that focuses on weighting recent documents higher in retrieval. This guide shows you how to build a production-ready system using Pinecone. Why

Intermediate

Vercel AI SDK vs LangChain: Which One Should You Use for Frontend AI Apps (2026)

Vercel AI SDK is nearly unbeatable for streaming chat UIs in Next.js, while LangChain excels at complex AI logic orchestration. This article clarifies their true roles and how to combine them, so you don't pick the wrong direction.

Beginner

Vercel AI SDK vs LangChain.js: Which is Better for Next.js AI apps? (2026)

Vercel AI SDK vs LangChain.js for Next.js AI apps deep comparison (2026): AI SDK focuses on UI/streaming (useChat, generateObject + Zod), LangChain.js on orchestration (chains/agents/RAG). Includes real TS code, selection advice, and combined usage: 'AI SDK for UI, LangChain for retrieval.'