Guides & Tutorials
Step-by-step tutorials to help you build AI apps, master new frameworks, and optimize your workflows.
Sort by:
Build a Titanic Data Analyst Agent with smolagents
Use smolagents CodeAgent to explore Titanic data, generate plots, and train an ML baseline from one natural-language prompt.
Read more →
Run a Microsoft AutoGen Team as a FastAPI WebSocket App
Adapt Microsoft AutoGen's app_team.py into a FastAPI WebSocket endpoint that streams multi-agent chat, persists state, and serves a browser UI.
Read more →
Fine-Tune a Quantized Llama on GSM8K with PEFT LoftQ
A step-by-step walkthrough of the Hugging Face PEFT GSM8K LoftQ script: 4-bit NF4 loading, preprocessing, training, and exact-match accuracy.
Read more →
Benchmark Local Models with llama.cpp's llama-eval.py
Use llama.cpp's single-file eval harness to run reproducible AIME, GSM8K, and GPQA benchmarks against a local server with Wilson confidence intervals.
Read more →
Run Distributed Full-Model DPO with PyTorch FSDP
Implement full-parameter DPO across multi-GPU nodes using torchtune's FSDP recipe, concatenated forward passes, and activation memory controls.
Read more →
Run an LLM Locally to Interact with Your Documents: Complete Ollama & Open WebUI Guide
Build a completely offline, zero-leakage local document intelligence system using Ollama, Open WebUI, and nomic-embed-text with custom chunking and system prompt engineering.
Read more →
Showing 6 of 76 guides
Complete guides archive
Browse every published entry. Newest stories and guides remain available above.
Browse all 76 entries
2026
- Build a Titanic Data Analyst Agent with smolagents
- Run a Microsoft AutoGen Team as a FastAPI WebSocket App
- Fine-Tune a Quantized Llama on GSM8K with PEFT LoftQ
- Benchmark Local Models with llama.cpp's llama-eval.py
- Run Distributed Full-Model DPO with PyTorch FSDP
- Run an LLM Locally to Interact with Your Documents: Complete Ollama & Open WebUI Guide
- Self-Hosting Your First LLM: Complete Hardware, Benchmark & Deployment Playbook
- Run SGLang Offline Batch Inference Directly from Python
- Deploy an LTX-2 Two-Stage Text-to-Video API on Modal H200 GPUs
- Build a Hybrid Sparse-Dense RAG Search Pipeline in Milvus
- Build Multimodal Image Search in Elasticsearch
- Build Semantic Search over Meeting Audio with Whisper and Pinecone
- Generate Synthetic RAG Test Sets With Ragas
- Build a ReAct Agent with Guaranteed JSON Output Using Outlines
- Run LLMs Locally: 6 Practical Methods (Ollama, LM Studio, vLLM, Jan, llama.cpp, and llamafile)
- Generate and Run a Python Expression with Outlines
- Build a Multi-Tool Claude Agent with MCP Servers in Python
- Build an Agentic RAG System with smolagents and ChromaDB
- Automate Prompt Optimization with DSPy GEPA
- Build a Grounded Search Agent with Google ADK
- Build a Multi-Agent Financial Research Bot with OpenAI Agents SDK
- Build a Multi-Agent Sequential Pipeline with Semantic Kernel
- Host and Run Qwen3.8-Flash Locally: Complete Unsloth and llama.cpp Deployment Guide
- Build a Routed RAG Chatbot with LlamaIndex and Chainlit
- Expose LlamaIndex Tool Specs as an MCP Server with fastmcp
- Fine-Tuning LLMs with LoRA: A Complete Practical Guide to Training & GGUF Deployment
- Graph RAG with Neo4j and OpenAI: Build a Product Search Pipeline
- Fine-tune a model with GRPO for mathematical reasoning
- Guaranteed JSON from llama.cpp with Pydantic and GBNF grammars
- Chain of Verification with SGLang: Reduce LLM Hallucinations
- Build a Self-Correcting RAG Agent with LangGraph and Milvus
- Hybrid Search with RRF in Elasticsearch: A Complete Guide
- Build Persistent Agent Working Memory with MongoDB and Tavily
- Evaluate Multi-Turn Conversations with Ragas AspectCritic
- Self-Consistency Voting with Outlines and gpt-4o-mini
- How to Remove Claude Watermarks from Text, Code, and Files
- AI Web Scraping in Python: When an LLM Earns Its Cost
- Build a Text-to-SQL Agent with smolagents in One File
- Build a Multi-Modal RAG Pipeline with LlamaIndex and Qdrant
- Generate Video with Google Veo 3.1 and the Gemini Python SDK
- Run parallel Claude agents with asyncio and a message hub
- Build a Deep Research API Agent Pipeline with OpenAI
- Build a Local LLM Zero-Shot Classifier You Can Actually Deploy
- The Complete Developer Guide to Running LLMs Locally: From Ollama to Production
- Event-Driven Architecture for Agentic AI: The Architect's Guide
- Cursor AI: Complete Setup and Practical Coding Guide
- How to Run DeepSeek R1 Locally with Ollama: Full Setup Guide
- Run DeepSeek V4 Flash Locally with llama.cpp (2026)
- How to Run Qwen3 Locally with Ollama: Setup, API, and a Gradio App
- Self-Host DeepSeek V4 with vLLM: 2026 Deployment Guide
- 5 Cool Things I Did With Local Language Models
- Mastering Advanced RAG Evaluation: From Basic Metrics to LLM-as-a-Judge
- Building Context-Aware Search in Python with LLM Embeddings and Metadata
- Top 5 Small Language Models for Agentic Tool Calling
- Advanced LLM Compression: A Hands-on Implementation Guide for FP8, GPTQ, and SmoothQuant using llmcompressor
- Beyond Prompt Engineering: Deep-Dive RAG for Intent Detection & Slot Filling in AI Agents
- The Developer's Guide to Running Claude Code for Free: Ollama, OpenRouter, and Local Proxies
- Building a Production RAG Pipeline with Bedrock and OpenSearch Serverless
- Secure RAG on Google Cloud with RAG Engine and Gemini (2026)
- Learning to Rank: The Hidden Layer Powering Modern RAG
- Designing a Production-Grade RAG Architecture
- RAG vs MCP in 2026: What Each Solves and How They Fit Together
- Local RAG Tutorial: LangChain, Ollama & ChromaDB with Ragas
- How to Build a Time-Series RAG for Forecasting Data
- What Is Tokenization Drift? A Practical Guide to Finding and Fixing It
- How to Analyze and Fine-Tune Agent Reasoning Traces
- APIs vs MCPs vs MCP Gateways: A Practical Guide for AI Builders
- Building AI Agents in Python with Pydantic AI
- Run Claude Code Locally with Ollama (2026 Setup)
- AI Risk Management: A Comprehensive Guide to Securing AI Systems
- Build a Tool-Calling Agent with a Local Small Model and Ollama (2026)
- Zero to Automation: How to Build Your First AI Agent
- Self-Verification for AI Agents: Build an Evaluator-Optimizer Loop in LangGraph
- Build Multi-Tenant RAG with Pinecone and Next.js (2026)
- Deploy an Open-Source LLM on Runpod Serverless with vLLM (2026)
- Getting Started with LangChain in 2026: Build a RAG Agent and a RAG Chain