How to extract GST invoices

Dynamite Docs, 2026-08-19

Scope and tax review

Reviewed by: Rajesh Sharma, FCA · Indirect Tax Practice. Last verified: 2026-08-19.

Dynamite Docs extracts fields from source documents. It does not determine whether an invoice complies with GST law, prepare a return, or make a document ready to file. Review every extracted value against the original and use the current GST Portal guidance or a qualified tax professional before filing.

We publish the controls we actually operate rather than claiming certifications we do not yet hold.

Official GST sources

CGST Rules: tax invoice particulars (Rule 46), Central Board of Indirect Taxes and Customs. Mandatory 16 invoice particulars and tax invoice format requirements.
Notification 78/2020: HSN reporting requirements, Central Board of Indirect Taxes and Customs. Turnover-based 4-digit and 6-digit HSN/SAC reporting rules on B2B invoices.
GSTIN structure and registration rules, GST Portal. 15-character state-PAN-entity format and registration validation.
Integrated Goods and Services Tax Act: Section 7 & 8, Central Board of Indirect Taxes and Customs. Determination of intra-state (CGST/SGST) vs inter-state (IGST) supplies.

Define the GST invoice fields before you start

A useful extraction schema separates supplier and recipient details, invoice details, item rows, tax amounts, and totals. At minimum, capture the invoice number and date, supplier GSTIN, recipient GSTIN when present, place of supply, taxable value, and the printed CGST, SGST, or IGST amounts.

For item-level work, add description, HSN or SAC code, quantity, rate, taxable value, tax rate, and line total. Keep fields blank when the invoice does not show them. Extraction should record the source, not fill gaps with guesses.

Read digital invoices and scans differently

A PDF exported from billing software often has selectable text. Read that text layer first. A scan or phone photo needs OCR, and small characters in GSTINs or HSN codes deserve extra review.

Rotate sideways pages, remove dark borders, and check that the full invoice is visible. A cropped footer can remove the tax summary or grand total even when every item row looks clear.

Keep invoice-level and item-level tax separate

Do not repeat a summary tax amount as though it belongs to each item. Capture printed line tax at the line level and printed tax summaries at the invoice level. This avoids double counting when the spreadsheet is grouped or summed.

Preserve CGST, SGST, and IGST in separate columns. If the source only prints a combined tax amount, keep it as printed and send the row for review instead of manufacturing a split.

Check identifiers and invoice math

Compare extracted GSTINs character by character with the invoice. Then check that item taxable values roll up to the printed taxable subtotal and that the extracted tax amounts and adjustments reconcile with the printed invoice total.

A math check finds extraction differences. It does not decide whether the tax treatment or credit claim is correct.

Prepare clean rows for accounting review

Use one invoice record for header and summary values, plus one linked row for each item. Include a source filename or document ID so a reviewer can return to the invoice quickly. Export only after flagged fields and reconciliation differences have been resolved.

Process GST invoices in Dynamite Docs

Upload the invoices, review the inferred GST fields in Data Studio, and correct any uncertain GSTIN, HSN or SAC, taxable value, or tax amount. Then export the approved table to Excel or CSV for bookkeeping and Chartered Accountant review.

Dynamite Docs prepares document data. It does not determine GST compliance, input tax credit eligibility, or filing treatment. Check the current GST Portal guidance and use a qualified tax professional before filing.

Related workflow: GST invoice OCR and extraction to Excel.

Keep reading

Try it yourself. Upload a PDF, scan, or image and let Dynamite Docs infer the schema.