RCRAG Converter

Does better OCR actually improve RAG retrieval?

Better OCR improves RAG only up to a point: once the characters are mostly right, retrieval quality is decided by reading order and page structure, and a high-accuracy engine that returns text in the wrong order still retrieves badly.

Character accuracy is the wrong headline number

OCR engines are compared on character or word error rate, which measures whether the letters are right. Retrieval does not care about individual letters; it cares whether a passage means what it appears to mean. An engine that reads every character correctly but returns a two-column page as interleaved lines produces passages that are locally perfect and globally wrong.

What actually breaks retrieval

Three things, in order of damage: reading order, because it decides which sentences end up in the same chunk; table structure, because a number separated from its heading is unrankable; and page furniture - headers, page numbers, watermarks - which repeats across every chunk and dilutes the vectors. None of these show up in a character error rate.

Blank pages are worse than failed pages

The dangerous outcome is an image that produces almost no text but is indexed anyway, because the resulting passages are nearly identical to one another. They then crowd real answers out of results. Building RAG Converter we found two unrelated images sharing about ninety percent of their chunk text, all of it boilerplate. The fix was to skip them and say so, rather than index a placeholder.

Resolution past the model's working size buys nothing

Detection models operate at a fixed working resolution and gain no accuracy from being handed more pixels. Measured on a page of rendered text, running at a native 1258 by 846 against the detector's own 736-pixel short side produced word-for-word identical output - the whole difference across the page was two full stops - and the smaller input was faster. A 12-megapixel phone photo is not fifteen times more readable; it is fifteen times more expensive.

Test on retrieval, not on transcription

The only benchmark that answers the question is your own: convert a sample, ask the questions you actually care about, and check whether the right passage comes back. An engine that wins on a transcription benchmark can lose on your corpus, and you will not find that out from anyone's accuracy table.

More on converting for RAG

  • rusty_ragdocument ingest, chunking and retrieval
  • rusty_xmlWord, PowerPoint and Excel, without LibreOffice
  • rusty_jpeg / rusty_pngimage decode
  • rusty_flacaudio decode
  • rusty_zstdcompression
  • rusty_allocthe allocator, in wasm too
  • rusty_timeNTP timestamps on every chunk
  • spacedbthe storage seam, CRDT per entry
  • FFAIthe AI toolkit the three engines below come from
  • CarmentaOCR - reads scans and screenshots, in your browser
  • Mercuryspeech recognition - turns recordings into transcripts
  • Argusvision - describes images and video frames

MATA Corporate Holdings © 2026 — Made in Scottsdale, Arizona

Remade with Rust