AI Backend Glossary
Clear definitions for every term you'll encounter building production AI APIs with FastAPI.
Alembic Migrations
Database schema version control for SQLAlchemy models.
API Key Management
Issuing, tracking, and revoking scoped API keys for programmatic access.
Async FastAPI
Building high-concurrency Python APIs with FastAPI and asyncio.
Celery Worker
A Python background task processor for long-running async jobs.
Docker Compose
A tool for defining and running multi-container Docker applications locally.
Embeddings
Numerical vector representations of text for semantic similarity search.
FastAPI Dependency Injection
FastAPI's built-in system for sharing reusable logic across route handlers.
JWT Authentication
Stateless authentication using signed JSON tokens.
Large Language Model (LLM)
A neural network trained on large text corpora that generates human-like text.
pgvector
A PostgreSQL extension that adds vector similarity search.
Production FastAPI
What it takes to run FastAPI reliably in production at scale.
Pydantic Validation
Python's type-safe data validation and serialization library.
Rate Limiting
Enforcing per-client request quotas to prevent abuse and manage costs.
Retrieval-Augmented Generation (RAG)
Grounding LLM responses in retrieved documents from a vector store.
Server-Sent Events (SSE)
A lightweight protocol for streaming data from server to browser over HTTP.
SQLAlchemy Async
Async database access in Python using SQLAlchemy 2.0's native async API.
SSE vs WebSockets
Choosing between Server-Sent Events and WebSockets for real-time AI streams.
Token Tracking
Counting LLM input and output tokens per request for cost and billing visibility.
Usage Metering
Tracking per-customer API consumption for usage-based billing.
Vector Database
A database optimized for storing and searching high-dimensional embedding vectors.