LLM Temperature, Top-P, and Top-K Explained, With Python Simulations
Build temperature, top-p, top-k, and min-p sampling from scratch in Python. Interactive code, probability visuals, and a per-task cheat sheet.
Gen AI
Gen AI tutorials from Machine Learning Plus: hands-on guides with worked examples and code you can read, copy and run. Start with the fundamentals and work through to the applied posts in the Generative AI and NLP track.
2026 76
OpenAI API Python Tutorial, Chat Completions, Streaming & Error Handling
Learn to use the OpenAI API in Python. Master chat completions, streaming responses, error handling, retries, and async calls with runnable examples.
Build a Python AI Chatbot with Memory Using LangChain
Learn to build a Python AI chatbot with conversation memory using LangChain and LangGraph. Master 5 memory strategies, add a Streamlit UI, and...
Zero-Shot vs Few-Shot Prompting: Complete Guide
Build a text classifier that hits 90%+ accuracy using only prompt engineering. Learn zero-shot, one-shot, and few-shot prompting with hands-on Python...
Transformer Attention from Scratch in NumPy (Python)
Build transformer attention from scratch in NumPy with runnable code. Scaled dot-product, multi-head attention, causal masking, and heatmaps step by...
Train a Custom Tokenizer with HuggingFace (Python)
Learn to train custom BPE and WordPiece tokenizers with HuggingFace for medical, legal, and domain-specific NLP. Includes evaluation metrics and code.
tiktoken vs HuggingFace Tokenizers: Benchmark Guide
Benchmark tiktoken vs HuggingFace Tokenizers on speed, vocabulary, and encoding. Runnable Python code, migration guide, and decision framework for...
LLM Structured Output: JSON Mode & Pydantic Guide
Learn LLM structured output in Python with 3 methods: OpenAI JSON schema, Claude tool extraction, and Instructor. Build a type-safe invoice parser...
Mamba & State Space Models: Build a Mini SSM Layer
Build a Mamba SSM layer from scratch in NumPy. Learn selective state spaces, implement selective scan, and benchmark SSM vs attention scaling with...
Speculative Decoding: Faster LLM Inference (Python)
Build a speculative decoding simulator in Python. Learn the draft-verify algorithm, measure acceptance rates, and understand when it speeds up LLM...
RLHF & DPO Explained: Simulate Alignment in Python
Build a reward model, PPO loop, and DPO training from scratch in NumPy. Compare RLHF vs DPO side-by-side with runnable code.
LLM API Retry & Fallback: Build a Resilient Client
Build a resilient LLM client in Python with retry, fallback chains, circuit breakers, and rate limiting, pure Python, runnable code, no SDKs needed.
Prompt Engineering Tutorial for Beginners (2026)
Master prompt engineering basics with Python. Learn the Role-Task-Format framework, zero-shot prompting, and build a testing harness that measures...
Positional Embeddings: RoPE & ALiBi Explained (Python)
Build sinusoidal, RoPE, and ALiBi positional embeddings from scratch in NumPy. Runnable code, heatmaps, and a clear comparison of all three schemes.
OpenAI Function Calling Tutorial in Python (2026)
Learn OpenAI function calling in Python with 3 working tools. Build the tool-use loop, handle parallel calls, and design schemas using raw HTTP...
OpenAI Batch API: Process 10K Prompts at 50% Cost
Master the OpenAI Batch API in Python: build a reusable pipeline for 10,000+ prompts at 50% cost with JSONL formatting, progress polling, and error...
OpenAI Chat Completions API: Complete Python Guide
Master the OpenAI API in Python with raw HTTP requests. Learn chat completions, streaming, parameters, error handling, retries, and cost tracking...
Ollama Tutorial: Run LLMs Locally (Llama, Mistral)
Learn to run LLMs locally with Ollama. Install Llama, Mistral, and DeepSeek, use the OpenAI-compatible Python API, and build a local-to-cloud...
