AI 开发 教程
系统化的 AI 开发学习路径。从提示词工程到模型微调，从 RAG 到 Agent 开发，覆盖 AI 应用开发全栈知识。共 142 篇教程，18 个分类，入门到高级全覆盖。
找到 46 篇教程
DeepSeek Inference Acceleration In-Depth Tutorial
Comprehensively master DeepSeek model inference acceleration techniques. In-depth comparison of four major engines: vLLM, SGLang, TensorRT-LLM, and llama.cpp, from deployment to tuning, from single GPU to distributed, providing a complete inference acceleration solution.
阅读教程 →DeepSeek Data Engineering Tutorial
From data collection to quality evaluation, fully master the large model data engineering pipeline. Covers core aspects such as SFT dataset construction, RLHF preference data preparation, data cleaning and deduplication, data augmentation, and large-scale data processing.
阅读教程 →DeepSeek Safety and Content Moderation
Production environment security protection guide: from prompt injection defense to content moderation systems, from jailbreak detection to red team testing. Complete security architecture design and Python implementation code to ensure AI applications are safe and reliable.
阅读教程 →DeepSeek Model Architecture Deep Dive
In-depth analysis of DeepSeek-V3's core technologies such as MoE architecture, MLA attention mechanism, and Multi-Token Prediction. Understand how DeepSeek achieves GPT-4o-level performance at extremely low cost, including architecture diagrams and source code analysis.
阅读教程 →DeepSeek Fine-tuning Hands-on Tutorial
Full practical guide to fine-tuning DeepSeek models: LoRA/QLoRA efficient fine-tuning, full-parameter fine-tuning, data preparation, training configuration, and evaluation validation. Covers fine-tuning solutions for DeepSeek-V3 and DeepSeek-R1, including complete code and best practices.
阅读教程 →DeepSeek Enterprise Application Tutorial
DeepSeek enterprise-level application architecture design: multi-tenant isolation, permission management, audit logs, API gateway, and cost control. Includes practical solutions for enterprise RAG systems, intelligent customer service, and knowledge base management, providing an AI implementation guide for large organizations.
阅读教程 →DeepSeek Performance Tuning Tutorial
Complete DeepSeek performance tuning guide: GPU memory optimization, batching strategies, quantization techniques, concurrency control, and latency optimization. Includes profiling tool usage, performance benchmarking, and best practices to achieve an optimal balance between throughput and latency.
阅读教程 →DeepSeek-V4.1-Flash: CED Asymmetric Architecture & KV Cache Compression
DeepSeek-V4.1-Flash redefines Agent-era inference with a 552B MoE and CED asymmetric architecture. We break down KV Cache compression and its cost model.
阅读教程 →Build Long-Context Multimodal Agents with DeepSeek-V4.1-Flash
Use DeepSeek-V4.1-Flash's 1M context and 384K output to build a multimodal Agent with vision, tool calls, and long-context memory, plus cost and pitfalls.
阅读教程 →DeepSeek-V4.1-Flash Local Deployment & Inference Optimization
Deploy DeepSeek-V4.1-Flash locally: CED architecture, KV Cache 4x compression, quantization, batching, and high-concurrency serving for max throughput.
阅读教程 →Dialogue Prefix Continuation: Let AI Perfectly Complete Your Half-Sentence
DeepSeek V4's Chat Prefix Completion (Beta) feature allows the model to continue generating from a specified prefix. This article details use cases, API calls, comparison with FIM, and practical application examples.
阅读教程 →Multi-Agent Collaboration Patterns in Practice: From Orchestration to Autonomy
Single agents have limited capabilities; multi-agent collaboration is key to unlocking complex tasks. This article starts from practical experience, compares mainstream collaboration modes such as Supervisor, GroupChat, and Sequential, and provides runnable code implementations.
阅读教程 →Model Distillation in Practice: Training Small Models with Large Models
Knowledge distillation allows small models to approach large model capabilities while significantly reducing inference costs. This article provides an in-depth explanation of distillation principles, data generation strategies, training techniques, and effect evaluation, teaching you to distill cost-effective small models with DeepSeek.
阅读教程 →LLM Inference Performance Optimization: vLLM and Continuous Batching
After model deployment, throughput and latency are core metrics. This article provides an in-depth analysis of vLLM's PagedAttention and Continuous Batching principles, and gives a complete optimization roadmap from benchmark testing, parameter tuning to production deployment.
阅读教程 →AI Agent Red Teaming and Security Assessment Framework
Agents that can call tools are at risk of being exploited. This article systematically explains Agent red team testing methodologies, covering attack surfaces such as prompt injection, unauthorized tool calls, supply chain pollution, as well as supporting automated evaluation and defense systems.
