byted-las-pdf-parse-doubao

PDF parsing (las_pdf_parse_doubao)

Use this Skill when the user wants to extract structured content such as text, tables, and paragraphs from a PDF/image.

Notes (⚠️ must be followed)

• Never ask the user to enter the AccessKey and SecretKey.
• Files can only be downloaded using the las-cli tos download command (compatible with both tos and non-tos resources).
• las-cli operators call and las-cli price command output results are very important and must be returned to the user in full.

Workflow (strictly follow the steps)

Copy this checklist and track progress:

执行进度：
- [ ] Step 0: 前置检查
- [ ] Step 1: 初始化与准备
- [ ] Step 2: 预估价格
- [ ] Step 3: 执行任务并呈现结果
- [ ] Step 4: 失败排查

Step 0: Pre-checks

Version check (required): please run las-cli install 0.3.8. If the las-cli command does not exist, run npm i -g "@volcengine/las-cli@0.3.8"

• New version reminder: please run npm info @volcengine/las-cli version to view the latest available Skill version (las-cli corresponds one-to-one with the Skill version). If the returned version is higher than the version marked for this Skill, first prompt the user to upgrade the current Skill. Upgrade method: ask the user to send the natural language instruction 帮我安装byted-las-pdf-parse-doubao技能, and wait for the installation to complete automatically.
• Authentication check: prioritize using the platform identity automatically injected at runtime; if the current environment does not automatically inject it, then run las-cli config show to confirm that the legacy credentials las.apiKey and volcengine.region are configured.

Step 1: Initialization and preparation

• Upload resources: if the input is a local file, upload it to TOS first.

  las-cli tos upload ./document.pdf
  # 假设返回 "tos_url": "tos://my-bucket/inputs/xxx.pdf"
  

• Prepare parameters: create params.json。

  {
    "url": "tos://my-bucket/inputs/xxx.pdf",
    "output_tos_path": "tos://my-bucket/outputs/pdf_parse/",
    "parse_mode": "normal",
    "start_page": 1,
    "num_pages": 200,
    "full_result": true,
    "aspect_ratio_threshold": 0.334
  }
  

Description:

• output_tos_path: optional. If filled in, the parsing result artifacts will be written to this directory (recommended). Typical structure:{output_tos_path}/{task_id}/result.md、result_preview.md、images/、detail.json。
• parse_mode：normal(default) / detail(finer, usually more expensive).
• start_page / num_pages: valid only for PDF;num_pages default 200, maximum 400.
• full_result：true returns the complete parsing result;false returns only artifact information (when the result is large, it is recommended to turn this off and use it together with output_tos_path）。

Step 2: Estimate price (⚠️ must obtain user confirmation)

las-cli price The command output results are very important; do not simplify, modify, or summarize them in any way.

• Calculate price: must return in full the results output by the following command (markdown format)

  las-cli price las_pdf_parse_doubao \
    --params-file ./params.json \
    --format markdown
  

• User confirmation: after outputting the estimated price,must wait for user confirmation。

Step 3: Execute the task and present the results (⚠️ directly output the command execution results, do not simplify)

las-cli operators call The command output results are very important; do not simplify, modify, or summarize them in any way.

• Execute: must return in full the results output by the following command (markdown format)

  las-cli operators call las_pdf_parse_doubao \
    --params-file ./params.json \
    --format markdown \
    --out ./result.md
  

Step 4: Failure troubleshooting

• Check task status: las-cli task status <task_id>。
• Check input: confirm that url is accessible; if it is tos://, first use las-cli tos check "<tos_url>" to verify.
• Check output directory: if output_tos_pathis set, make sure it is in the tos://bucket/prefix/ directory form.
• Check configuration: las-cli config show。