Extract embedded text from a public digital PDF into page-numbered JSON for RAG, research

[
  {
    "scheme": "exact",
    "network": "eip155:8453",
    "payTo": "0x1cfC6489bC9703a2A49715b8a746D8c6075F3A80",
    "asset": "0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913",
    "amount": "10000",
    "maxTimeoutSeconds": 300
  },
  {
    "scheme": "exact",
    "network": "algorand:wGHE2Pwdvd7S12BL5FaOP20EGYesN73ktiC1qzkkit8=",
    "payTo": "PFHYLVHX77ANNQVF67LK6EVYB34D5VDIUOWLOL5SX367M366DBLOQQAOCA",
    "asset": "31566704",
    "amount": "10000",
    "maxTimeoutSeconds": 300
  }
]

{
  "bazaar": {
    "info": {
      "input": {
        "body": {
          "url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf"
        },
        "bodyType": "json",
        "method": "POST",
        "type": "http"
      },
      "output": {
        "example": {
          "ocr_performed": false,
          "ok": true,
          "page_count": 1,
          "pages": [
            {
              "characters": 14,
              "page": 1,
              "text": "Dummy PDF file"
            }
          ],
          "text": "Dummy PDF file",
          "warnings": [
            "Embedded text only; images and table structure are not extracted."
          ]
        },
        "type": "json"
      }
    },
    "schema": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "properties": {
        "input": {
          "additionalProperties": false,
          "properties": {
            "body": {
              "additionalProperties": false,
              "properties": {
                "url": {
                  "description": "Public HTTP/HTTPS URL to a digital PDF; no credentials or private addresses.",
                  "format": "uri",
                  "maxLength": 2048,
                  "type": "string"
                }
              },
              "required": [
                "url"
              ],
              "type": "object"
            },
            "bodyType": {
              "enum": [
                "json",
                "form-data",
                "text"
              ],
              "type": "string"
            },
            "method": {
              "enum": [
                "POST"
              ],
              "type": "string"
            },
            "type": {
              "const": "http",
              "type": "string"
            }
          },
          "required": [
            "type",
            "method",
            "bodyType",
            "body"
          ],
          "type": "object"
        },
        "output": {
          "properties": {
            "example": {
              "type": "object"
            },
            "type": {
              "type": "string"
            }
          },
          "required": [
            "type"
          ],
          "type": "object"
        }
      },
      "required": [
        "input"
      ],
      "type": "object"
    }
  }
}

curl "https://api.agentwork.run/v1/pdf/read"
# -> 402 Payment Required, accepts[] lists how to pay
# retry with a PAYMENT-SIGNATURE (or PAYMENT header) once paid

const res = await fetch("https://api.agentwork.run/v1/pdf/read");
if (res.status === 402) {
  const { accepts } = await res.json();
  // pay one of accepts[] via an x402 client, then retry with the payment header
}

import httpx
res = httpx.get("https://api.agentwork.run/v1/pdf/read")
if res.status_code == 402:
    accepts = res.json()["accepts"]
    # pay one of accepts[] via an x402 client, then retry with the payment header