DiskANN

A silver coin embossed with a detailed V-engine and the word RAGE across its lower rim.

RAGE, Three Years On: The Engine Was the Right Word

RAGE said generation should stand on retrieved evidence. Three years on, I run that way, with pgvector and DiskANN, and two of its promises are still open.

Learn More
RAGE ingest verification: 197 equals 197 carved on a slab under a green and violet aurora, captioned the count agrees with itself — the predicted chunk count matching the delivered chunk count exactly

197 chunks, zero reconnects: what happened when I actually ran the ingest

RAGE ingest results: 41 documents, 197 chunks, zero reconnects — and the two tunnel failures that taught more than the success did.

Learn More
RAGE, the Retrieval Augmented Generative Engine: structured databases, unstructured documents, APIs and live web content feeding a turbine that outputs real-time insight, generative reports, predictive forecasts and strategic decisions

What it costs to remember: the RAGE ingestion path, and a map of the whole project

How RAGE ingests a corpus into pgvectorscale: 515s down to 0.49s on re-ingest, DiskANN over 48,800 bge-m3 chunks, and a map of the whole RAGE project.

Learn More