Generative AI
Dive into Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Agentic AI Workflows, LangGraph, custom assistants, and production deployment of AI applications.
Generative AI Tutorials (86)
Browse, search, and work through all available articles for this category.
Loop Engineering: How to Build AI Agents That Know When They Are Done
Loop engineering explained: the five-step agent loop, why state must live outside the model, why a maker cannot grade its own work, and the four ways loops fail.
Read Tutorial
Interactive LLM Demos: A 40-Day Visual Roadmap to Generative AI
A verified list of free, browser-based interactive demos that teach LLMs, embeddings, RAG, vector databases, and AI agents across a 40-day learning path.
Read Tutorial
Build and Deploy a Free Customer Support AI Agent with Hexabot, OpenRouter, and Railway on a Live Website
A complete, hands-on walkthrough for building a free customer support AI agent with open-source Hexabot and a free OpenRouter model, deploying it on Railway with Postgres, grounding it in your own content with RAG, and embedding the live-chat widget on your live website.
Read Tutorial
Production Deployment of LangChain DeepAgent Systems
Deploy a production-ready LangChain DeepAgent financial research system utilizing sandboxed filesystem backends, LangGraph CLI servers, and a custom UI frontend.
Read Tutorial
Orchestrating Hierarchical Multi-Agent Research Teams
Implement a hierarchical multi-agent research team coordinating Orchestrator, Researcher, and Editor agents on a real filesystem using LangGraph.
Read Tutorial
Decomposing Financial Queries with TODO Planning Agents
Implement a task-planning agentic RAG system that decomposes complex financial comparison queries into checklists using TodoListMiddleware and SummarizationMiddleware.
Read Tutorial
Building a Dual-Tool Multimodal Financial Research Agent
Build a dual-tool multimodal financial research agent with persistent SQLite session memory, historical hybrid search, and live Yahoo Finance MCP integration.
Read Tutorial
Advanced Hybrid Search and Reranking for Agentic RAG
Master advanced retrieval strategies by combining dense embeddings, sparse BM25 tokenizers, dynamic metadata filtering, and Cross-Encoder reranking.
Read Tutorial
Multimodal Data Ingestion Pipeline with Docling and Qdrant
Design and implement a complete financial document ingestion pipeline extracting text, tables, and charts with Docling and storing them in Qdrant with hybrid vector embeddings.
Read Tutorial
Real-World Agent Project: MySQL & Streaming
Load an e-commerce SQLite database into a cloud MySQL server and connect it to a read-only streaming agent that answers questions over real data.
Read Tutorial
Deploy AI Agents with FastAPI
Serve your agent through FastAPI streaming endpoints and build a Streamlit chat client that consumes the live token stream with memory and PDF export.
Read Tutorial
Build a Daily Briefing AI Agent
Combine Gmail, Google Calendar, Yahoo Finance, weather, and web search MCP tools into one agent that delivers a personalized morning briefing.
Read Tutorial
Build a Google Sheets Analysis Agent with MCP
Connect Google Sheets and Yahoo Finance MCP servers so an agent can read spreadsheets, analyze data, and report financial insights from the terminal.
Read Tutorial
Build a Code Execution Agent with E2B
Give an AI agent a secure E2B cloud sandbox to run Python, analyze CSV and Excel data, and generate charts without touching your machine.
Read Tutorial
Build a Travel Planner Agent with MCP
Build a travel planner agent that combines Airbnb and Google Calendar MCP servers with memory to plan trips and add itineraries to your calendar.
Read Tutorial
Build a Hotel Search AI Agent with MCP
Learn the Model Context Protocol and build a hotel search agent that connects an Airbnb MCP server to a Gemini agent for live listings, weather, and web search.
Read Tutorial
LangChain Agent Fundamentals
Master LangChain agents end to end: tools, short- and long-term memory, streaming, middleware, guardrails, human-in-the-loop, and prompt engineering.
Read Tutorial
Getting Started with Gemini 3 & LangChain
Set up Gemini 3, LangChain, and LangSmith, then explore streaming, multimodal input, tool calling, reasoning, and context caching for AI agents.
Read Tutorial
LangChain Agents Bootcamp: Financial Analysis
Build custom LangChain agents with SQLite memory checkpointers, structured outputs, stream updates, and custom middleware for PII and todo planning.
Read Tutorial
MCP Stock Researcher Agent for Financial Analysis
Build a specialized financial research agent utilizing Model Context Protocol (MCP) and Yahoo Finance server tools for real-time stock analysis.
