Organize
Batch document sets are sorted into usable research collections before deeper processing begins.
BDS Platform
Batch Document Search
A local, private document-intelligence system that organizes complex files, indexes them for hybrid search, extracts entities, and builds an Obsidian-compatible knowledge graph.
The Pipeline
Four phases, from raw files to a knowledge graph.
BDS moves a document set through four stages — and each one is usable before the next completes.
Index
After Phase 2, hybrid BM25 and semantic search become available for immediate review.
Extract Entities
Phase 3a identifies people, organizations, events, and key terms for structured research review.
Build Knowledge Graphs
Phase 3b expands entity cards, relationships, and Obsidian-compatible graph exploration.
How To Read Results
Search signals, not magic scores.
These are the education cards that will become Lucy Lu-guided animation overlays.
| Signal | Plain-English meaning | Animation use |
|---|---|---|
| both | Meaning-match and word-match agree. This is the strongest relevance signal. | Pulse green. “Two independent methods agreed.” |
| vector | Meaning-match. The text reads like the question even when different words are used. | Blue highlight. “Same idea, different words.” |
| bm25 | Word-match. It shares query words but may not actually answer the question. | Amber caution. “Read the snippet before trusting it.” |
| CORPUS_GAP | The documents may not contain strong evidence for the question. | Orange/red banner. “Empty-handed is a finding.” |
Local demo capture: extraction/search workflow, result rows, hover tooltips, and interpretation signals.
Animation Pilot
First clip: “How your library gets built.”
The first production target should be a short hybrid clip combining real GUI capture, retro-lab overlays, and Dr. Lucy Lu as a calm scientific guide.
0–5s
The lab wakes up
Console lights, BDS board, Lucy Lu observing.
5–16s
Drop documents → organize
Boeing/NTSB/SEC sample enters the pipeline.
16–25s
Index → search ready
Hybrid retrieval becomes operational after Phase 2.
25–40s
Entities → graph → evidence
Entity cards and knowledge graph bloom; source verification closes the loop.
Guided Interpretation
Lucy Lu appears where explanation matters.
Dr. Lucy Lu will guide selected BDS learning moments — result signals, corpus gaps, RAG diagnostics, and source verification — without getting in the way of the working application.
Principle
BDS tells you where to look — not what to conclude. Lucy Lu’s role is to reinforce that discipline through short, clear teaching moments.