//
Search across all documentation pages
13 pages in this section.
Why tokens, context windows, the prompt-as-interface idea, and structured output/tool schemas are one underlying model rather than unrelated API details - the mental model behind every other page in this section.
Learn LLM basics with 10 Python examples, covering chat completions, system and user prompts, and prerequisites for OpenAI and Anthropic APIs.
Integrate Anthropic Claude models into your Python applications. Learn to use the Messages API for streaming, tool use, vision, and structured outputs.
Learn to use the OpenAI Python SDK for chat completions, embeddings, and tool calling. Discover how LiteLLM abstracts multiple LLM providers.
Load and run open-source models from Hugging Face Hub using the transformers library. Use pipeline for quick inference or AutoModel for custom generation.
Learn prompt engineering techniques to shape LLM behavior, reduce hallucinations, and improve task accuracy with system prompts, few-shot examples, and chain-of-thought.
Learn to generate and use text embeddings with OpenAI's API. Discover how embeddings power semantic search, clustering, and RAG retrieval.
Build reliable, safe, and cost-effective LLM applications. Learn best practices for security, API usage, and prompt quality.
A single-page roundup of every highlight bullet from the 12 pages in the LLMs & GenAI section, grouped by source page so you can scan all 49 takeaways without opening each article individually.