From 7241b91c4814478a81103b4c7a6c2c294092f36a Mon Sep 17 00:00:00 2001 From: S Jannette Date: Fri, 8 May 2026 03:53:43 -0400 Subject: [PATCH] Refine README for clarity and consistency --- README.md | 16 ++++------------ 1 file changed, 4 insertions(+), 12 deletions(-) diff --git a/README.md b/README.md index dee45e0..e1321a8 100644 --- a/README.md +++ b/README.md @@ -31,27 +31,19 @@ make dev ## Rationale -NotebookLM is a powerful research tool, but it is proprietary and closed. -This clone demonstrates the core source-grounded Q&A pattern with transparent -retrieval, generation, and groundedness scoring (LLM response quality cosine scoring) -- all with swappable models/fully open source. +This app demonstrates the core source-grounded Q&A pattern with transparent retrieval, generation, and groundedness scoring (LLM response quality cosine scoring) -- all with swappable models and is fully open source. ## Design Two-package monorepo: -- `server/` -- single Express backend with layered architecture - (routes -> services -> stores). Routes orchestrate; services contain - business logic; stores manage in-memory state. +- `server/` -- single Express backend with layered architecture (routes -> services -> stores). Routes orchestrate; services contain business logic; stores manage in-memory state. -- `client/` -- React 19 SPA via Vite. Two-panel layout: sidebar for - notebooks/data sources, main area for LLM chat with explorable citations, - groundedness badges (cosine similarity scoring of LLM responses), and follow-up question chips. +- `client/` -- React 19 SPA via Vite. Two-panel layout: sidebar for notebooks/data sources, main area for LLM chat with explorable citations, groundedness badges (cosine similarity scoring of LLM responses), and follow-up question chips. ## Query pipeline -Embed query (Voyage) -> k-NN search -> rerank (Voyage) -> -generate answer with citations (Claude) -> compute groundedness score -(cosine similarity of answer vs cited chunks). +Source Ingestion -> Parsing -> Chunking -> Embedding -> Storage (vector store) -> { user query submission } -> evaluation of user query → Retrieval -> Ranking -> Response Generation -> Response Groundedness Scoring ## License