Building AI Applications with OpenAI Tools & Retrieval

Build reliable tool-calling systems using the OpenAI function calling API with parallel execution, permission boundaries, and production-grade error handling. Learn to define JSON Schema tool definitions, orchestrate parallel tool calls, enforce structured outputs with Pydantic, implement role-based tool permissions, and build a production tool orchestration runtime with retry logic and execution logging.

Build production-grade RAG pipelines using OpenAI embeddings, pgvector, hybrid search, and the native File Search API. Learn to compute semantic similarity with text-embedding-3-small, store and query vectors at scale with pgvector, combine BM25 keyword search with vector search using Reciprocal Rank Fusion, and build an enterprise RAG assistant with hallucination detection and source attribution.

Build real-world applications that combine vision, audio, and image generation using the OpenAI API. Learn to analyze images and documents with GPT-4o, transcribe and translate audio with Whisper, generate expressive speech with TTS, create and edit images with gpt-image-1, and orchestrate all modalities in a multimodal meeting assistant capstone project.

Build a fully playable web-based RPG powered by OpenAI. You'll start with a complete game engine rooms, characters, combat, pixel art, the whole dungeon and progressively breathe life into it using the OpenAI API. Each exercise adds a new AI capability: a game master that remembers your adventure, NPCs with real personalities, dynamically narrated combat, structured output for reliable state changes, streaming responses, and finally voiced narration with the OpenAI Speech API. By the end you'll have a game you actually want to play, and a solid understanding of how to build multi-turn, multi-persona, multi-modal AI applications.