Repository Issue Activity (beta)

#173 Finetuning for layout detection

#536 [Bug: Breaking] `AttributeError: 'PdfDocument' object has no attribute 'render'` in Streamlit app

#555 Nothing happens when I start OCR

#554 [BUG: Breaking] SpawnError: docker run failed: docker: Error response from daemon: unknown or invalid runtime name: nvidia

#540 RecognitionPredictor deterministically outputs Cyrillic/Armenian homoglyphs for specific short German text lines (llamacpp backend)

#544 [BUG: Output] Text inside Diagram/Figure regions is never OCR'd — full_page returns an empty skipped block (detection+recognition reads it fine)

#551 Full-page OCR narrates a table as a <p> caption instead of transcribing it — every figure is lost (surya-ocr-2)

#549 [FEAT] Support podman

#480 Update Pillow version constraint to support Python 3.14

#547 vLLM container is published on all interfaces (-p {port}:8000 ignores SURYA_INFERENCE_HOST)

#543 [BUG: Breaking] vLLM EngineCore crashes with SIGSEGV (`realloc(): invalid pointer` / `EngineCore: -11`) during startup when loading `datalab-to/surya-ocr-2`

#542 [BUG: Breaking] Inference error with llama.cpp backend: failed to parse grammar due to \d escape in bbox schema

#541 How to reproduce the 83.3% olmOCR-bench score? What are the "adjustments applied to account for our output HTML format"?

#538 Verify evals on Papers with Code

#523 [BUG: Breaking] Parallel inference not working on llama.cpp backend.

#531 [BUG: Breaking] Import Error

#522 Kubernetes deployment: the current vllm backend asks for starting new docker container, problem in cloud deployment

#521 [FEAT] When will the Dhivehi language (Thana Script) be available for Surya OCR?

#513 ss

#518 [BUG: Path Traversal] Unauthenticated arbitrary file read via file_path in the surya screenshot server

#517 [BUG: Breaking]

#514 Add-in for Outlook/Gmail

#515 Build self-serve trial entry path

#516 Redesign/rebuild the testimonials section

#511 No progress indication for full-page OCR (surya_ocr)