Skip to content
Codeloom

Topics / LLMs

🤖

LLMs

Large language models, prompting, tool use, and agentic patterns.

Browse 45 tutorials → Other topics

Why learn LLMs?

  • The fastest-growing capability in software since the smartphone.

  • Used in code review, search, support, content, and agentic workflows.

  • Every product team is now adding AI features.

  • A skill that pairs well with any backend or frontend role.

What you can build with LLMs

Chatbots and copilots Document Q&A and search Workflow automation with tool use Content generation and summarization

LLMs tutorials

45 articles · page 1 of 3

Hand-written tutorials, ordered as a recommended learning path.

  1. 01 What Is an LLM? A clear, honest introduction to large language models — tokens, next-token prediction, training vs inference, context windows, why hallucinations happen, and when LLMs are the right tool.
  2. 02 Tool Use & Function Calling How LLMs call functions: defining tools with JSON schema, the request → tool-call → response loop, common patterns like search and database queries, and the failure modes that bite in production.
  3. 03 LLM Evaluation Why vibes do not scale: building golden datasets, exact-match vs LLM-as-judge scoring, A/B comparing prompts and models, regression suites, and the observability you need to ship safely.
  4. 04 Context Window Strategies Learn practical strategies for handling long documents within LLM context windows, including chunking, summarization, sliding windows, and map-reduce patterns.
  5. 05 Evaluation Metrics Master LLM evaluation with automated metrics like BLEU and ROUGE, plus human evaluation frameworks for measuring quality, safety, and reliability.
  6. 06 Function Calling Compare function calling implementations across OpenAI, Anthropic, and Google, with patterns for routing, chaining, and error handling.
  7. 07 Semantic Caching Reduce LLM API costs and latency by caching responses based on semantic similarity rather than exact string matching.
  8. 08 Structured Output Extract structured data from unstructured text using LLMs with JSON mode, Pydantic validation, and provider-specific structured output APIs.
  9. 09 Synthetic Data Use large language models to generate high-quality synthetic datasets for training, testing, and evaluating AI systems.
  10. 10 Context Windows Manage long conversations and large documents within LLM context limits using truncation, summarization, and sliding window techniques.
  11. 11 Batching & Throughput Maximize LLM throughput and reduce costs with request batching, concurrent API calls, and queue-based processing patterns.
  12. 12 Hallucination Mitigation Detect, measure, and reduce LLM hallucinations with grounding, verification chains, and citation-based generation techniques.
  13. 13 Fine-Tuning LLMs A hands-on guide to fine-tuning large language models using LoRA, QLoRA, and Hugging Face. Covers dataset preparation, training configuration, evaluation, and deployment considerations.
  14. 14 Function Calling How to implement function calling and tool use with LLMs. Covers tool definitions, the execution loop, multi-turn conversations, error handling, and parallel tool calls.
  15. 15 Structured Output How to reliably get JSON, typed objects, and structured data from LLMs using JSON mode, function calling, Pydantic schemas, and constrained generation with the Outlines library.
  16. 16 Tokenization How LLMs break text into tokens using BPE, SentencePiece, and tiktoken. Covers vocabulary construction, token limits, and practical implications for prompt engineering.
  17. 17 Eval Frameworks A practical overview of evaluation frameworks for AI applications: what they measure, how they differ, and how to pick one that matches your workflow.
  18. 18 Multimodal Models An introduction to multimodal AI models that handle text, images, audio, and video, including how they work, how to use them, and where they shine.
  19. 19 Open Source Models A practical comparison of leading open source language models: Llama, Mistral, Qwen, Gemma, and Phi families, with guidance on licenses, sizes, and where each fits.
  20. 20 RLHF Explained How RLHF turns raw language models into helpful assistants: the three-stage pipeline, reward modeling, PPO, and the trade-offs that drive newer alternatives like DPO.