Upload and parse a file

{
  "$defs": {
    "AuditMetadata": {
      "additionalProperties": false,
      "description": "User attribution included with SIEM logging events when SIEM Logging is enabled for the organization.",
      "properties": {
        "username": {
          "description": "The username associated with the request.",
          "maxLength": 1024,
          "type": "string"
        }
      },
      "required": [
        "username"
      ],
      "type": "object"
    },
    "ParseFormats": {
      "default": [
        "markdown"
      ],
      "description": "Output formats supported for `/parse` uploads. Browser-rendering formats and change tracking are not supported.",
      "items": {
        "oneOf": [
          {
            "properties": {
              "type": {
                "enum": [
                  "markdown"
                ],
                "type": "string"
              }
            },
            "required": [
              "type"
            ],
            "title": "Markdown",
            "type": "object"
          },
          {
            "properties": {
              "type": {
                "enum": [
                  "summary"
                ],
                "type": "string"
              }
            },
            "required": [
              "type"
            ],
            "title": "Summary",
            "type": "object"
          },
          {
            "properties": {
              "type": {
                "enum": [
                  "html"
                ],
                "type": "string"
              }
            },
            "required": [
              "type"
            ],
            "title": "HTML",
            "type": "object"
          },
          {
            "properties": {
              "type": {
                "enum": [
                  "rawHtml"
                ],
                "type": "string"
              }
            },
            "required": [
              "type"
            ],
            "title": "Raw HTML",
            "type": "object"
          },
          {
            "properties": {
              "type": {
                "enum": [
                  "links"
                ],
                "type": "string"
              }
            },
            "required": [
              "type"
            ],
            "title": "Links",
            "type": "object"
          },
          {
            "properties": {
              "type": {
                "enum": [
                  "images"
                ],
                "type": "string"
              }
            },
            "required": [
              "type"
            ],
            "title": "Images",
            "type": "object"
          },
          {
            "properties": {
              "prompt": {
                "description": "The prompt to use for the JSON output",
                "type": "string"
              },
              "schema": {
                "description": "The schema to use for the JSON output. Must conform to [JSON Schema](https://json-schema.org/).",
                "type": "object"
              },
              "type": {
                "enum": [
                  "json"
                ],
                "type": "string"
              }
            },
            "required": [
              "type"
            ],
            "title": "JSON",
            "type": "object"
          }
        ]
      },
      "type": "array"
    },
    "ParseOptions": {
      "description": "Optional parse options sent as JSON in the multipart `options` field.",
      "properties": {
        "auditMetadata": {
          "$ref": "#/$defs/AuditMetadata"
        },
        "blockAds": {
          "default": true,
          "description": "Enable ad and cookie popup blocking.",
          "type": "boolean"
        },
        "excludeTags": {
          "description": "Tags to exclude from the output.",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "formats": {
          "$ref": "#/$defs/ParseFormats"
        },
        "headers": {
          "description": "Headers to send when additional network requests are required.",
          "type": "object"
        },
        "includeTags": {
          "description": "Tags to include in the output.",
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        "integration": {
          "anyOf": [
            {
              "description": "Optional integration identifier.",
              "type": "string"
            },
            {
              "type": "null"
            }
          ]
        },
        "onlyMainContent": {
          "default": true,
          "description": "Only return the main content of the page excluding headers, navs, footers, etc.",
          "type": "boolean"
        },
        "origin": {
          "default": "api",
          "description": "Origin identifier for analytics and logging.",
          "type": "string"
        },
        "parsers": {
          "default": [
            "pdf"
          ],
          "description": "Controls file parser behavior when relevant (for example PDF parser mode).",
          "items": {
            "oneOf": [
              {
                "additionalProperties": false,
                "properties": {
                  "blocks": {
                    "default": false,
                    "description": "Include per-page typed layout blocks alongside the document markdown. Populates the `blocks` field on the document: typed blocks (title, section_header, text, table, formula, figure, caption, ...) with normalized bounding boxes, reading order, character-span links into the markdown, and per-block confidence. No additional cost.",
                    "type": "boolean"
                  },
