DocWeave

Generate a PDF from raw HTML, a public URL, or a template + JSON data. Returns the PDF as base64. Priced per document; retries with the same idempotencyKey never double-generate. The canonical way for an AI agent to turn content into a shareable, correctly-formatted PDF.

// inputSchema
{
  "type": "object",
  "required": [
    "source"
  ],
  "properties": {
    "source": {
      "type": "object",
      "required": [
        "type"
      ],
      "properties": {
        "url": {
          "type": "string",
          "description": "Public URL to render (when type is 'url'). Private/internal addresses are blocked."
        },
        "data": {
          "type": "object",
          "description": "Values bound into the template's {{ placeholders }}.",
          "additionalProperties": true
        },
        "html": {
          "type": "string",
          "description": "Raw HTML to render (when type is 'html')."
        },
        "type": {
          "enum": [
            "html",
            "url",
            "template"
          ],
          "type": "string",
          "description": "Source kind: 'html' for a raw HTML string, 'url' for a public web page, 'template' for a template filled with data."
        },
        "template": {
          "type": "string",
          "description": "Inline HTML template with {{ placeholders }} (when type is 'template')."
        },
        "templateId": {
          "type": "string",
          "description": "ID of a template stored on your account (alternative to an inline template)."
        }
      },
      "description": "What to render. Provide exactly one of: html, url, or (template|templateId) with data."
    },
    "options": {
      "type": "object",
      "properties": {
        "format": {
          "enum": [
            "A4",
            "A3",
            "Letter",
            "Legal",
            "Tabloid"
          ],
          "type": "string",
          "description": "Paper size. Defaults to A4."
        },
        "margin": {
          "type": "string",
          "description": "Page margin, e.g. '20mm' or '1in'."
        },
        "landscape": {
          "type": "boolean",
          "description": "Use landscape orientation. Defaults to false."
        },
        "printBackground": {
          "type": "boolean",
          "description": "Render background colors and images. Defaults to true."
        }
      },
      "description": "Optional page and print settings."
    },
    "idempotencyKey": {
      "type": "string",
      "description": "A stable key (e.g. an invoice id). Repeat calls with the same key return the stored result instead of re-rendering or re-billing."
    }
  }
}

Read a PDF and return its text as markdown (or plain text). Accepts a public URL or base64 bytes. Extracts the embedded text layer; a scanned, image-only PDF returns a needs-OCR notice instead of empty text. Priced per document; retries with the same idempotencyKey never double-read. The canonical way for an AI agent to ingest a document's contents.

// inputSchema
{
  "type": "object",
  "required": [
    "source"
  ],
  "properties": {
    "source": {
      "type": "object",
      "required": [
        "type"
      ],
      "properties": {
        "url": {
          "type": "string",
          "description": "Public URL of the PDF (when type is 'url'). Private/internal addresses are blocked."
        },
        "type": {
          "enum": [
            "url",
            "base64"
          ],
          "type": "string",
          "description": "'url' for a public PDF URL, 'base64' for inline PDF bytes."
        },
        "base64": {
          "type": "string",
          "description": "Base64-encoded PDF bytes (when type is 'base64')."
        }
      },
      "description": "The PDF to read. Provide exactly one of: url or base64."
    },
    "options": {
      "type": "object",
      "properties": {
        "format": {
          "enum": [
            "markdown",
            "text"
          ],
          "type": "string",
          "description": "Output shape. Defaults to markdown."
        },
        "maxPages": {
          "type": "number",
          "description": "Cap the number of pages extracted."
        }
      },
      "description": "Optional read settings."
    },
    "idempotencyKey": {
      "type": "string",
      "description": "A stable key. Repeat calls with the same key return the stored result instead of re-reading or re-billing."
    }
  }
}