Deterministic, not AI-guessed
The parser locates the SPIR layout by its printed labels and positions. It is always best to supply the source .xlsx file in the industry standard layout, as that gives the most reliable read.
SPIR spare parts record extraction
SPIR forms are the least spreadsheet-like spreadsheets in engineering: multiple tabs, merged headers, tag groups running across the columns and part line items running down the rows. AxioExtract reads them with a deterministic template parser rather than a vision model, so the same form gives the same result every time.
How the read works
Specific tabs only
Multi-tab workbooks are common — the data usually lives on one sheet such as “SPIR Data”. Only the relevant sheet is read, so supporting tabs, instructions and revision logs do not pollute the output. Source spreadsheets are required to ensure pages are picked up correctly.
Matrix to triples
The tag-versus-part matrix is flattened into (tag group, part, quantity) triples, which is the form that spreadsheets, ERPs and procurement systems can actually use.
PDF SPIRs
When the SPIR arrives as a PDF rather than a workbook, the grid is reconstructed from the page geometry — text positions and rule lines.
Tag register and bill of materials
A tag group covers several physical tags. “Generate tag register” explodes each group into its individual tags and can be downloaded as CSV. From there the BOM panel builds either a per-tag bill of materials — every tag with its parts and quantities — or a consolidated one that sums identical parts into a single procurement line. A dropdown filter shows the item count per tag so you can view the BOM for one tag at a time. More on BOM output is on extract a BOM from a PDF.
Scoring and blank cells
SPIR forms are legitimately sparse: most tag-versus-part intersections are empty because that tag does not take that part. Completeness scoring therefore counts only the columns a SPIR read must fill, and ignores non-required cells that are blank on the source, so a correctly read sparse form is not penalised.
Previewing the workbook
Spreadsheet and PDF SPIRs are shown in a built-in preview with a tab strip and sticky headers, so a selected row scrolls into view on the original sheet. Corrections are made in the grid before exporting to Excel, Google Sheets, JSON or XML.
From matrix to procurement lines
The output of a SPIR read is a set of (tag group, part, quantity) triples, and two things can be built from it immediately. A tag register explodes each tag group into its individual tags, so a group covering six identical valves becomes six rows. A bill of materials rolls the triples up either per tag or consolidated across the whole record, flagging missing part numbers, zero quantities and duplicate lines that were merged.
Every table carries the tab it came from, so a workbook with several SPIR sheets stays traceable after export. More on the BOM side is on extracting a BOM from a PDF.
Cost and file preparation
A SPIR read from its template is 4 credits per page. Supply the source .xlsx wherever possible: the workbook keeps its cell structure, so the read is deterministic and the same form gives the same answer every time. A PDF SPIR is reconstructed from page geometry instead, and if the layout cannot be resolved the sheet falls back to a vision read at the higher rate.
Common questions
What is a SPIR?
A Spare Parts and Interchangeability Record is a supplier form that lists tag groups across the columns and spare part line items down the rows, with quantities at each intersection. It is used to agree recommended spares for a package of equipment.
Can a SPIR be read without AI?
Yes. AxioExtract reads SPIR workbooks and SPIR PDFs deterministically, using label and position matching rather than a vision model, which makes repeat reads of the same template consistent.
Can a bill of materials be produced from a SPIR?
Yes. After review you can generate a tag register from the tag groups, then build a BOM in per-tag or consolidated view, filter it to a single tag, and export it.
Try it on your own document
Credits are included with every new workspace — no card required to start.
Start extracting