Version history

{
  "version": "0.1.0",
  "summary": "Extract structured content (sections, figures, tables, references) from a PDF URL.",
  "runtime": "http_post",
  "runtime_config": {
    "url_env": "SCIDEX_V1_TOOLS_PDF_EXTRACT_URL",
    "url_default": "http://v1.scidex.ai/internal/tools/pdf_extract",
    "timeout_secs": 300
  },
  "input_schema": {
    "type": "object",
    "required": [
      "url"
    ],
    "properties": {
      "url": {
        "type": "string",
        "description": "PDF URL or file path accessible to the extractor."
      },
      "extract_tables": {
        "type": "boolean",
        "default": true
      },
      "extract_figures": {
        "type": "boolean",
        "default": true
      },
      "extract_references": {
        "type": "boolean",
        "default": true
      }
    }
  },
  "output_schema": {
    "type": "object",
    "properties": {
      "tables": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "figures": {
        "type": "array",
        "items": {
          "type": "object"
        }
      },
      "sections": {
        "type": "array",
        "items": {
          "type": "object",
          "properties": {
            "text": {
              "type": "string"
            },
            "heading": {
              "type": "string"
            }
          }
        }
      },
      "references": {
        "type": "array",
        "items": {
          "type": "object"
        }
      }
    }
  },
  "resource_caps": {
    "network": "external",
    "memory_peak_mb": 2048,
    "max_duration_secs": 300
  },
  "cost_model": {
    "per_call_usd": 0.05
  },
  "examples": [
    {
      "input": {
        "url": "https://example.org/paper.pdf"
      }
    }
  ],
  "lifecycle_state": "active"
}