Read Tutorial
Hugging Face Transformers: A Beginner's Guide
Get started with Hugging Face Transformers: run pretrained models in one line with pipelines for text, image, and audio tasks like classification, QA, and translation.
Read Tutorial
RAGWire Architecture and Setup
Learn RAGWire's production RAG architecture, configure ingestion and retrieval pipelines, and build a filter-aware agent in a Jupyter notebook.
Read Tutorial
RAGWire Providers and Components
Swap between Ollama, OpenAI, Gemini, Groq, and HuggingFace with a single config change. Use Qdrant Cloud with MMR retrieval.
Read Tutorial
Transformer Architecture & LLM Foundations
Understand the transformer architecture from the ground up: why RNNs fell short, how self-attention works, and how encoders and decoders power modern LLMs.
Read Tutorial
BERT Architecture: Theory and Fine-Tuning
Learn how BERT's bidirectional encoder works, how masked language modeling pretrains it, and how a classification head adapts it to downstream NLP tasks.
Read Tutorial
Personal Gym Supplements RAG
Build a domain-specific RAG pipeline for health supplement research papers with custom metadata extraction and hybrid retrieval.
Read Tutorial
Conversational RAG Chatbot with Chainlit
Build an end-to-end conversational RAG chatbot in a single file with RAGWire, LangChain agent, and Chainlit UI.
Read Tutorial
Fine-Tuning BERT for Sentiment Classification
Fine-tune BERT for multi-class emotion classification on Twitter tweets using Hugging Face Transformers, the Trainer API, and a custom evaluation function.
Read Tutorial
Knowledge Distillation: DistilBERT, TinyBERT, MobileBERT
Understand knowledge distillation and how DistilBERT, TinyBERT, and MobileBERT compress BERT into smaller, faster models that keep most of its accuracy.
Read Tutorial
Chainlit Chat Frontend with Auth
Build a production Chainlit frontend with SSE streaming, persistent SQLite chat history, password auth, and PDF export.
Read Tutorial
Fine-Tuning Distilled BERT for Fake News Detection
Fine-tune DistilBERT, MobileBERT, and TinyBERT to detect fake news, then benchmark their accuracy and speed against full BERT in a head-to-head comparison.
Read Tutorial
Fine-Tuning DistilBERT for Restaurant Search NER
Fine-tune DistilBERT for named entity recognition on restaurant search queries, extracting cuisines, locations, ratings, and dishes with IOB tagging and seqeval.
Read Tutorial
Multi-Agent Supervisor with MS Agent Framework
Build a parallel multi-agent RAG workflow with Microsoft Agent Framework, four specialists, a fan-in aggregator, and a synthesizer.
Read Tutorial
Fine-Tuning T5 for Custom Text Summarization
Fine-tune the T5 text-to-text model for abstractive dialogue summarization on the SAMSum dataset using Hugging Face's Seq2Seq Trainer and data collator.
Read Tutorial
Fine-Tuning Vision Transformer (ViT) for Images
Fine-tune a Vision Transformer (ViT) to classify Indian food images with Hugging Face, using an image processor, the Trainer API, and patch-based attention.
Read Tutorial
Fine-Tuning Phi-2 with LoRA and QLoRA
Learn the theory behind PEFT, LoRA, and QLoRA, then fine-tune Microsoft's Phi-2 on a custom product dataset with quantization on a single GPU.
Read Tutorial
Fine-Tuning TinyLlama as a Chat (Instruct) Model
Turn the TinyLlama 1.1B base model into a conversational assistant with 4-bit QLoRA, chat templates, and the TRL SFTTrainer on a single GPU.
Read Tutorial
MCP Dev Setup: Anaconda, uv, and Claude
Set up a complete MCP development environment on Windows, Anaconda, Ollama, Node.js, Claude Desktop, and the uv package manager, with Linux/macOS notes.
Read Tutorial
PageRAG Data Ingestion with Docling & ChromaDB
Build a page-wise PDF ingestion pipeline with Docling, filename metadata, SHA-256 deduplication, and local nomic-embed-text embeddings stored in ChromaDB.
Read Tutorial
Introduction to Model Context Protocol
Understand the Model Context Protocol, client, host, and server roles, the JSON-RPC foundation, tools/resources/prompts, and stdio vs Streamable HTTP transports.
Read Tutorial
RAG Data Retrieval and Re-Ranking with BM25Plus
Hybrid retrieval over SEC filings, LLM metadata filters and SEC keywords, MMR search in ChromaDB, and BM25Plus re-ranking, packaged as reusable LangChain tools.