Multimodal AI Tutorial: GPT-4o Vision & Audio API
Learn multimodal AI in Python with GPT-4o, Claude, and Gemini vision APIs. Build image classification, chart analysis, receipt OCR, and audio...
Build a Multi-Provider LLM Toolkit (Python Project)
Build a zero-dep LLM toolkit in Python, unified client for OpenAI, Claude, Gemini, Ollama with cost tracking, retry, streaming, and structured output.
LLM API Router: Groq, Together AI & OpenRouter
Build a multi-provider LLM router in Python with cost-based routing, latency tracking, and automatic fallbacks across Groq, Together AI, and...
Mixture of Experts (MoE): Build a Router in Python
Build a Mixture of Experts (MoE) layer in Python with NumPy. Router, top-k gating, load balancing, and expert networks, with runnable code and...
MHA vs GQA vs MQA: Attention & KV Cache Guide
Build MHA, GQA, and MQA attention from scratch in NumPy. Calculate KV cache VRAM for Llama 3 70B, Mistral 7B, and any model with a reusable...
Lost-in-the-Middle: Fix LLM Position Bias (Python)
Measure and fix LLM position bias with Python. Build a needle-in-haystack test, plot the U-shaped curve, and implement position reordering.
Long-Context LLMs: Sliding Window Summarization Guide
Build a sliding window summarization pipeline in Python that handles documents exceeding LLM context windows. Map-reduce and recursive strategies...
LLM Streaming Tutorial: SSE in Python Step-by-Step
Stream LLM tokens from OpenAI, Claude, and Gemini in Python using SSE and async generators. Includes FastAPI server, backpressure handling, and...
LLM Scaling Laws: Model Comparison Dashboard (2026)
Learn LLM scaling laws and compare GPT, Claude, Gemini, Llama, Mistral, and DeepSeek on benchmarks, pricing, and context windows with interactive...
Temperature, Top-p & Top-k in LLMs Explained (Python)
Master LLM temperature, top-k, and top-p with interactive Python simulations. Runnable code, exercises, and a sampling playground to build real...
GPT vs Claude vs Gemini: Python Benchmark (2026)
Build a Python benchmarking harness to compare GPT-4o, Claude, Gemini, and Llama on quality, latency, and cost with LLM-as-judge and radar charts.
LLM Evaluation: Build an LLM-as-Judge Pipeline
Build an LLM evaluation pipeline in Python with LLM-as-judge scoring, rubric design, A/B testing, and regression alerts. Runnable code examples...
Build an LLM Benchmarking Platform (Python Project)
Build an LLM benchmarking platform in Python from scratch. Define test suites, compare providers with raw HTTP, score with LLM-as-judge, and generate...
LLM API Pricing Guide: Compare & Optimize Costs
Learn to count LLM tokens with tiktoken, compare API pricing across OpenAI, Claude, and Gemini (March 2026), and cut costs by 90% with 10 proven...
OpenAI, Claude & Gemini API Tutorial in Python (2026)
Learn to call OpenAI, Claude, and Gemini APIs from Python in 15 minutes. Includes code examples, error handling, streaming, and a unified wrapper.
KV Cache Explained: Build a Cache Manager in Python
Learn how KV caching works in LLMs, calculate VRAM usage for real models, and build a PagedAttention-style cache manager with token eviction in pure...
Groq vs Fireworks vs Together AI: Speed Benchmark
Build a Python benchmark harness comparing Groq, Fireworks, Together AI, and Replicate on latency, throughput, and cost with runnable code.
Hugging Face Inference API Tutorial in Python
Master Hugging Face inference in 20 minutes. Run LLMs locally with Pipeline API or serverless via HTTP, with Python examples you can copy and run.
Gemini API Tutorial: Multimodal AI in Python
Build a multimodal document analyzer with the Google Gemini API in Python. Analyze images, PDFs, and text with structured JSON output, using raw HTTP...
