News for hackers. Stuff that matters.

pvpv

Show HN: Irpapers – Visual embeddings vs. OCR trade-offs in scientific PDFs

https://github.com/weaviate/query-agent-benchmarking

Hey HN, we are releasing IRPAPERS to answer a highly pragmatic question: when building a RAG pipeline over PDFs, should you OCR the text or just embed the raw page images?Processing PDFs in production usually involves stringing together brittle OCR heuristics. While recent multimodal embeddings (like ColModernVBERT or ColPali) allow you to skip OCR entirely and retrieve directly from visual...

( Read More... | no comments | on HN )
just to compare both fusion approaches we did some internal benchmarks testing recall on a standard (FIQA) dataset. According to our internal benchmarks, the relativeScoreFusion algorithm showed a ~6% improvement in recall over the default rankedFusion method.
Re:Elasticsearch: Most Downloaded Vector Database on Friday July 21, 2023 @12:49AM (#36810107)
what andre said haha srsly