教程中心
AI Agent 从入门到实战：概念理解、MCP 使用、平台实操、工作流自动化
1252
教程总数
234
入门教程
42
实操教程
按主题浏览
AI Model Quantization (GPTQ, AWQ): Complete Developer Guide 2026
Master AI Model Quantization (GPTQ, AWQ) with practical examples and production patterns
AI 模型量化（GPTQ/AWQ）完全指南（2026）：用更少比特存权重以省显存/提速。GPTQ vs AWQ 对比、bitsandbytes/GGUF、4bit 甜点位选择，以及"直接下预量化权重 + vLLM/Ollama 部署"的实战路径。
LLM Fine-tuning with LoRA: Complete Developer Guide 2026
Master LLM Fine-tuning with LoRA with practical examples and production patterns
LoRA 微调大模型完全指南（2026）：冻结基座、只训低秩适配器，单卡数小时完成；QLoRA 在 4bit 基座上训练适配器。含 PEFT 真实代码、何时该微调(vs 提示/RAG)、数据质量 > 数量的实战要点。
Streaming AI Responses with Server-Sent Events: Complete Developer Guide 2026
Master Streaming AI Responses with Server-Sent Events with practical examples and production patterns
用 SSE 实现 AI 流式响应（2026）：为什么用 SSE 而非 WebSocket、FastAPI 服务端 + 浏览器 EventSource 客户端真实代码、关闭代理缓冲/逐 token flush/断连取消等生产要点，以及 Next.js 用 Vercel AI SDK 的更简路径。
Semantic Search Implementation: Complete Developer Guide 2026
Master Semantic Search Implementation with practical examples and production patterns
语义搜索实现完全指南（2026）：分块→嵌入→向量库存储→近邻检索→重排的完整管线，含真实代码、向量库选型(Chroma/Qdrant/pgvector/Pinecone)、分块/混合检索/重排/元数据过滤等质量杠杆。RAG 的检索底座。
OpenAI Function Calling Complete Guide: Complete Developer Guide 2026
Master OpenAI Function Calling Complete Guide with practical examples and production patterns
OpenAI Function/Tool Calling 完全指南（2026）：用 JSON Schema 定义工具→模型返回结构化调用→你执行并回填结果的完整循环，含真实代码、生产模式(校验/tool_choice/并行调用/strict)、与结构化输出的区别，以及它如何支撑 Agent。
Corrective RAG: Implementation Guide with Weaviate 2026
Build a self-correcting retrieval with quality assessment RAG system from scratch
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.
Multi-Vector RAG: Implementation Guide with Weaviate 2026
Build a storing multiple embedding types per document RAG system from scratch
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.
RAPTOR RAG: Implementation Guide with Pinecone 2026
Build a hierarchical document summarization for better context RAG system from scratch
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
Hybrid Search RAG: Implementation Guide with Elasticsearch 2026
Build a combining vector and keyword search for maximum recall RAG system from scratch
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
Contextual Compression RAG: Implementation Guide with Pinecone 2026
Build a compressing retrieved context to fit LLM window RAG system from scratch
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
Self-Query RAG: Implementation Guide with Qdrant 2026
Build a AI-generated metadata filters for precise retrieval RAG system from scratch
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.
Graph RAG: Implementation Guide with Neo4j 2026
Build a knowledge graph traversal for multi-hop reasoning RAG system from scratch
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
Parent Document RAG: Implementation Guide with Chroma 2026
Build a retrieving small chunks with large parent context RAG system from scratch
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
Time-Aware RAG: Implementation Guide with Pinecone 2026
Build a weighting recent documents higher in retrieval RAG system from scratch
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
Cross-Encoder RAG: Implementation Guide with Qdrant 2026
Build a neural reranking for high-precision retrieval RAG system from scratch
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.