Skip to content
Home
AI & LLMs

AI & LLMs

Learning Path — 18 articles

1 AI and LLMs: Complete Guide to Large Language Models Understand how large language models work — transformer architecture, training, tokenization, context windows, and … Start Here 2 Prompt Engineering: Best Practices for LLM Output Master prompt engineering — system prompts, few-shot learning, chain-of-thought, structured outputs, iterative … Start Here 3 OpenAI API: Complete Developer's Guide Master the OpenAI API — chat completions, streaming, function calling, structured outputs, embeddings, token management, … Start Here 4 Running Local LLMs with Ollama: Complete Guide Run LLMs locally with Ollama — installation, model management, REST API, Python integration, custom Modelfiles, and … 5 RAG: Retrieval-Augmented Generation Complete Guide Build RAG systems — chunking strategies, embedding models, vector databases, retrieval pipelines, hybrid search, … 6 LangChain: Building Production LLM Applications Build LLM applications with LangChain — chains, agents, RAG integration, memory systems, and best practices. Covers … 7 Fine-Tuning LLMs: LoRA, QLoRA, and Practical Guide Fine-tune LLMs for your domain — LoRA, QLoRA, dataset preparation, Axolotl training, and deployment. Reduce memory … 8 Vector Databases: Complete Guide for AI Applications Master vector databases for AI — HNSW, IVF, DiskANN indexing, Chroma vs Pinecone vs Qdrant vs pgvector, hybrid search, … 9 LLM Safety: Guardrails and Responsible AI Guide Secure LLM applications against prompt injection, data leakage, and harmful outputs. Covers input/output filtering, red … 10 AI Chatbots: Building Conversational Applications with LLMs Design and deploy production AI chatbots — conversation management, token optimization, streaming, memory systems, tool … 11 AI Agents: Architecture, Tools, and Implementation Learn to build AI agents — ReAct pattern, tool use, memory systems, multi-agent orchestration, and production … 12 Embeddings and Semantic Search: Complete Guide Master text embeddings and semantic search — generation methods, similarity metrics, hybrid search, and building … 13 LLM Evaluation: Benchmarks, Metrics, and Best Practices Systematically evaluate LLMs — MMLU, HumanEval, GSM8K benchmarks, LLM-as-judge, hallucination detection, and production … 14 LLM Application Architecture: Production Design Patterns Design production-grade LLM systems — caching, semantic caching, fallback chains, rate limiting, circuit breakers, … 15 LLM Model Comparison: Choosing the Right Model Compare GPT-4o, Claude 3.5, Llama 3, Gemini, and Mistral — performance, pricing, context windows, and task suitability. … 16 Hugging Face Transformers: Complete Library Guide Master Hugging Face Transformers — pipeline API, model loading, tokenization, fine-tuning with Trainer, quantization, … Advanced 17 Ethical Implications of AI: Bias, Privacy, and Safety Explore the critical ethical challenges of AI — algorithmic bias, privacy, job displacement, accountability, and … Advanced 18 Advanced Prompting: Expert Techniques for LLMs Master advanced LLM prompting techniques — chain-of-thought, tree-of-thought, self-consistency, structured outputs, and … Advanced