阅读教程 →Multimodal Agent in Practice: Vision-Driven Automated Operations
When agents can 'see' screens and images, the boundaries of automation are greatly expanded. This article explains the architecture design of multimodal agents, screenshot understanding, UI element positioning, and complete implementation of action execution, with runnable code.
阅读教程 →RLHF Reinforcement Fine-Tuning in Practice: From Preference Data to Reward Model
RLHF aligns model outputs with human preferences. This article walks through the complete RLHF pipeline, from preference data collection and reward model training to PPO reinforcement fine-tuning, and provides engineering insights on data quality and effect evaluation.
阅读教程 →Agent State Machine and Fault-Tolerant Orchestration: Building Reliable Agents
In real business, agents fail: tool timeouts, context overflow, loop deadlocks. This article models the agent lifecycle with a finite state machine and explains the complete implementation of fault-tolerant orchestration, including timeout circuit breaking, retry compensation, and session recovery.
阅读教程 →DeepSeek-R1 Reasoning Model: Principles & CoT Engineering
Explore DeepSeek-R1's RL-based training for long chain-of-thought reasoning. Learn CoT prompting, output constraints, temperature tuning, cost control, and evaluation for production.
阅读教程 →Designing Large-Scale Vector Search: From HNSW to Distributed Indexing
Learn to build a scalable vector search foundation for tens of millions of vectors with millisecond recall. Covers HNSW graph indexing, IVF-PQ quantization, memory/SSD tiering, sharding, replication, cascaded retrieval, caching, architecture comparisons, and load testing.
阅读教程 →Agent Memory System Design: Short-Term, Long-Term, and Tool Memory
Memory is the foundation of Agent intelligence. This article models four layers: working, episodic, semantic, and tool memory, covering compression, retrieval, writing, and forgetting strategies. Implement a complete Agent memory subsystem with vector memory and reflection using DeepSeek API.
阅读教程 →Multi-Agent Collaboration: Building an AI Team with Skill Chains
A single AI has limited capabilities, but collaboration among multiple AI roles can solve complex problems. This article explains how to orchestrate multiple Agents with skill chains, building a collaborative team of planner → executor → reviewer.
阅读教程 →Hands-on: Build Your First Agent Loop Application
From theory to practice, this article teaches you step by step how to build a complete Agent Loop application using the DeepSeek API. It includes the complete process of requirements analysis, task planning, step-by-step execution, and result verification.
阅读教程 →Chain-of-Thought Deep Dive
Chain-of-Thought (CoT) is not just about adding 'Let's think step by step'. This article deeply analyzes the working mechanism, variant strategies, and cutting-edge progress of CoT from three dimensions: cognitive science, information theory, and engineering practice, helping you truly understand the essence of AI reasoning.
阅读教程 →Prompt Security and Injection Defense
Prompt injection is the primary security threat to AI applications. Attackers can bypass system instructions, steal sensitive information, and induce malicious behavior through carefully crafted inputs. This article explains in depth the attack vectors, detection methods, and defense strategies of prompt injection to help you build secure AI applications.
阅读教程 →RAG Evaluation and Quality Metrics System
Without measurement, there is no improvement. Quality evaluation of RAG systems involves three levels: retrieval quality, generation quality, and end-to-end quality. This article systematically explains core evaluation metrics and frameworks such as Recall@k, MRR, Faithfulness, and RAGAS to help you establish a scientific RAG quality measurement system.
阅读教程 →Agentic RAG: Let AI Retrieve Autonomously
Traditional RAG is passive—the system retrieves what the user asks. Agentic RAG gives AI autonomous decision-making ability, enabling it to proactively determine whether retrieval is needed, what to retrieve, and how to integrate multiple retrieval results. This article deeply analyzes the architecture design and implementation path of Agentic RAG.
阅读教程 →AI-Driven Data Analysis Pipeline
Traditional data analysis relies on extensive manual coding, while AI-driven data analysis pipelines make natural language the interface for data queries. This article builds a complete data analysis pipeline with NL2SQL + automatic visualization + insight generation, allowing anyone to explore data using natural language.
阅读教程 →Monitoring and Observability for AI Applications
Observability for AI applications is far more complex than for traditional applications—it requires monitoring multiple dimensions such as LLM call latency, token consumption, hallucination rate, and user satisfaction. This article builds a complete AI application monitoring system, covering metric collection, alert configuration, cost tracking, and quality monitoring.
