NLP / llms

LLMs, RAG, agents, and evals

Pretraining, fine-tuning, SFT, RLHF, DPO, LoRA, quantization, RAG, vector databases, reranking, tool use, agents, safety, and evals.

shellbackend needed later
Focus
  • RAG pipeline
  • fine-tuning vs prompting
  • reranking
  • LLM evals
Future feature idea

RAG pipeline workbench with chunking, embeddings, reranking, hallucination tests, and cost/latency tradeoffs.

Self-check
  1. What is the core job of "LLMs, RAG, agents, and evals"?
  2. Which common mistake would break a production implementation of this topic?
  3. Which inputs or limits must be validated before the interactive feature ships?
  4. What is the smallest test that proves the future implementation behaves correctly?
  5. When does this module really need backend compute, and when is a UI simulation enough?
Implementation notes
  • Start with one focused feature, not a full course inside one page.
  • All public inputs must be typed, bounded, and covered by reject-case tests.
  • If a model, dataset, or job is added, document source, license, limits, and fallback.
  • The interaction must explain the topic rather than serve as decoration.