跳到正文
TakoAPI
返回技能列表

docstrange

由 shhdwi 提供

Personal Development
2.9k下载量由 clawskills.sh 提供
21星标
0浏览量
0 个赞登录后即可为这个技能点赞
—暂无评分
你的评分

简介

Document extraction API by Nanonets.

描述

该技能的功能

DocStrange is a document extraction API by Nanonets. It converts PDFs and images to markdown, JSON, or CSV, returning per-field confidence scores for each extracted value.

Per-field confidence scores (0-100) let you automatically flag uncertain extractions for manual review rather than trusting all output blindly.

何时使用

  • Extracting invoice fields from supplier PDFs
  • Parsing receipts for expense reports
  • Converting scanned bank statements to structured data
  • Digitizing paper forms into JSON
  • OCR-ing printed documents for search indexing

示例工作流

输入

User asks: Extract the invoice number, date, vendor, and total from this invoice PDF

智能体
  1. 1

    Receives the PDF file path from the user

  2. 2

    Sends a POST request to /api/v1/extract/sync with output_format=json and field list ["invoice_number", "date", "vendor", "total"]

  3. 3

    Adds include_metadata=confidence_score to the request

  4. 4

    Parses the response and flags any field with a confidence score below 80 for manual review

输出

JSON object with invoice_number, date, vendor, and total values, each annotated with a 0-100 confidence score

前置要求

  • Nanonets DocStrange account
  • DOCSTRANGE_API_KEY environment variable

安装

clawhub install shhdwi/docstrange

运行 CLI 命令,或把这段提示词粘贴到 Claude Code、Cursor、Codex 或你在用的任意编程智能体里。

链接