Intermediate Vocabulary #ai #llm #machine-learning #rag

AI & LLM Vocabulary

5 exercises — the vocabulary every developer working with AI needs in English: RAG architecture, hallucination, AI agents, model quantisation, and prompting techniques.

Core AI & LLM vocabulary clusters
  • Architecture: LLM, transformer, embedding, vector database, RAG, fine-tuning, context window, tokens
  • Quality issues: hallucination, grounding, factuality, alignment, RLHF, Constitutional AI
  • Agents: tool use, function calling, ReAct, planning, orchestration, LangChain, AutoGen
  • Deployment: inference, latency, throughput, VRAM, quantisation (INT4/INT8), GGUF, bitsandbytes
  • Prompting: zero-shot, few-shot, chain-of-thought, system prompt, temperature, top-p
  • Evaluation: benchmark, MMLU, HumanEval, BLEU, ROUGE, perplexity, evals
0 / 5 completed
1 / 5
An ML engineer explains their system:
"Instead of searching the entire document database for every query, we first convert documents to vectors using an embedding model and store them in a vector database. At query time, we embed the question and retrieve the k nearest neighbours — semantically similar documents — then pass them as context to the LLM."
What architecture is described here?