repoGitLabTrust 82 · PrimaryPublished 6d agoLive · 6d ago
lemarco/rag-from-scratch
Demystify RAG by building it from scratch. Local LLMs, no black boxes - real understanding of embeddings, vector search, retrieval, and context-augmented generation.
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 51%Cutting RAG inference costs 6x starts with deciding what never reaches the LLM →
- PossiblePossibly related (embedding) · 51%Loop Engineering for RAG Generation: iterate top-k one at a time - Towards Data Science →
- PossiblePossibly related (embedding) · 50%We’ve got a workshop on production retrieval-augmented generation with open models, benchmarked end to end, thought it’d be relevant here [D] →
- PossiblePossibly related (embedding) · 50%Domain-tailored RAG framework improves industrial LLM question answering in new engineering study - EurekAlert! →
Covers
newsCutting RAG inference costs 6x starts with deciding what never reaches the LLMnewsLoop Engineering for RAG Generation: iterate top-k one at a time - Towards Data SciencenewsWe’ve got a workshop on production retrieval-augmented generation with open models, benchmarked end to end, thought it’d be relevant here [D]newsDomain-tailored RAG framework improves industrial LLM question answering in new engineering study - EurekAlert!
Related across the graph
newsWe’ve got a workshop on production retrieval-augmented generation with open models, benchmarked end to end, thought it’d be relevant here [D]newsCutting RAG inference costs 6x starts with deciding what never reaches the LLMnewsDomain-tailored RAG framework improves industrial LLM question answering in new engineering study - EurekAlert!newsLoop Engineering for RAG Generation: iterate top-k one at a time - Towards Data Science