1 Agent
1.1 Intro
1.2 Basic
1.3 Output Parser
1.4 Model
1.5 Memory
2 RAG
2.1 Preprocess
2.1.1 Document Loader
2.1.2 Text Splitter
2.1.3 Embeddings
2.1.4 Vector Store
2.2 Runtime Process
2.2.1 Retriever
2.2.2 Reranker
2.3 Prompt Engineering
2.3.1 프롬프트 설계 기초
2.3.2 LangChain 프롬프트 도구
2.3.3 프롬프트 분석 (Prompt Analytics)
- 10-PromptAnalytics
- 11-PromptWritingMethod
- 12-PromptAnalytics-conversation-analysis1
- 13-PromptAnalytics-conversation-analysis2
- 14-PromptAnalytics-segmentation
- 15-1-PromptAnalytics-segmentation-strategy
- 15-2-PromptAnalytics-user-data-strategy
- 15-3-PromptAnalytics-utterance-data-pipeline
- 16-PromptAnalytics-reasoning
2.3.4 프롬프팅 기법
- 18-PromptWriting-techniques
- 19-PromptWriting-zeroshot
- 20-PromptWriting-fewshot
- 21-PromptWriting-chain-of-thought
- 22-PromptWriting-zeroshot-CoT
- 23-PromptWriting-self-consistency
- 24-PromptWriting-advenced techniques
- 25-PromptWriting-knowledge-generation
- 26-PromptWriting-prompt-chaining
- 27-PromptWriting-tree-of-thoughts
- 28-PromptWriting-active-prompting
- 29-PromptWriting-rag1
- 30-PromptWriting-APE
- 31-PromptWriting-rag2
- 32-PromptWriting-directional-stimulus
- 33-PromptWriting-ReAct
2.3.5 실전 프롬프트 설계
2.3.6 RAG
- 00-RAG-Basic-PDF
- 01-RAG-Basic-Webloader
- 02-RAG-Advanced
- 03-Conversation-With-History
- 04-RAPTOR-Long-Context-RAG-CODE
- 05-RAPTOR-Long-Context-RAG-PDF
- 08-Web-Summarize-Chain-Of-Density
- 10-Multi_modal_RAG-GPT-4o
- 11-RAG-Variants-Comparison
- 12-Custom-RAG-vs-Agent
- 13-RAG-Orchestration-Roadmap
- 14-Long-Context-Limits
- 15-Structured-RAG-Architecture
- 16-RAG-vs-Long-Context-Decision
2.3.7 Cloud RAG (Azure)
- Azure-RAG-Overview
- Project Setting
- Azure-Blob-Storage
- Azure-Document-Intelligence
- Azure-OpenAI-Embeddings
- Azure-AI-Search-Integration
- LangChain-to-LangGraph
- Azure-OpenAI-LLM
- Azure-Functions-Apps
- Azure-Container-Apps
- End-to-End-Azure-RAG
- CodeBaseAnalyzer
- RAG-optimization
관련 참조: Azure 인프라 설정(VM, Blob Storage, AI Search, Document Intelligence)에 대한 상세 내용은 Engineering - Azure Cloud 섹션을 참고한다. Agent 시스템 구축을 위한 DevOps 워크플로는 Engineering - Agent Platform Design 섹션에서 다룬다.
2.3.8 LangChain Expression Language
2.3.9 Chains
3 Agent Process
- Tools
- Bind-Tools
- Agent
- Agent-More-LLMs
- Human-Intervention
- Agentic-RAG
- CSV-Excel-Agent
- Agent-Toolkits-File-Management
- Agent-Report-With-Image-Generation
- Two-Agent-Debate-With-Tools
- React-Agent
- Plan-Execute-Agent
- Multi-Agent-System
- Multi-Agent
- ReAct Agent: LangChain v1 create_agent
- ReAct Agent와 Playwright 브라우저 자동화
3.1 RAG & Agent Evaluation
- Test-Dataset-Generator-RAGAS
- Evaluation-Using-RAGAS
- Translate-HF-Upload
- LangSmith-Dataset
- LangSmith-LLM-as-Judge
- LangSmith-Embedding-Distance-Evaluation
- LangSmith-Custom-LLM-Evaluation
- LangSmith-Heuristic-Evaluation
- LangSmith-Compare-Evaluation
- LangSmith-Summary-Evaluation
- LangSmith-Groundedness-Evaluation
- LangSmith-Pairwise-Evaluation
- LangSmith-Repeat-Evaluation
- LangSmith-Online-Evaluation
- Prompt-Quality-Control
- Prompt-Quality-Control-testRules
- Prompt-Quality-Control-testMethod
- Prompt-Quality-Control-qualititative
- Prompt-Quality-Control-quantitative
- Prompt-Evaluation-Justification
- Prompt-Evaluation-LLMasJudge
- Prompt-Evaluation-template
- LangSmith-CLI-SDK-Automation
- LangSmith-vs-Custom-Evaluation
- LangSmith-Security-Governance
- to-be-organized
관련 참조: Agent 평가에서 활용하는 실험 설계 및 통계적 검정 방법론은 Experimentation 섹션에서 체계적으로 다룬다. A/B 테스트를 통한 Agent 성능 비교 실험 설계는 A/B 테스트의 핵심 메커니즘을 참고한다.