Read Tutorial
Agentic PageRAG: A ReAct Agent with LangGraph
Build a ReAct agent in LangGraph that wraps retrieval as a tool, decides when to call it, decomposes comparison questions, and answers SEC filings with citations.
Read Tutorial
Build Your First MCP Server with FastMCP
Build your first MCP server with FastMCP, a math tool and a live weather tool, then call them from both the raw MCP SDK client and the FastMCP client.
Read Tutorial
Corrective RAG (CRAG) with LangGraph and Ollama
Build a self-correcting CRAG workflow in LangGraph that grades retrieved documents, rewrites weak queries, and falls back to web search before answering.
Read Tutorial
MCP Servers with a Local LangChain Agent
Connect local Ollama LLMs to MCP servers as an autonomous agent using mcp-use, run multiple servers, switch stdio/HTTP transports, and use a server manager.
Read Tutorial
Connect MCP Servers to Claude Desktop
Register your own and community MCP servers in Claude Desktop, edit claude_desktop_config.json, add stdio servers with uv/npx/uvx, and use them safely.
Read Tutorial
Reflexion Agentic RAG: Self-Improving Answers
Build a Reflexion agent in LangGraph that drafts an answer, reflects on missing information, retrieves to fill gaps, and revises iteratively until complete.
Read Tutorial
MCP for Data Analysis with Claude Desktop
Turn Claude Desktop into a no-code data analyst, read an Excel support-ticket dataset with an MCP server and auto-generate a PowerPoint analysis report.
Read Tutorial
Self-RAG: Grounded Answers with Quality Gates
Build Self-RAG in LangGraph with document grading plus hallucination and answer-quality gates that regenerate or rewrite until the answer is grounded and useful.
Read Tutorial
Adaptive RAG: Routing Documents, SQL, and Web
Build Adaptive RAG in LangGraph that routes each query to a vector store, a SQL employee database, or live web search, with SQLite short-term memory.
Read Tutorial
MCP Tools, Resources, and Prompts
Master MCP's three building blocks, tools, resources, and prompts, by building a job-search assistant server with FastMCP, the JSearch API, and a resume resource.
Read Tutorial
MCP RAG Server with LangChain & ChromaDB
Build an MCP vector-database server with FastMCP, ChromaDB, and Ollama embeddings, ingest PDFs from a file, folder, or URL, then query it from a Streamlit agent.
Read Tutorial
Research Assistant with MCP and LangGraph
Build a research assistant that crawls the web with Firecrawl and stores findings in per-topic ChromaDB vector stores, orchestrated by a LangGraph agent over multiple MCP servers.
Read Tutorial
Deploy an MCP Server on AWS EC2
Deploy a remote MCP server on an Amazon Linux EC2 instance, SSH in, install Anaconda and uv, serve over Streamable HTTP with OpenAI embeddings, and connect Claude Desktop.
Read Tutorial
Publish Your MCP Server on PyPI
Turn your MCP server into a pip-installable package, restructure to a src layout, configure pyproject.toml and an entry point, build with uv, and publish to PyPI.
Read Tutorial
Introduction to LangGraph and Stateful Workflows
Learn the fundamentals of LangGraph. Master State, Nodes, and Edges to build stateful, multi-agent applications using a Finite State Machine model in Python.
Read Tutorial
Conditional Routing in LangGraph Workflows
Learn how to implement conditional routing in LangGraph. Use Pydantic to structure LLM outputs and route execution dynamically based on sentiment analysis.
Read Tutorial
Building a ReAct Agent with Tools in LangGraph
Learn how to build a stateful ReAct agent in LangGraph. Define custom tools for weather and math calculations, bind them to an LLM, and loop executions.
Read Tutorial
Agentic Memory and Streaming in LangGraph
Learn how to implement thread-based conversation memory with MemorySaver checkpointer and stream graph outputs in LangGraph with local Ollama models.
Read Tutorial
Short Term Memory with SQLite and PostgreSQL
Production-ready short-term memory using SQLite and PostgreSQL checkpointers, conversations that survive server restarts with full thread isolation.
Read Tutorial
Long Term Memory Across Conversations
Build agents with cross-thread long-term memory using PostgresStore, store user preferences, search semantically, and personalize responses across sessions.
Read Tutorial
Interrupt and Human-in-the-Loop Workflows
Pause agent execution for human approval using interrupt(), resume with the Command API, and protect users with a regex PII guardrail node.
Read Tutorial
Building a Reflection Agent in LangGraph
Build a self-improving research agent with a researcher node, critique node, and iterative reflection loop, web search, evaluate, revise, repeat.
