Receipt scanning

Nodes used: Parse, Extract This example reads a receipt photo or scan and returns the merchant, the totals, the item count and how the purchase was paid. An enum field pins the payment method to a fixed set of names, and a boolean flags alcohol for expense policies.

The workflow

{
  "name": "Receipt scanning",
  "description": "Extract receipt details from photos and scans",
  "nodes": [
    { "id": "parse_1", "type": "parse" },
    {
      "id": "extract_1",
      "type": "extract",
      "extraction_schema": {
        "fields": [
          { "name": "store_name",      "description": "Name of the store or merchant", "data_type": "string" },
          { "name": "store_address",   "description": "Full address of the store location", "data_type": "string" },
          { "name": "receipt_date",    "description": "Date of the purchase transaction", "data_type": "date" },
          { "name": "total_amount",    "description": "Total amount charged including tax", "data_type": "float" },
          { "name": "tax_amount",      "description": "Total tax amount", "data_type": "float" },
          { "name": "number_of_items", "description": "Total number of items purchased", "data_type": "integer" },
          {
            "name": "payment_method",
            "description": "Payment method used for the transaction",
            "data_type": "enum",
            "enum_options": [
              { "name": "cash",           "description": "Cash payment" },
              { "name": "credit_card",    "description": "Credit card payment" },
              { "name": "debit_card",     "description": "Debit card payment" },
              { "name": "mobile_payment", "description": "Mobile or digital wallet payment" }
            ]
          },
          { "name": "contains_alcohol", "description": "Whether any alcoholic beverage was included in the purchase", "data_type": "boolean" }
        ]
      }
    }
  ],
  "edges": [{ "source": "parse_1", "target": "extract_1" }]
}

import os
from anyformat.sdk import Client
from anyformat.workflow import Schema

client = Client(api_key=os.environ["ANYFORMAT_API_KEY"])

workflow = (
    client.workflow("Receipt scanning", "Extract receipt details from photos and scans")
    .parse()
    .extract([
        Schema.string("store_name",       "Name of the store or merchant"),
        Schema.string("store_address",    "Full address of the store location"),
        Schema.date("receipt_date",       "Date of the purchase transaction"),
        Schema.float("total_amount",      "Total amount charged including tax"),
        Schema.float("tax_amount",        "Total tax amount"),
        Schema.integer("number_of_items", "Total number of items purchased"),
        Schema.enum("payment_method", "Payment method used for the transaction", options=[
            Schema.option("cash",           "Cash payment"),
            Schema.option("credit_card",    "Credit card payment"),
            Schema.option("debit_card",     "Debit card payment"),
            Schema.option("mobile_payment", "Mobile or digital wallet payment"),
        ]),
        Schema.boolean("contains_alcohol", "Whether any alcoholic beverage was included in the purchase"),
    ])
    .create()
)

import { Anyformat, Schema } from "@anyformat/sdk";

const af = new Anyformat({ apiKey: process.env.ANYFORMAT_API_KEY! });

const workflow = await af
  .workflow("Receipt scanning", "Extract receipt details from photos and scans")
  .parse()
  .extract([
    Schema.string("store_name",       "Name of the store or merchant"),
    Schema.string("store_address",    "Full address of the store location"),
    Schema.date("receipt_date",       "Date of the purchase transaction"),
    Schema.float("total_amount",      "Total amount charged including tax"),
    Schema.float("tax_amount",        "Total tax amount"),
    Schema.integer("number_of_items", "Total number of items purchased"),
    Schema.enum("payment_method", "Payment method used for the transaction", [
      Schema.option("cash",           "Cash payment"),
      Schema.option("credit_card",    "Credit card payment"),
      Schema.option("debit_card",     "Debit card payment"),
      Schema.option("mobile_payment", "Mobile or digital wallet payment"),
    ]),
    Schema.boolean("contains_alcohol", "Whether any alcoholic beverage was included in the purchase"),
  ])
  .create();

Run it and read the result

Send the photo as the files field. JPG, PNG and PDF all work. Poll the run until its status is processed.

