{
  "schemaVersion": "1.0",
  "item": {
    "slug": "upstage-document-parse",
    "name": "upstage-document-parse",
    "source": "tencent",
    "type": "skill",
    "category": "开发工具",
    "sourceUrl": "https://clawhub.ai/upstage-deployment/upstage-document-parse",
    "canonicalUrl": "https://clawhub.ai/upstage-deployment/upstage-document-parse",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/upstage-document-parse",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=upstage-document-parse",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-05-07T17:22:31.273Z",
      "expiresAt": "2026-05-14T17:22:31.273Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=afrexai-annual-report",
        "contentDisposition": "attachment; filename=\"afrexai-annual-report-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/upstage-document-parse"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/upstage-document-parse",
    "agentPageUrl": "https://openagent3.xyz/skills/upstage-document-parse/agent",
    "manifestUrl": "https://openagent3.xyz/skills/upstage-document-parse/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/upstage-document-parse/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Upstage Document Parse",
        "body": "Extract structured content from documents using Upstage's Document Parse API."
      },
      {
        "title": "Supported Formats",
        "body": "PDF (up to 1000 pages with async), PNG, JPG, JPEG, TIFF, BMP, GIF, WEBP, DOCX, PPTX, XLSX, HWP"
      },
      {
        "title": "Installation",
        "body": "clawhub install upstage-document-parse"
      },
      {
        "title": "API Key Setup",
        "body": "Get your API key from Upstage Console\nConfigure the API key:\n\nopenclaw config set skills.entries.upstage-document-parse.apiKey \"your-api-key\"\n\nOr add to ~/.openclaw/openclaw.json:\n\n{\n  \"skills\": {\n    \"entries\": {\n      \"upstage-document-parse\": {\n        \"apiKey\": \"your-api-key\"\n      }\n    }\n  }\n}"
      },
      {
        "title": "Usage Examples",
        "body": "Just ask the agent to parse your document:\n\n\"Parse this PDF: ~/Documents/report.pdf\"\n\"Parse: ~/Documents/report.jpg\""
      },
      {
        "title": "Sync API (Small Documents)",
        "body": "For small documents (recommended < 20 pages)."
      },
      {
        "title": "Parameters",
        "body": "ParameterTypeDefaultDescriptionmodelstringrequiredUse document-parse (latest) or document-parse-nightlydocumentfilerequiredDocument file to parsemodestringstandardstandard (text-focused), enhanced (complex tables/images), autoocrstringautoauto (images only) or force (always OCR)output_formatsstring['html']text, html, markdown (array format)coordinatesbooleantrueInclude bounding box coordinatesbase64_encodingstring[]Elements to base64: [\"table\"], [\"figure\"], etc.chart_recognitionbooleantrueConvert charts to tables (Beta)merge_multipage_tablesbooleanfalseMerge tables across pages (Beta, max 20 pages if true)"
      },
      {
        "title": "Basic Parsing",
        "body": "curl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@/path/to/file.pdf\" \\\n  -F \"model=document-parse\""
      },
      {
        "title": "Extract Markdown",
        "body": "curl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@report.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"output_formats=['markdown']\""
      },
      {
        "title": "Enhanced Mode for Complex Documents",
        "body": "curl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@complex.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"mode=enhanced\" \\\n  -F \"output_formats=['html', 'markdown']\""
      },
      {
        "title": "Force OCR for Scanned Documents",
        "body": "curl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@scan.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"ocr=force\""
      },
      {
        "title": "Extract Table Images as Base64",
        "body": "curl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@invoice.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"base64_encoding=['table']\""
      },
      {
        "title": "Response Structure",
        "body": "{\n  \"api\": \"2.0\",\n  \"model\": \"document-parse-251217\",\n  \"content\": {\n    \"html\": \"<h1>...</h1>\",\n    \"markdown\": \"# ...\",\n    \"text\": \"...\"\n  },\n  \"elements\": [\n    {\n      \"id\": 0,\n      \"category\": \"heading1\",\n      \"content\": { \"html\": \"...\", \"markdown\": \"...\", \"text\": \"...\" },\n      \"page\": 1,\n      \"coordinates\": [{\"x\": 0.06, \"y\": 0.05}, ...]\n    }\n  ],\n  \"usage\": { \"pages\": 1 }\n}"
      },
      {
        "title": "Element Categories",
        "body": "paragraph, heading1, heading2, heading3, list, table, figure, chart, equation, caption, header, footer, index, footnote"
      },
      {
        "title": "Async API (Large Documents)",
        "body": "For documents up to 1000 pages. Documents are processed in batches of 10 pages."
      },
      {
        "title": "Submit Request",
        "body": "curl -X POST \"https://api.upstage.ai/v1/document-digitization/async\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@large.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"output_formats=['markdown']\"\n\nResponse:\n\n{\"request_id\": \"uuid-here\"}"
      },
      {
        "title": "Check Status & Get Results",
        "body": "curl \"https://api.upstage.ai/v1/document-digitization/requests/{request_id}\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\"\n\nResponse includes download_url for each batch (available for 30 days)."
