⚠️ Ephemeral demo: Uploaded documents are stored in server memory only — wiped on restart. Do NOT upload personal, confidential, or sensitive documents. The 5 demo documents below are pre-loaded and permanent.

GraphQ

Zero-chunking document search — no neural networks, no embedding APIs, no vector databases.

📄
Documents
🕸️
NPMI Graph
🧬
GEE Embedding
LIDER Index
🔍
Sub-ms Search

Raw text in, ranked results out. Three compute-only stages on commodity hardware.

⏳ Checking...
1

NPMI Normalized Pointwise Mutual Information

NPMI(i,j) = ln(P(i,j)/P(i)P(j)) / −ln(P(i,j))

Converts raw word co-occurrence into meaningful edge weights. Suppresses hub words ("the", "is"), amplifies rare but meaningful pairs.

vocab: — edges: —
2

GEE Graph Encoder Embedding

Z = Dα · A · Y

Model-free graph embedding. One matrix multiply — no eigen-decomposition, no gradient descent, no training.

dims: — α: 0.5
3

LIDER Learned Index for Dense Retrieval

predict(position) → local binary search

Replaces ANN tree traversal with a learned model that predicts where each match lives. Sub-millisecond at billion scale.

bins: — vectors: —
Try:
🔬 Pipeline Trace Step-by-step execution for this query
🔍

5 demo documents pre-loaded and indexed

Graph Theory · Machine Learning · Search Engines · NLP · Network Science

Try a suggested query above or type your own.

📄 Upload your own PDF (ephemeral — wiped on restart)

Drop a PDF here or browse

Max 20MB · replaces demo index until server restart
🕸️ Co-occurrence Graph D3 force-directed network of word relationships
Nodes = vocabulary words (sized by frequency) Edges = NPMI weight (thicker = stronger co-occurrence) Click a node to see its nearest neighbors