阅读教程 →Model Evaluation and A/B Testing
After fine-tuning, how can you objectively evaluate model performance? How should A/B tests be designed to obtain statistically significant conclusions? This article establishes a scientific model evaluation system from three dimensions: offline evaluation, online A/B testing, and statistical significance.
阅读教程 →Design of Agent Memory Systems
Memory is the key to transforming agents from one-time tools to long-term intelligent companions. This article deeply analyzes the architecture design of agent memory systems, covering short-term/long-term memory, RAG-enhanced memory, and hybrid retrieval strategies.
阅读教程 →In-Depth Implementation of ReAct Agents
ReAct (Reasoning + Acting) is one of the most classic paradigms in agent development. This article explains in depth how to build a production-grade ReAct agent, from principles to implementation, including prompt engineering, tool management, and error recovery.
阅读教程 →Design of Multi-Agent Communication Protocols
When multiple AI agents need to collaborate, communication protocols are the key link connecting them. This article explores the design principles, message formats, routing strategies, and consistency guarantees of multi-agent communication protocols.
阅读教程 →Detailed Explanation of DPO Preference Alignment Training
DPO (Direct Preference Optimization) is a simplified alternative to RLHF that does not require training a reward model. This article explains the principles, implementation details, and training techniques of DPO in depth.
阅读教程 →Graph-Enhanced RAG (GraphRAG) in Practice
Traditional RAG only retrieves text fragments; GraphRAG introduces knowledge graphs on this basis, enabling multi-hop reasoning and relation-aware retrieval. This article explains the construction and practical application of GraphRAG from scratch.
阅读教程 →GPU Cluster Management and Scheduling
Managing a cluster of dozens of GPUs requires professional scheduling strategies. This article explains practical experience in GPU resource management, task priority scheduling, memory fragmentation cleanup, and multi-tenant isolation.
阅读教程 →Enterprise AI Middleware Architecture Design
When an enterprise needs to manage dozens of AI services in a unified manner, the middleware layer is crucial. This article explains the complete architecture design of AI gateways, rate limiting, load balancing, model routing, and monitoring.
阅读教程 →Large Model Safety and Alignment Techniques
AI safety is the baseline requirement for production deployment. This article provides an in-depth explanation of alignment techniques such as RLHF, DPO, and Constitutional AI, as well as security practices like content moderation and prompt injection defense, to help you build safe and reliable AI applications.
阅读教程 →In-Depth Guide to GPU-Accelerated Inference Optimization
GPU inference optimization is key to reducing the cost of large model deployment. This article provides an in-depth explanation of core technologies such as FlashAttention, quantized inference, TensorRT acceleration, and continuous batching to help you maximize GPU utilization.
阅读教程 →Prompt Injection Defense and Security Hardening
Prompt injection is the number one security threat facing large model applications. This article provides an in-depth analysis of various injection attack principles and offers systematic defense strategies, including input filtering, output validation, sandbox isolation, and permission control.
阅读教程 →Advanced RAG: Multi-hop Retrieval and Self-Query
Basic RAG cannot handle complex problems that require cross-document reasoning. This article provides an in-depth explanation of advanced RAG techniques such as multi-hop retrieval, self-query retrieval, and context compression, helping you elevate your RAG system to production-grade level.
阅读教程 →Multi-Agent Collaboration: Building an AI Team
A single Agent has limited capabilities; multi-Agent collaboration can solve more complex problems. This article explains the design patterns, communication mechanisms, and practical application cases of multi-Agent systems, teaching you to build AI teams that can work collaboratively.
阅读教程 →Dataset Construction and Quality Evaluation
Data quality determines the upper limit of fine-tuning effectiveness. This article systematically explains the construction methods of fine-tuning datasets, data cleaning strategies, quality evaluation metrics, and data augmentation techniques, helping you build high-quality fine-tuning datasets.
阅读教程 →Best Practices for Large Model API Service
API-fying LLM capabilities is a key step for enterprise-level applications. This article systematically explains best practices for LLM API services from dimensions such as architecture design, rate limiting strategies, cache optimization, and security protection.
阅读教程 →AI Application Performance Optimization and Cost Control
The performance and cost of AI applications directly impact product experience and commercial viability. This article systematically explains methods for AI application performance optimization and cost control from dimensions such as prompt optimization, caching strategies, model selection, and architecture design.
阅读教程 →Structured Output and JSON Mode in Practice
In production environments, unstructured output from AI is difficult to use directly. This article provides an in-depth explanation of how to make large models output structured data, including JSON Schema constraints, Pydantic integration, and best practices for structured output.
阅读教程 →