Read Tutorial
SQL Agent with LangGraph Workflows
Build a natural language SQL agent with LangGraph, dedicated tools for schema inspection, query generation, validation, execution, and error fixing.
Read Tutorial
MCP Integration with LangGraph
Connect LangGraph agents to external MCP servers, build an Airbnb search agent using langchain-mcp-adapters and the @openbnb/mcp-server-airbnb package.
Read Tutorial
I Gave Claude Fable 5 a Real Consulting Project
A hands-on test of Claude Fable 5 on a live financial consulting project, PDF analysis, legacy code migration, reconciliation debugging, and autonomous reports.
Read Tutorial
Ollama Setup Guide
Install Ollama, master every CLI command, call the REST API, and build a custom persona model using a Modelfile, all locally.
Read Tutorial
LangChain Getting Started
Install LangChain and langchain-ollama, configure environment variables, connect to a local Ollama model, and invoke and stream chat completions in Python.
Read Tutorial
LangChain Prompt Templates
Master LangChain prompt templates, message roles, SystemMessage, HumanMessage, and ChatPromptTemplate with dynamic variables.
Read Tutorial
LangChain Expression Language & Chains
Master LangChain Expression Language (LCEL), sequential, parallel, router, and custom chains with the pipe operator, RunnableParallel, and @chain.
Read Tutorial
LangChain Output Parsing
Parse LLM responses into structured Python objects, Pydantic models, JSON dicts, and CSV lists, using LangChain's output parsers and with_structured_output().
Read Tutorial
LangChain Chat Message Memory
Add persistent chat memory to any LangChain chain, store and replay multi-turn conversation history using RunnableWithMessageHistory and SQLChatMessageHistory.
Read Tutorial
Build Your Own Chatbot with LangChain
Build a streaming, multi-session chatbot web app with LangChain, Ollama, and Streamlit, using persistent SQL memory and token-by-token streaming output.
Read Tutorial
LangChain Document Loaders
Load PDFs, webpages, PowerPoint, Excel, and Word files into LangChain for Q&A and summarization, plus MarkitDown and Docling for advanced extraction.
Read Tutorial
Vector Stores and Retrievals with FAISS
Build a FAISS vector store from PDF documents using Ollama embeddings. Chunk, embed, index, and retrieve semantically relevant content for RAG applications.
Read Tutorial
RAG: Chat with Your Own Documents
Build a complete RAG chain that loads a persisted FAISS vector store and answers questions grounded strictly in your own documents using LangChain and Ollama.
Read Tutorial
Tool Calling and Function Calling with LangChain
Define custom tools, bind them to an LLM, call multiple tools in parallel, and generate grounded final answers using LangChain's tool-calling API with Ollama.
Read Tutorial
LangChain Agents with create_agent
Build autonomous LangChain v1 agents with create_agent, wire web search tools, tune model parameters, switch models dynamically, and stream responses.
Read Tutorial
Agentic RAG with LangChain, FAISS, and Ollama
Turn a FAISS vector store into an agent tool and build Agentic RAG that retrieves document context only when relevant, with a streaming chat loop.
Read Tutorial
Text to SQL Agent with LangChain
Build a natural language SQL agent with five tools: schema inspection, query generation, validation, execution, and error correction.
Read Tutorial
LinkedIn Profile Scraping with LLM
Scrape LinkedIn profiles with Selenium and BeautifulSoup, clean the raw HTML, and structure the data as JSON with a two-pass LLM pipeline.
Read Tutorial
Resume Parsing with LangChain and LLMs
Extract structured data from PDF resumes with PyMuPDF and an LLM, guaranteeing valid JSON via JsonOutputParser in a two-stage pipeline.
Read Tutorial
Deploy Resume Parsing with Streamlit
Wrap the two-stage LLM resume parser in a Streamlit web app, upload PDFs and view extracted JSON data in real time.
Read Tutorial
RAGWire, FastAPI RAG Backend Setup
Step-by-step guide to deploying RAGWire, an OpenAI-compatible FastAPI RAG server, on Railway, Render, AWS ECS, GCP Cloud Run, and Azure Container Apps.
Read Tutorial
OpenAI Compatible FastAPI Endpoint API Reference
Full API reference for RAGWire's OpenAI-compatible FastAPI endpoints covering health checks, model listing, chat completions, and document ingestion.
Read Tutorial
Hunyuan3D v2 and Blender MCP Setup Guide
Step-by-step guide to integrating Hunyuan3D-2 with Blender MCP so Claude Desktop can generate and place 3D assets inside Blender scenes via natural language.
Read Tutorial