Backend
API design, caching, and the server-side patterns that keep services fast and correct under load. Ordered from foundational to advanced, 14 docs in this category.
Docs in Backend
LLM Fundamentals: Tokens, Context Windows & Sampling
Why a token isn't a word, what actually happens when a request would exceed the context window, and what temperature and top_p each control during generation.
Python Data Structures
When to reach for a list, tuple, dict, or set based on what operations you actually need fast, and why choosing the wrong one is a common hidden performance bug.
Python Syntax Fundamentals
How Python's significant whitespace, dynamic typing, and object model shape idiomatic code, and the mutable-default-argument trap that catches almost everyone once.
Python Virtual Environments & Packaging
Why every Python project needs an isolated environment, what a lockfile actually pins down that a requirements list doesn't, and how to avoid the global-install dependency trap.
Embeddings & Vector Search
How embeddings turn text into vectors that cosine similarity can compare mathematically, why shortening an embedding's dimensions trades some accuracy for real storage and speed savings, and when semantic search actually beats keyword search.
LLM Evaluation & Reducing Hallucinations
Why "it feels better" isn't a shippable justification for a prompt change, what an LLM-graded eval actually measures, and why explicitly allowing "I don't know" is one of the most effective, cheapest hallucination fixes available.
Prompt Engineering
Why a role set in the system prompt shapes every response differently than the same instruction in a user message, and why 3-5 well-chosen examples reliably steer output format better than more instructions alone.
Python Web Frameworks Overview
How Flask, Django, and FastAPI trade minimalism, batteries-included structure, and async-first design differently, and how to actually choose based on project shape.
Redis Caching Patterns
Cache-aside, write-through, and write-behind explained, plus the TTL, stampede, and invalidation pitfalls that show up once Redis caching hits real traffic.
REST vs GraphQL
The real trade-offs between REST and GraphQL, over/under-fetching, caching, versioning, and when each one is the better default for an API.
Retrieval-Augmented Generation (RAG)
Why a document chunk embedded in isolation loses the context that made it meaningful, and how prepending explanatory context to each chunk before embedding measurably cut retrieval failures in Anthropic's own published results.
Testing Python with pytest
How pytest's fixture system and plain-assert philosophy replace unittest's boilerplate, and why fixture scope is the setting most likely to cause confusing test failures.
Python Async Programming
How asyncio's single-threaded event loop achieves concurrency without threads, why blocking calls silently defeat it, and when async actually helps versus when it's pure overhead.
Tool Use & Agents
How a tool call actually completes as a round trip, a tool_use block your code executes and a tool_result you send back, and why every tool definition you provide adds real tokens to every request whether or not it's ever called.