Molecular PDF parser Rule-based extraction · No LLM · No OCR

Extract a Molecular report to JSON

Upload one PDF, pick a file from the source folder, or parse every PDF under a folder path. Text is extracted with layout rules — images and graphs are skipped.

Upload a PDF

Use this for a one-off report on your machine.

Parse from source folder

/data/source

Parse all PDFs in a folder

Recursive: every .pdf in this folder and its subfolders. Unchanged successful files are skipped unless you re-extract. Failures go to quarantine.

Preview parsed JSON

Open any extracted file in tree view or raw JSON. Path: /data/output

FileStatus
29381_Lung COE NGS only Panel(Saarthi)_dc889a4d.json PASSED Preview
29379_ALL COMPREHENSIVE NGS PANEL (550 GENES TMB MSI)_50185b8f.json PASSED Preview
29389_Lung COE NGS only Panel(Saarthi)_6f36c914.json PASSED Preview
29388_Lung COE NGS only Panel(Saarthi)_553cf95e.json PASSED Preview
29387_CLINICAL EXOME SEQUENCING_438456ce.json PASSED Preview
29385_TranSeq ALL NGS_66b33913.json PASSED Preview
29384_TranSeq ALL NGS_5e564069.json PASSED Preview
29383_COMPREHENSIVE MYELOID PANEL NGS(AML,MDS,MPN,CML,CMML & JMML)_f01292d2.json PASSED Preview
29380_NGS Expanded Panel for Solid Tumor Tissue_58e25acb.json PASSED Preview
29382_EGFR RT PCR, LUNG NGS PANEL, ALK BY IHC (SMART LUNG PANEL)_945c598b.json PASSED Preview