LLM Context Windows Explained: Token Budget Guide
Learn how LLM context windows work, count tokens with tiktoken, estimate API costs, and build a Python token budget manager that allocates context...
Constitutional AI: Build a Self-Critique Loop (Python)
Build a Constitutional AI safety loop in Python. Generate, critique, and revise LLM responses with raw API calls, no fine-tuning needed.
How LLM Tokenization Works: Build a BPE Tokenizer
Build a working BPE tokenizer in Python, learn how text becomes tokens, and use tiktoken to count tokens and estimate LLM API costs across providers.
Claude API Tutorial: Messages, Tools & Streaming
Master the Claude API with raw HTTP, messages, streaming, tool use, extended thinking, and prompt caching with runnable Python code examples.
What Is LangGraph? How It Works and When to Use It
Discover what is LangGraph, how it compares to LangChain, and when graph-based orchestration is the right choice for building reliable AI agents.
Prompt Engineering Fundamentals, Reliable LLM Outputs
Apply prompt engineering fundamentals, zero-shot, few-shot, chain-of-thought, and structured output, to get consistent, reliable results from any LLM.
LangGraph Tool Calling: Build Agents That Take Action
Build LangGraph agents that call tools with @tool, bind_tools, and ToolNode. Step-by-step examples for web search, database queries, and API calls in...
LangGraph Subgraphs: Compose Reusable Workflows
Learn how to build modular LangGraph apps with subgraphs you can develop, test, and reuse across projects, with full code examples and patterns.
LangGraph Structured Output & Self-Correcting Agents
Build LangGraph agents that return validated, typed data using Pydantic models, with automatic retry loops that self-correct on validation failures.
LangGraph Streaming: Real-Time Agent Output Guide
Add real-time streaming to your LangGraph agents, pick the right stream mode, show tokens as they arrive, and build chat UIs that feel instant.
LangGraph State Management: TypedDict & Reducers
Master LangGraph state management with TypedDict schemas, reducer functions, and add_messages. Learn how nodes share data, merge updates, and track...
LangGraph ReAct Agent: Build from Scratch
Learn to build a ReAct agent from scratch in LangGraph with this hands-on guide, wire the think-act-observe loop, add tools, and debug agent cycles.
LangGraph RAG Agent: Self-Correcting Retrieval Pipeline
Build a RAG agent in LangGraph that routes questions, grades documents, detects hallucinations, and rewrites queries when results are poor. Full code...
LangGraph SQL Agent: Answer Business Questions
Step-by-step guide to building a LangGraph SQL agent that turns plain English into SQL, runs queries, retries on errors, and explains results clearly.
LangGraph Multi-Agent Research Assistant Project
Build a multi-agent research pipeline in LangGraph with planner, researcher, writer, and reviewer agents that turn any topic into a polished report.
LangGraph + FastAPI: Build a Full-Stack AI App
Build a full-stack AI app from scratch with FastAPI and LangGraph, streaming responses, saved chats, API key auth, and a live chat frontend in one...
LangGraph Document Processing Agent: Multi-Modal
Build a LangGraph agent that reads PDFs, images, and text, cross-checks facts across sources, and writes a clean JSON report, with full code...
LangGraph Customer Support Agent with Escalation
Learn to build a LangGraph customer support agent that classifies queries, searches a knowledge base, escalates to humans, and logs every step.
LangGraph Web Scraping Agent: Autonomous Pipeline
Learn to build a LangGraph pipeline that scrapes websites on its own, pulls structured data, handles pagination and errors, and writes analytical...
LangGraph Platform: Deploy Agents as APIs
Deploy LangGraph agents as scalable APIs with LangGraph Server, step-by-step guide covering SDK setup, streaming, background runs, and cloud hosting.
LangGraph Checkpointing: Save & Resume Graph State
Save and resume LangGraph agent state with checkpointers so your conversations survive crashes, restarts, and long breaks between sessions.
