18 AI engineering concepts, from RAG variants to LoRA/QLoRA, mapped to open-source repos
MaryamMiradi · x · 2026-10-18
Maryam Miradi breaks down 18 commonly confused AI engineering concepts across five categories, each with a matching open-source project:
- Knowledge & databases: vector DB (Milvus), graph DB (Neo4j), ontology (OWL API), knowledge graph (RDFLib).
- Search & ranking: vector search (FAISS), hybrid search (OpenSearch), embeddings (Sentence Transformers), rerankers (FlagEmbedding).
- RAG & retrieval: RAG (RAGFlow), Agentic RAG (LangGraph), GraphRAG, Long Context, CAG (cached knowledge instead of repeated retrieval).
- Training & adaptation: full fine-tuning (Transformers), LoRA (PEFT), QLoRA.
- Optimization: quantization (llama.cpp), knowledge distillation (EasyDistill).
Key point: these combine freely in one system — e.g. hybrid search + reranking + GraphRAG + agentic retrieval, or LoRA fine-tuning followed by quantization. Pick architecture based on data, task, latency and cost constraints.
More from coding & agent
- Dev builds ChatGPT plugin that has his Dot monitor news hourly and alert him — koltregaskes · 2026-10-18
- Optimus launches: an autonomous RL agent harness that runs experiments itself — _AustinCalvert_ · 2026-10-18
- Work IQ MCP in GitHub Copilot cuts hours of manual issue tracking to under 30 minutes — DanWahlin · 2026-10-18
- Working with AI: sort your work by AI-verifiability, then design verifiers or be the judge — danshipper · 2026-10-18
- Personal agents vs. websites that block them: real-phone computer use may win — lucasmeijer · 2026-10-18
- LSCBench: top AI coding agent passes 91.3% of tests but only 25.1% ship securely — krishnan · 2026-10-18