# 1. Create the workflow with the JSON above
curl -X POST 'https://api.anyformat.ai/v3/workflows/' \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY" \
  -H 'Content-Type: application/json' \
  -d @receipt-workflow.json
# → 201 { "id": "<workflow_id>", ... }

# 2. Upload the receipt photo and start a run
curl -X POST "https://api.anyformat.ai/v3/workflows/$WORKFLOW_ID/upload/run/" \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY" \
  -F 'files=@receipt.jpg'
# → 202 { "run_id": "<run_id>", "document_packet_id": "...", "status": "queued" }

# 3. Poll until "status" is "processed"
curl "https://api.anyformat.ai/v3/runs/$RUN_ID/" \
  -H "Authorization: Bearer $ANYFORMAT_API_KEY"

result = workflow.run("receipt.jpg").wait()

print(result.fields["store_name"].value)
print(result.fields["total_amount"].value)
print(result.fields["payment_method"].value)
print(result.fields["contains_alcohol"].value)

import type { ExtractedField } from "@anyformat/sdk";

const file = new File([readFileSync("receipt.jpg")], "receipt.jpg", { type: "image/jpeg" });
const result = await (await workflow.run(file)).wait();

console.log((result.field("store_name") as ExtractedField<string> | undefined)?.value);
console.log((result.field("total_amount") as ExtractedField<string> | undefined)?.value);
console.log((result.field("payment_method") as ExtractedField<string> | undefined)?.value);
console.log((result.field("contains_alcohol") as ExtractedField<string> | undefined)?.value);  // "True" or "False"

Response

The results envelope of a processed run, trimmed. Every value is a string on the wire, including booleans ("True" / "False") and numbers. A field the model could not find comes back with value: null and confidence: null, as tax_amount does on this receipt.

{
  "status": "processed",
  "results": {
    "parse": { "markdown": "...", "parse_confidence": 96.0, "blocks": [] },
    "extractions": [
      {
        "split_name": null,
        "partition": null,
        "fields": {
          "store_name": {
            "value": "Corner Grocery",
            "confidence": 97.0,
            "evidence": [{ "text": "CORNER GROCERY", "page_number": 1 }],
            "verification_status": "not_verified",
            "value_override": null
          },
          "total_amount": {
            "value": "23.45",
            "confidence": 98.0,
            "evidence": [{ "text": "TOTAL 23.45", "page_number": 1 }],
            "verification_status": "not_verified",
            "value_override": null
          },
          "tax_amount": {
            "value": null,
            "confidence": null,
            "evidence": [],
            "verification_status": "not_verified",
            "value_override": null
          },
          "payment_method": {
            "value": "credit_card",
            "confidence": 95.0,
            "evidence": [{ "text": "VISA ****1234", "page_number": 1 }],
            "verification_status": "not_verified",
            "value_override": null
          },
          "contains_alcohol": {
            "value": "False",
            "confidence": 92.0,
            "evidence": [],
            "verification_status": "not_verified",
            "value_override": null
          }
        }
      }
    ]
  }
}

Tips

Good lighting and a flat surface make a large difference to a receipt photo. A crumpled or shadowed receipt lowers parse_confidence.
Prefer PNG over a heavily compressed JPG when you control the capture.
An enum with explicit options stops free-text variations such as “Visa”, “credit card” and “CC”. The value is always one of your option names.
A boolean arrives as the string "True" or "False". Compare against the string, or cast it, before you branch on it.
Treat value: null as “not on the receipt”, not as zero. Faded thermal paper often loses the tax line first.
Set a lower confidence threshold on contains_alcohol than on total_amount. The flag matters less than the amount.

Examples

Read only

Read, then pull out

Sort first, then pull out

Extract, then check

Operate at scale

The workflow

Run it and read the result

Response

Tips

Next steps

Runs and results

Errors

​The workflow

​Run it and read the result

​Response

​Tips

​Next steps

Runs and results

Errors

The workflow

Run it and read the result

Response

Tips

Next steps