3.2 Personalization
3.3 LangGraph
3.3.1 Core Features
- LangGraph-Overview
- LangGraph-Introduction
- LangGraph-ChatBot
- LangGraph-Agent
- LangGraph-Agent-With-Memory
- LangGraph-Streaming-Outputs
- LangGraph-Human-In-the-Loop
- LangGraph-Manual-State-Update
- LangGraph-State-Customization
- LangGraph-DeleteMessages
- LangGraph-ToolNode
- LangGraph-Branching
- LangGraph-Add-Conversation-Summary
- LangGraph-Subgraph
- LangGraph-Subgraph-Transform-State
- LangGraph-Streaming-Steps
- LangChain-to-LangGraph-Migration
3.3.2 Structures
3.3.3 Use Cases
- LangGraph-Agent-Simulation
- LangGraph-Prompt-Generation
- LangGraph-CRAG
- LangGraph-Self-RAG
- LangGraph-Plan-and-Execute
- LangGraph-Multi-Agent-Collaboration 6-1. LangGraph-Multi-Agent-Collaboration-llama3
- LangGraph-Multi-Agent-Supervisor
- LangGraph-Hierarchial-Agent-Team
- LangGraph-SQL-Agent
- LangGraph-Research-Assistant
3.4 Fine Tuning
3.5 Streamlit Applications
3.6 GraphRAG
3.6.1 Phase 1: 개념
3.6.2 Phase 2: 환경 설정
3.6.3 Phase 3: 핵심 컴포넌트
3.6.4 Phase 4: 실무 통합
3.6.5 Phase 5: 실전 예제
3.6.6 Phase 6: 심화
3.6.7 Phase 7: 응용
3.6.8 Neo4j GraphRAG
3.6.8.1 Phase 1: 개념 & 환경
3.6.8.2 Phase 2: 그래프 구축
3.6.8.3 Phase 3: 검색
3.6.8.4 Phase 4: GDS 그래프 분석
3.6.8.5 Phase 5: Full GraphRAG
3.6.8.6 Phase 6: 평가
3.7 Agent Architecture
3.7.1 Agent 설계 패턴
3.7.2 시스템 프롬프트 설계
3.7.3 스킬 (Skill) 시스템
3.7.4 도구 (Tool) 시스템과 SDK
3.7.5 하네스 엔지니어링 — 개념과 자체 체계
3.7.6 하네스 엔지니어링 — 산업 사례
3.7.7 실전 사례
3.8 Segmentation & Personalization
4 References
- GitHub-https://github.com/langchain-ai/langchain
- Documentation-https://python.langchain.com/
- Academy-https://academy.langchain.com/
- API Reference-https://python.langchain.com/api_reference/
- GitHub-https://github.com/langchain-ai/langgraph
- Documentation-https://langchain-ai.github.io/langgraph/
- LangChain OpenTutorial-https://github.com/LangChain-OpenTutorial/LangChain-OpenTutorial
- Experiments-https://github.com/daveebbelaar/langchain-experiments
- Tutorials-https://github.com/gkamradt/langchain-tutorials
- RAG Overview - Azure AI Search-https://learn.microsoft.com/en-us/azure/search/retrieval-augmented-generation-overview
- Advanced RAG Systems-https://learn.microsoft.com/en-us/azure/developer/ai/advanced-retrieval-augmented-generation
- RAG in Azure AI Foundry-https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/retrieval-augmented-generation
- RAG with Document Intelligence-https://learn.microsoft.com/en-us/azure/ai-services/document-intelligence/concept/retrieval-augmented-generation
- RAG with Machine Learning Prompt Flow-https://learn.microsoft.com/en-us/azure/machine-learning/concept-retrieval-augmented-generation
- RAG on Databricks-https://learn.microsoft.com/en-us/azure/databricks/generative-ai/retrieval-augmented-generation
- RAG Evaluators-https://learn.microsoft.com/en-us/azure/ai-foundry/concepts/evaluation-evaluators/rag-evaluators
- RAG with Content Understanding-https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/tutorial/build-rag-solution
- GPT-RAG Enterprise Solution-https://github.com/Azure/GPT-RAG
- LangChain 한국어 튜토리얼-https://github.com/teddylee777/langchain-kr - Lee, T.
- 테디노트 YouTube-https://www.youtube.com/c/@teddynote - Lee, T.
- 데이터 분석 블로그-https://teddylee777.github.io - Lee, T.
- 테디노트-https://wikidocs.net - Lee, T.