LangGraph Debugging with LangSmith Tracing Guide
Master LangGraph debugging with LangSmith tracing, follow step-by-step examples to inspect agent runs, tag traces, and monitor production performance.
LangGraph Multi-Agent: Supervisor, Swarm & Network
Build multi-agent AI systems in LangGraph using supervisor, swarm, and network patterns, with full code for each and a guide to choosing the right...
LangGraph Memory: Short-Term, Long-Term & Conversation
Build LangGraph agents with lasting memory using sliding windows, summaries, and cross-session stores to manage tokens and recall user context.
LangGraph Map-Reduce: Parallel Execution with Send API
Learn how to run LangGraph branches in parallel using the Send API and map-reduce pattern to process multiple items at once and merge results cleanly.
LangGraph Installation & Setup: Build Your First Graph
Complete your LangGraph installation setup in minutes, then build and run your first StateGraph that calls an LLM and returns a response.
LangGraph Human-in-the-Loop: Add Approval Steps
Learn to pause LangGraph agents for human review, accept edits, and resume safely with working interrupt and Command patterns.
LangGraph Nodes, Edges & State: Core Concepts Explained
Understand LangGraph nodes edges state and conditional routing through visual diagrams and runnable Python examples you can copy and extend.
LangGraph Error Handling: Retries & Fallback Strategies
Make your LangGraph agents production-ready with retry logic, fallback paths, and error tracking that keeps pipelines alive when things go wrong.
LangGraph Cycles & Recursion Limits: Control Agent Loops
Master LangGraph cycles and recursion limits, stop runaway agents, handle GraphRecursionError, and build clean exit strategies for your loops.
LangGraph Conditional Edges: Dynamic Routing Guide
Build LangGraph workflows that branch at runtime using conditional edges and routing functions. Route by LLM output, user input, or custom logic with...
LangGraph Code Generation Agent: Build & Run Python
Step-by-step guide to building a LangGraph agent that writes Python code, runs it safely, checks the output, and self-corrects until it works.
LangChain Crash Course, Chains, Models, and Output Parsers
Follow this hands-on LangChain tutorial to master chat models, prompt templates, output parsers, and LCEL chains with runnable Python examples.
Introduction to LLMs and the OpenAI API in Python
Start using the OpenAI API Python SDK today. Build your first LLM-powered app with runnable code for chat completions, streaming, and token...
Unsloth Fine-Tuning, Train LLMs 2x Faster with 70% Less Memory
Fine-tune LLMs with Unsloth, 2x faster training, 70% less GPU memory. Step-by-step guide with LoRA, QLoRA, code examples, and deployment tips.
How to Evaluate LLMs, Metrics, Benchmarks & Python Code
Learn LLM evaluation from scratch -- benchmarks, metrics (BLEU, ROUGE, perplexity), LLM-as-judge, and custom pipelines with runnable Python code.
DPO (Direct Preference Optimization), A Simpler Alternative to RLHF
Align LLMs with human preferences using one loss function -- no reward model, no RL. Complete guide with derivation, PyTorch code, and DPO variants.
How LLMs Work: Transformers Explained Step-by-Step
Learn how LLMs work step by step. Build an inference simulator in Python, tokenize, embed, compute attention, sample, and decode with runnable code...
Build an AI Chatbot with Memory in Python (2026)
Build a Python AI chatbot with conversation memory that actually remembers. Raw HTTP tutorial with streaming, 3 hands-on exercises, and complete code...
2025 20
RAPTOR RAG Explained: Building Hierarchical Retrieval for Smarter AI Answers
RAPTOR (Recursive Abstractive Processing for Tree-Organized Retrieval) builds a tree of increasingly abstract summaries over your documents, so RAG...
GraphRAG Explained: Your Complete Guide to Knowledge Graph-Powered RAG
Graph RAG is an advanced RAG technique that connects text chunks using vector similari to build knowledge graphs, enabling more comprehensive and...