      },
      {
        "title": "List All Requests",
        "body": "curl \"https://api.upstage.ai/v1/document-digitization/requests\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\""
      },
      {
        "title": "Status Values",
        "body": "submitted: Request received\nstarted: Processing in progress\ncompleted: Ready for download\nfailed: Error occurred (check failure_message)"
      },
      {
        "title": "Notes",
        "body": "Results stored for 30 days\nDownload URLs expire after 15 minutes (re-fetch status to get new URLs)\nDocuments split into batches of up to 10 pages"
      },
      {
        "title": "Python Usage",
        "body": "import requests\n\napi_key = \"up_xxx\"\n\n# Sync\nwith open(\"doc.pdf\", \"rb\") as f:\n    response = requests.post(\n        \"https://api.upstage.ai/v1/document-digitization\",\n        headers={\"Authorization\": f\"Bearer {api_key}\"},\n        files={\"document\": f},\n        data={\"model\": \"document-parse\", \"output_formats\": \"['markdown']\"}\n    )\nprint(response.json()[\"content\"][\"markdown\"])\n\n# Async for large docs\nwith open(\"large.pdf\", \"rb\") as f:\n    r = requests.post(\n        \"https://api.upstage.ai/v1/document-digitization/async\",\n        headers={\"Authorization\": f\"Bearer {api_key}\"},\n        files={\"document\": f},\n        data={\"model\": \"document-parse\"}\n    )\nrequest_id = r.json()[\"request_id\"]\n\n# Poll for results\nimport time\nwhile True:\n    status = requests.get(\n        f\"https://api.upstage.ai/v1/document-digitization/requests/{request_id}\",\n        headers={\"Authorization\": f\"Bearer {api_key}\"}\n    ).json()\n    if status[\"status\"] == \"completed\":\n        break\n    time.sleep(5)"
      },
      {
        "title": "LangChain Integration",
        "body": "from langchain_upstage import UpstageDocumentParseLoader\n\nloader = UpstageDocumentParseLoader(\n    file_path=\"document.pdf\",\n    output_format=\"markdown\",\n    ocr=\"auto\"\n)\ndocs = loader.load()"
      },
      {
        "title": "Environment Variable (Alternative)",
        "body": "You can also set the API key as an environment variable:\n\nexport UPSTAGE_API_KEY=\"your-api-key\""
      },
      {
        "title": "Tips",
        "body": "Use mode=enhanced for complex tables, charts, images\nUse mode=auto to let API decide per page\nUse async API for documents > 20 pages\nUse ocr=force for scanned PDFs or images\nmerge_multipage_tables=true combines split tables (max 20 pages with enhanced mode)\nResults from async API available for 30 days\nServer-side timeout: 5 minutes per request (sync API)\nStandard documents process in ~3 seconds"
      }
    ],
    "body": "Upstage Document Parse\n\nExtract structured content from documents using Upstage's Document Parse API.\n\nSupported Formats\n\nPDF (up to 1000 pages with async), PNG, JPG, JPEG, TIFF, BMP, GIF, WEBP, DOCX, PPTX, XLSX, HWP\n\nInstallation\nclawhub install upstage-document-parse\n\nAPI Key Setup\nGet your API key from Upstage Console\nConfigure the API key:\nopenclaw config set skills.entries.upstage-document-parse.apiKey \"your-api-key\"\n\n\nOr add to ~/.openclaw/openclaw.json:\n\n{\n  \"skills\": {\n    \"entries\": {\n      \"upstage-document-parse\": {\n        \"apiKey\": \"your-api-key\"\n      }\n    }\n  }\n}\n\nUsage Examples\n\nJust ask the agent to parse your document:\n\n\"Parse this PDF: ~/Documents/report.pdf\"\n\"Parse: ~/Documents/report.jpg\"\n\nSync API (Small Documents)\n\nFor small documents (recommended < 20 pages).\n\nParameters\nParameter\tType\tDefault\tDescription\nmodel\tstring\trequired\tUse document-parse (latest) or document-parse-nightly\ndocument\tfile\trequired\tDocument file to parse\nmode\tstring\tstandard\tstandard (text-focused), enhanced (complex tables/images), auto\nocr\tstring\tauto\tauto (images only) or force (always OCR)\noutput_formats\tstring\t['html']\ttext, html, markdown (array format)\ncoordinates\tboolean\ttrue\tInclude bounding box coordinates\nbase64_encoding\tstring\t[]\tElements to base64: [\"table\"], [\"figure\"], etc.\nchart_recognition\tboolean\ttrue\tConvert charts to tables (Beta)\nmerge_multipage_tables\tboolean\tfalse\tMerge tables across pages (Beta, max 20 pages if true)\nBasic Parsing\ncurl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@/path/to/file.pdf\" \\\n  -F \"model=document-parse\"\n\nExtract Markdown\ncurl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@report.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"output_formats=['markdown']\"\n\nEnhanced Mode for Complex Documents\ncurl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@complex.