← All categories

AI Engineering

RAG pipelines, vector databases, embeddings, LangChain, LlamaIndex, AI agents, function calling, structured output, prompt caching, streaming, context management, hybrid search, re-ranking, evaluation, guardrails, observability, multi-agent systems, and cost optimization.

AI Engineering

What is RAG and why use it?

What are embeddings?

Chunking strategies for RAG

Similarity search: cosine vs dot product vs HNSW

Vector database trade-offs

Streaming LLM responses

LangChain basics

Function calling / tool use

Structured output with Pydantic + instructor

Prompt caching (Anthropic & OpenAI)

Context window management

Hybrid search (keyword + semantic)

Re-ranking with cross-encoders

AI agents and the ReAct pattern

LlamaIndex basics

Evaluating RAG pipelines with ragas

Multi-agent systems

LLM observability with LangSmith and Langfuse

Guardrails and content filtering

Anthropic Claude API: extended thinking, prompt caching, tool use

LLM cost optimization strategies

Advanced RAG patterns: HyDE, query expansion, self-query