tutorials

Tutorials

Verified step-by-step guides for AI development.

Overview

This category contains the best tutorials and learning resources for building AI applications, from beginner quickstarts to advanced deployment guides.

---

Tutorials

LangChain Quickstart

Field	Details
Description	Getting started with LangChain for building LLM applications
Level	Beginner
Topic	LangChain
Prerequisites	Python, API key
URL	python.langchain.com/docs/get_started/quickstart

What you'll learn: Basic LangChain setup, chains, prompts, memory.

---

RAG with LlamaIndex

Field	Details
Description	Building a RAG application from scratch with LlamaIndex
Level	Beginner
Topic	RAG
Prerequisites	Python, LLM API key
URL	docs.llamaindex.ai/en/stable/getting_started/starter_example/

What you'll learn: Document indexing, querying, RAG pipeline basics.

---

Fine-tuning LLMs

Field	Details
Description	Guide to fine-tuning open-source LLMs with LoRA
Level	Intermediate
Topic	Fine-tuning
Prerequisites	Python, PyTorch, Transformers
URL	huggingface.co/docs/transformers/training

What you'll learn: LoRA, PEFT, model customization, training loops.

---

Building Agents with CrewAI

Field	Details
Description	Tutorial for creating multi-agent systems with CrewAI
Level	Intermediate
Topic	Agents
Prerequisites	Python, LLM API key
URL	docs.crewai.com/getting-started/quickstart

What you'll learn: Agent roles, tool usage, multi-agent collaboration.

---

Deploying LLMs with vLLM

Field	Details
Description	Production deployment guide for LLMs using vLLM
Level	Advanced
Topic	Deployment
Prerequisites	Python, GPU, Linux
URL	docs.vllm.ai/en/latest/getting_started/quickstart.html

What you'll learn: Production serving, scaling, optimization.

---

Building RAG Apps with LangChain

Field	Details
Description	End-to-end tutorial for building retrieval-augmented generation applications
Level	Intermediate
Topic	RAG
Prerequisites	Python, LangChain, vector database
URL	python.langchain.com/docs/tutorials/rag

What you'll learn: Document loading, embedding, vector stores, retrieval chains.

---

Fine-tuning with LoRA/QLoRA

Field	Details
Description	Practical guide to parameter-efficient fine-tuning with LoRA and QLoRA
Level	Intermediate
Topic	Fine-tuning
Prerequisites	Python, PyTorch, GPU with 16GB+ VRAM
URL	huggingface.co/docs/peft/quicktour

What you'll learn: LoRA configuration, QLoRA 4-bit quantization, PEFT library.

---

Deploying with Docker

Field	Details
Description	Containerize and deploy AI applications using Docker
Level	Intermediate
Topic	Deployment
Prerequisites	Basic command line, Docker installed
URL	docs.docker.com/get-started/

What you'll learn: Dockerfile creation, containerization, Docker Compose, deployment.

---

Building Agents with AutoGen

Field	Details
Description	Tutorial for building multi-agent conversational AI systems with AutoGen
Level	Intermediate
Topic	Agents
Prerequisites	Python, LLM API key
URL	microsoft.github.io/autogen/docs/Getting-Started

What you'll learn: Agent orchestration, tool use, multi-agent workflows.

---

Prompt Engineering Guide

Field	Details
Description	Comprehensive guide to prompt engineering techniques and best practices
Level	Beginner
Topic	Prompting
Prerequisites	None
URL	prometingguide.ai

What you'll learn: Few-shot, chain-of-thought, zero-shot, advanced prompting strategies.

---

HuggingFace Transformers Tutorial

Field	Details
Description	Official tutorial for using HuggingFace Transformers library
Level	Beginner
Topic	Transformers
Prerequisites	Python
URL	huggingface.co/docs/transformers/training

What you'll learn: Pipeline API, fine-tuning, tokenizers, model hub usage.

---

Building with Ollama

Field	Details
Description	Guide to running and building with local LLMs using Ollama
Level	Beginner
Topic	Local LLMs
Prerequisites	Basic command line
URL	ollama.com/blog

What you'll learn: Model pulling, custom model creation, API integration, local inference.

---

Fine-tuning LLMs with Axolotl

Field	Details
Description	Complete guide to fine-tuning LLMs using the Axolotl framework
Level	Advanced
Topic	Fine-tuning
Prerequisites	Python, GPU with 24GB+ VRAM, Linux
URL	github.com/OpenAccess-AI-Collective/axolotl

What you'll learn: YAML config, multi-GPU training, LoRA/QLoRA, dataset prep, evaluation.

---

Quick Reference

Tutorial	Level	Topic	Time
LangChain Quickstart	Beginner	LangChain	30 min
RAG with LlamaIndex	Beginner	RAG	1 hour
Prompt Engineering Guide	Beginner	Prompting	1-2 hours
HF Transformers Tutorial	Beginner	Transformers	1 hour
Building with Ollama	Beginner	Local LLMs	30 min
Fine-tuning LLMs	Intermediate	Fine-tuning	2-4 hours
RAG with LangChain	Intermediate	RAG	2-3 hours
LoRA/QLoRA Fine-tuning	Intermediate	Fine-tuning	2-4 hours
CrewAI Agents	Intermediate	Agents	1-2 hours
AutoGen Agents	Intermediate	Agents	2-3 hours
Docker Deployment	Intermediate	Deployment	1-2 hours
vLLM Deployment	Advanced	Deployment	2-3 hours
Axolotl Fine-tuning	Advanced	Fine-tuning	4-6 hours

---

How to Use

1. Browse tutorials.json for all available tutorials
2. Filter by level (beginner, intermediate, advanced)
3. Follow URLs for full tutorial content
4. See ../templates/ for project starters
5. See ../research-papers/ for background theory

Related Categories

• Templates - Project starters
• Research Papers - Background theory
• AI Frameworks - Framework docs

---

Status: Actively maintained | Last updated: 2026-08-16