Fusion RAG Explained: How to Combine Vector and Keyword Search for Better AI Answers
Fusion RAG is a technique that combines vector and keyword search scores to find more relevant documents for your system. Instead of relying on just...
Feedback Loop RAG: Improving Retrieval with User Interactions
Feedback Loop RAG is an advanced RAG technique that learns from user interactions to continuously improve retrieval quality over time. Unlike...
Adaptive RAG: The Ultimate Guide to Dynamic Retrieval-Augmented Generation
Adaptive RAG chooses the retrieval strategy from the question's complexity: no retrieval for simple queries, single-step retrieval for factual ones...
Self RAG Explained: Teaching AI to Evaluate Its Own Responses
Self RAG teaches a language model to critique its own generation: decide when retrieval is needed, judge whether retrieved passages are relevant and...
Multi-Modal RAG Explained: How AI Understands Text, Images, and More
Multi-Modal RAG retrieves from text and visual content together, so an AI system can answer questions from documents, images, charts and diagrams...
Document Augmentation : A Guide to Optimizing RAG Performance
Document Augmentation RAG enriches documents with generated summaries, questions and metadata before indexing, so user queries match more entry...
Corrective RAG: Fixing LLM Errors for Accurate AI Response
Corrective RAG (CRAG) is an advanced RAG technique that adds a quality check layer to your retrieval system. Instead of blindly trusting retrieved...
Building Reliable RAG Systems: Adding Validation Layers for Accurate AI Answers
Reliable RAG adds validation layers to retrieval-augmented generation: it checks document relevance, detects hallucinations and highlights which...
Hybrid Search: Vector + Keyword Techniques for better RAG retrieval
Hybrid Search RAG combines vector embeddings for semantic matches with keyword search for exact matches, then ranks and merges the results. Learn how...
Explainable Retrieval: How to Make RAG Systems Transparent & Trustworthy
Explainable Retrieval is a technique that makes RAG (Retrieval-Augmented Generation) systems transparent by showing users which documents were...
Semantic Chunking for RAG: Optimizing Retrieval-Augmented Generation
Semantic Chunking is a context-aware text splitting technique that groups sentences by meaning rather than splitting by fixed sizes. This preserves...
HyPE-RAG: How Hypothetical Prompt Embeddings Solve Question Matching in Retrieval Systems
HyPE (Hypothetical Prompt Embeddings) is an advanced RAG enhancement technique that precomputes hypothetical questions for each document chunk during...
Optimizing RAG Chunk Size: Your Definitive Guide to Better Retrieval Accuracy
The optimal chunk size for RAG systems is usually 128 to 512 tokens: smaller chunks suit precise fact lookups, larger chunks keep more context for...
Relevant Segment Extraction (RSE) – Building better Context by assembling contiguous chunks for better RAG Performance
Relevant Segment Extraction (RSE) is a query-time post-processing technique that intelligently combines related text chunks into longer, coherent...
Hypothetical Document Embedding (HyDE) – A Smarter RAG method to Search Documents
Learn how HyDE (Hypothetical Document Embeddings) improves RAG systems by creating richer query embeddings for smarter, more accurate AI-driven...
Build a Simple RAG System with CSV Files: Step-by-Step Guide for Beginners
Learn how to build a Simple RAG system using CSV files by converting structured data into embeddings for more accurate, AI-powered question answering.
Simple RAG Explained: A Beginner’s Guide to Retrieval-Augmented Generation (RAG)
Discover how Simple RAG (Retrieval-Augmented Generation) works. This beginner’s guide breaks down how RAG works step by step with Python code...
Ollama Tutorial: Your Guide to running LLMs Locally
A complete guide to Ollama, run LLMs like Llama 3, Mistral, and Gemma locally. Covers installation, model management, prompting, API usage, and...