                  "maxPages": {
                    "description": "Maximum number of pages to parse from the PDF.",
                    "maximum": 10000,
                    "minimum": 1,
                    "type": "integer"
                  },
                  "mode": {
                    "default": "auto",
                    "description": "PDF parsing mode. \"fast\": text-only extraction. \"auto\": text-first with OCR fallback. \"ocr\": OCR on every page.",
                    "enum": [
                      "fast",
                      "auto",
                      "ocr"
                    ],
                    "type": "string"
                  },
                  "pageMarkers": {
                    "default": false,
                    "description": "Annotate page breaks in the document markdown: pages are joined with `\\n\\n---\\n\\n\\n\\n`, where N is the 1-based physical page of the content that follows. Markers appear between pages only (no leading marker for page 1), and numbering may skip pages merged across a page break — use `pages: true` when every physical page is needed. No new response field; no additional cost.",
                    "type": "boolean"
                  },
                  "pages": {
                    "default": false,
                    "description": "Include physical per-page markdown alongside the document markdown. Populates the `pages` field on the document as an array of { pageNumber, markdown }. No additional cost.",
                    "type": "boolean"
                  },
                  "type": {
                    "enum": [
                      "pdf"
                    ],
                    "type": "string"
                  }
                },
                "required": [
                  "type"
                ],
                "type": "object"
              }
            ]
          },
          "type": "array"
        },
        "proxy": {
          "description": "Proxy mode for parse uploads. `/parse` supports only `basic` and `auto`.",
          "enum": [
            "basic",
            "auto"
          ],
          "type": "string"
        },
        "redactPII": {
          "default": false,
          "description": "Redact personally identifiable information from returned markdown. Pass `true` to use defaults, or an object to tune mode, entities, and replacement style.",
          "oneOf": [
            {
              "type": "boolean"
            },
            {
              "$ref": "#/$defs/RedactPIIOptions"
            }
          ]
        },
        "removeBase64Images": {
          "default": true,
          "description": "Remove base64-encoded images from output and keep alt text placeholders.",
          "type": "boolean"
        },
        "skipTlsVerification": {
          "default": true,
          "description": "Skip TLS certificate verification when making requests.",
          "type": "boolean"
        },
        "timeout": {
          "default": 30000,
          "description": "Timeout in milliseconds for the request. Default is 30000 (30 seconds). Maximum is 300000 (300 seconds).",
          "maximum": 300000,
          "type": "integer"
        },
        "zeroDataRetention": {
          "default": false,
          "description": "If true, this will enable zero data retention for this parse. To enable this feature, please contact help@Asale.dev",
          "type": "boolean"
        }
      },
      "type": "object"
    },
    "RedactPIIEntity": {
      "description": "Public PII entity buckets supported by Asale redaction.",
      "enum": [
        "PERSON",
        "EMAIL",
        "PHONE",
        "LOCATION",
        "FINANCIAL",
        "SECRET"
      ],
      "type": "string"
    },
    "RedactPIIOptions": {
      "additionalProperties": false,
      "description": "Tuning options for PII redaction.",
      "properties": {
        "entities": {
          "description": "Restrict redaction to these entity buckets. If omitted, all supported entities are redacted.",
          "items": {
            "$ref": "#/$defs/RedactPIIEntity"
          },
          "type": "array"
        },
        "mode": {
          "default": "accurate",
          "description": "Redaction strategy. `accurate` is model-only and optimized for precision, `aggressive` increases recall with additional heuristics, and `fast` uses heuristics without the model call.",
          "enum": [
            "accurate",
            "aggressive",
            "fast"
          ],
          "type": "string"
        },
        "replaceStyle": {
          "default": "tag",
          "description": "`tag` replaces spans with placeholders like ``, `mask` replaces characters with `*`, and `remove` deletes the span text.",
          "enum": [
            "tag",
            "mask",
            "remove"
          ],
          "type": "string"
        }
      },
      "type": "object"
    }
  },
  "additionalProperties": false,
  "properties": {
    "body": {
      "properties": {
        "file": {
          "additionalProperties": false,
          "properties": {
            "content_base64": {
              "maxLength": 1400000,
              "type": "string"
            },
            "content_type": {
              "type": "string"
            },
            "filename": {
              "minLength": 1,
              "type": "string"
            }
          },
          "required": [
            "filename",
            "content_base64"
          ],
          "type": "object"
        },
        "options": {
          "$ref": "#/$defs/ParseOptions"
        }
      },
      "required": [
        "file"
      ],
      "type": "object"
    }
  },
  "required": [
    "body"
  ],
  "type": "object"
}