Automated API image parsing for NetSuite ERP intelligence
Automated API image parsing for NetSuite ERP intelligence converts each image attached to a record into searchable passages, so the assistant answers from the file rather than from fields someone typed.
How does automated API image parsing feed NetSuite ERP intelligence?
Automated API image parsing for NetSuite ERP intelligence converts each attached image into passages when the file is saved, so the assistant can cite the file instead of guessing from record fields.
Where the image 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 image is not, until automated API image 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 an image actually yields
JPEG, PNG, GIF, WebP, BMP, and TIFF are pixels. The parser decodes the bitmap and records its size. It does not invent a text layer. Words come from OCR, and a description comes from the vision model only when that engine is on. If those engines produce nothing, the file is skipped rather than indexed as a blank placeholder that crowds real passages out of search.
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 image inside chat for every question never builds that index. Automated API image 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 image 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 images.