کتاب مهندسی هوش مصنوعی

مقدمه‌ای بر ساخت برنامه‌های هوش مصنوعی با مدل‌های بنیادی

The Rise of AI Engineering • From Language Models to Large Language Models • From Large Language Models to Foundation Models • From Foundation Models to AI Engineering • Foundation Model Use Cases • Coding • Image and Video Production • Writing • Education • Conversational Bots • Information Aggregation • Data Organization • Workflow Automation • Planning AI Applications • Use Case Evaluation • Setting Expectations • Milestone Planning • Maintenance • The AI Engineering Stack • Three Layers of the AI Stack • AI Engineering Versus ML Engineering • AI Engineering Versus Full-Stack Engineering • Summary

درک مدل‌های بنیادی

Training Data • Multilingual Models • Domain-Specific Models • Modeling • Model Architecture • Model Size • Post-Training • Supervised Finetuning • Preference Finetuning • Sampling • Sampling Fundamentals • Sampling Strategies • Test Time Compute • Structured Outputs • The Probabilistic Nature of AI • Summary

روش‌شناسی ارزیابی

Challenges of Evaluating Foundation Models • Understanding Language Modeling Metrics • Entropy • Cross Entropy • Bits-per-Character and Bits-per-Byte • Perplexity • Perplexity Interpretation and Use Cases • Exact Evaluation • Functional Correctness • Similarity Measurements Against Reference Data • Introduction to Embedding • AI as a Judge • Why AI as a Judge? • How to Use AI as a Judge • Limitations of AI as a Judge • What Models Can Act as Judges? • Ranking Models with Comparative Evaluation • Challenges of Comparative Evaluation • The Future of Comparative Evaluation • Summary

ارزیابی سیستم‌های هوش مصنوعی

Evaluation Criteria • Domain-Specific Capability • Generation Capability • Instruction-Following Capability • Cost and Latency • Model Selection • Model Selection Workflow • Model Build Versus Buy • Navigate Public Benchmarks • Design Your Evaluation Pipeline • Step 1. Evaluate All Components in a System • Step 2. Create an Evaluation Guideline • Step 3. Define Evaluation Methods and Data • Summary

مهندسی پرامپت

Introduction to Prompting • In-Context Learning: Zero-Shot and Few-Shot • System Prompt and User Prompt • Context Length and Context Efficiency • Prompt Engineering Best Practices • Write Clear and Explicit Instructions • Provide Sufficient Context • Break Complex Tasks into Simpler Subtasks • Give the Model Time to Think • Iterate on Your Prompts • Evaluate Prompt Engineering Tools • Organize and Version Prompts • Defensive Prompt Engineering • Proprietary Prompts and Reverse Prompt Engineering • Jailbreaking and Prompt Injection • Information Extraction • Defenses Against Prompt Attacks • Summary

RAG و عامل‌ها

RAG • RAG Architecture • Retrieval Algorithms • Retrieval Optimization • RAG Beyond Texts • Agents • Agent Overview • Tools • Planning • Agent Failure Modes and Evaluation • Memory • Summary

تنظیم دقیق

Finetuning Overview • When to Finetune • Reasons to Finetune • Reasons Not to Finetune • Finetuning and RAG • Memory Bottlenecks • Backpropagation and Trainable Parameters • Memory Math • Numerical Representations • Quantization • Finetuning Techniques • Parameter-Efficient Finetuning • Model Merging and Multi-Task Finetuning • Finetuning Tactics • Summary

مهندسی مجموعه‌داده

Data Curation • Data Quality • Data Coverage • Data Quantity • Data Acquisition and Annotation • Data Augmentation and Synthesis • Why Data Synthesis • Traditional Data Synthesis Techniques • AI-Powered Data Synthesis • Model Distillation • Data Processing • Inspect Data • Deduplicate Data • Clean and Filter Data • Format Data • Summary

بهینه‌سازی استنتاج

Understanding Inference Optimization • Inference Overview • Inference Performance Metrics • AI Accelerators • Inference Optimization • Model Optimization • Inference Service Optimization • Summary

معماری مهندسی هوش مصنوعی و بازخورد کاربر

AI Engineering Architecture • Step 1. Enhance Context • Step 2. Put in Guardrails • Step 3. Add Model Router and Gateway • Step 4. Reduce Latency with Caches • Step 5. Add Agent Patterns • Monitoring and Observability • AI Pipeline Orchestration • User Feedback • Extracting Conversational Feedback • Feedback Design • Feedback Limitations • Summary