OpenAI API
Build AI-powered apps with the OpenAI API. Chat completions, function calling, embeddings, vision, DALL-E image generation, Assistants API, fine-tuning, streaming, and production patterns for cost and latency optimisation.
FundamentalsTopics 1–10
- ·What is the OpenAI API
- ·Getting Your API Key
- ·Chat Completions
- ·Messages & Roles
- ·Temperature & Max Tokens
- ·Streaming Responses
- ·Token Counting & Costs
- ·Models Overview
- ·Error Handling
- ·Rate Limits
Start Fundamentals →
IntermediateTopics 1–10
- ·Function Calling
- ·Structured Outputs
- ·Tool Use
- ·Vision & Image Inputs
- ·Embeddings API
- ·Batch API
- ·Fine-tuning Overview
- ·Prompt Engineering Patterns
- ·Conversation History Management
- ·System Prompt Design
Start Intermediate →
AdvancedTopics 1–10
- ·Assistants API
- ·Threads & Runs
- ·File Search (RAG)
- ·Code Interpreter
- ·DALL-E Image Generation
- ·Text-to-Speech & Whisper
- ·Reasoning Models (o1/o3)
- ·Fine-tuning in Depth
- ·Custom Functions at Scale
- ·Prompt Caching
Start Advanced →
ProductionTopics 1–10
- ·Cost Optimisation
- ·Latency Reduction
- ·Retry Logic & Backoff
- ·Secrets Management
- ·Rate Limit Handling
- ·Observability with LangSmith
- ·Caching Strategies
- ·Multi-Model Fallbacks
- ·Content Moderation
- ·Deployment Architecture
Start Production →