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"mode=enhanced\" \\\n  -F \"output_formats=['html', 'markdown']\"\n\nForce OCR for Scanned Documents\ncurl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@scan.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"ocr=force\"\n\nExtract Table Images as Base64\ncurl -X POST \"https://api.upstage.ai/v1/document-digitization\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@invoice.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"base64_encoding=['table']\"\n\nResponse Structure\n{\n  \"api\": \"2.0\",\n  \"model\": \"document-parse-251217\",\n  \"content\": {\n    \"html\": \"<h1>...</h1>\",\n    \"markdown\": \"# ...\",\n    \"text\": \"...\"\n  },\n  \"elements\": [\n    {\n      \"id\": 0,\n      \"category\": \"heading1\",\n      \"content\": { \"html\": \"...\", \"markdown\": \"...\", \"text\": \"...\" },\n      \"page\": 1,\n      \"coordinates\": [{\"x\": 0.06, \"y\": 0.05}, ...]\n    }\n  ],\n  \"usage\": { \"pages\": 1 }\n}\n\nElement Categories\n\nparagraph, heading1, heading2, heading3, list, table, figure, chart, equation, caption, header, footer, index, footnote\n\nAsync API (Large Documents)\n\nFor documents up to 1000 pages. Documents are processed in batches of 10 pages.\n\nSubmit Request\ncurl -X POST \"https://api.upstage.ai/v1/document-digitization/async\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\" \\\n  -F \"document=@large.pdf\" \\\n  -F \"model=document-parse\" \\\n  -F \"output_formats=['markdown']\"\n\n\nResponse:\n\n{\"request_id\": \"uuid-here\"}\n\nCheck Status & Get Results\ncurl \"https://api.upstage.ai/v1/document-digitization/requests/{request_id}\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\"\n\n\nResponse includes download_url for each batch (available for 30 days).\n\nList All Requests\ncurl \"https://api.upstage.ai/v1/document-digitization/requests\" \\\n  -H \"Authorization: Bearer $UPSTAGE_API_KEY\"\n\nStatus Values\nsubmitted: Request received\nstarted: Processing in progress\ncompleted: Ready for download\nfailed: Error occurred (check failure_message)\nNotes\nResults stored for 30 days\nDownload URLs expire after 15 minutes (re-fetch status to get new URLs)\nDocuments split into batches of up to 10 pages\nPython Usage\nimport requests\n\napi_key = \"up_xxx\"\n\n# Sync\nwith open(\"doc.pdf\", \"rb\") as f:\n    response = requests.post(\n        \"https://api.upstage.ai/v1/document-digitization\",\n        headers={\"Authorization\": f\"Bearer {api_key}\"},\n        files={\"document\": f},\n        data={\"model\": \"document-parse\", \"output_formats\": \"['markdown']\"}\n    )\nprint(response.json()[\"content\"][\"markdown\"])\n\n# Async for large docs\nwith open(\"large.pdf\", \"rb\") as f:\n    r = requests.post(\n        \"https://api.upstage.ai/v1/document-digitization/async\",\n        headers={\"Authorization\": f\"Bearer {api_key}\"},\n        files={\"document\": f},\n        data={\"model\": \"document-parse\"}\n    )\nrequest_id = r.json()[\"request_id\"]\n\n# Poll for results\nimport time\nwhile True:\n    status = requests.get(\n        f\"https://api.upstage.ai/v1/document-digitization/requests/{request_id}\",\n        headers={\"Authorization\": f\"Bearer {api_key}\"}\n    ).json()\n    if status[\"status\"] == \"completed\":\n        break\n    time.sleep(5)\n\nLangChain Integration\nfrom langchain_upstage import UpstageDocumentParseLoader\n\nloader = UpstageDocumentParseLoader(\n    file_path=\"document.pdf\",\n    output_format=\"markdown\",\n    ocr=\"auto\"\n)\ndocs = loader.load()\n\nEnvironment Variable (Alternative)\n\nYou can also set the API key as an environment variable:\n\nexport UPSTAGE_API_KEY=\"your-api-key\"\n\nTips\nUse mode=enhanced for complex tables, charts, images\nUse mode=auto to let API decide per page\nUse async API for documents > 20 pages\nUse ocr=force for scanned PDFs or images\nmerge_multipage_tables=true combines split tables (max 20 pages with enhanced mode)\nResults from async API available for 30 days\nServer-side timeout: 5 minutes per request (sync API)\nStandard documents process in ~3 seconds"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/upstage-deployment/upstage-document-parse",
    "publisherUrl": "https://clawhub.ai/upstage-deployment/upstage-document-parse",
    "owner": "upstage-deployment",
    "version": "1.0.4",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/upstage-document-parse",
    "downloadUrl": "https://openagent3.xyz/downloads/upstage-document-parse",
    "agentUrl": "https://openagent3.xyz/skills/upstage-document-parse/agent",
    "manifestUrl": "https://openagent3.xyz/skills/upstage-document-parse/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/upstage-document-parse/agent.md"
  }
}