Automated API PDF parsing for NetSuite ERP intelligence
Automated API PDF parsing for NetSuite ERP intelligence converts each PDF attached to a record into searchable passages, so the assistant answers from the file rather than from fields someone typed.
How does automated API PDF parsing feed NetSuite ERP intelligence?
Automated API PDF parsing for NetSuite ERP intelligence converts each attached PDF into passages when the file is saved, so the assistant can cite the file instead of guessing from record fields.
Where the PDF sits in NetSuite
NetSuite keeps the file in the File Cabinet and links it to the transaction, vendor, or item. The typed fields on that record are already searchable. The PDF is not, until automated API PDF parsing copies its words into passages keyed to the same record. ERP intelligence that only reads the fields is intelligence about what a person typed, not about what the file says.
What a PDF actually yields
A PDF with a text layer stores words as text, and that layer becomes passages. A scanned PDF stores a photograph of the page, so the same extension yields nothing until OCR runs. Two-column contracts and footnotes can extract out of reading order, which is why a sample of the JSONL should be read before a whole library is indexed.
The API call that feeds NetSuite
A SuiteScript user event or a scheduled script can POST those bytes when the file is attached. The response is JSONL, one passage per line, with the record id in metadata for the retrieval store beside NetSuite. Asking a model to reread the PDF inside chat for every question never builds that index. Automated API PDF parsing runs when the file is saved, once, and later questions retrieve.
What the answer is allowed to cite
After a clean parse, an answer should cite the passage and the PDF it came from. A file that yields no text is a skip, named as a skip, not a blank passage that crowds real hits. The parsers are Remade with Rust crates, and RAG Converter is part of MATA. The longer note on this format is RAG for PDF.