Automated API CSV parsing for SAP ERP intelligence
Automated API CSV parsing for SAP ERP intelligence converts each CSV export attached to a record into searchable passages, so the assistant answers from the file rather than from fields someone typed.
How does automated API CSV parsing feed SAP ERP intelligence?
Automated API CSV parsing for SAP ERP intelligence converts each attached CSV export into passages when the file is saved, so the assistant can cite the file instead of guessing from record fields.
Where the CSV export sits in SAP
SAP keeps the file on the business object through Generic Object Services or ArchiveLink, beside the order, invoice, or vendor. The typed fields on that record are already searchable. The CSV export is not, until automated API CSV 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 CSV actually yields
A CSV row of bare values retrieves for nothing, because the words a person would search for live in the header. The parser writes each cell as header: value and emits blocks of about two hundred rows, so a long export is cut on row boundaries instead of through the middle of a record. A header-only file is still indexed: it says what the export was about.
The API call that feeds SAP
An integration flow or an attachment event can POST those bytes when the document is linked. The response is JSONL, one passage per line, with the record id in metadata for the retrieval store beside SAP. Asking a model to reread the CSV export inside chat for every question never builds that index. Automated API CSV 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 CSV export 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 CSV.