upstage-document-classification

Classify PDFs, images, and DOCX into user-defined categories with confidence scores.

9|1|Updated Apr 20, 2026
One-click install
npx skills add https://github.com/UpstageAI/upstage-extensions-hub --skill upstage-document-classification
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: upstage-document-classification
Source: https://github.com/UpstageAI/upstage-extensions-hub/tree/main/skills/upstage-document-classification
Command: npx skills add https://github.com/UpstageAI/upstage-extensions-hub --skill upstage-document-classification

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Classify documents into user-defined categories and route them appropriately to streamline workflows and archival processes.

Core Features & Use Cases

  • Classify documents into predefined categories with confidence scores using the Upstage Document Classification API.
  • Split multi-document PDFs into individual documents to enable per-document processing and routing.
  • Route and organize documents by type for downstream automation, search, and analytics, including mixed document sets (PDFs, images, DOCX).

Quick Start

Classify a sample PDF into its category and optionally split the document into individual items for separate processing.

Frequently Asked Questions about upstage-document-classification

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I classify and split multi-document PDFs into categories?

To classify and split multi-document PDFs, you apply the document classification API to the input, which categorizes pages into predefined types and optionally splits the file into individual documents for separate processing.

Can I classify images and DOCX files or does this only support PDF routing?

You can classify images and DOCX files in addition to PDFs. The document classification API processes mixed document sets to route and organize various file formats into user-defined categories.

How do I route invoices, contracts, and receipts automatically using a classification API?

Routing invoices, contracts, and receipts is done by defining these as categories in the document classification API, which then assigns category labels and confidence scores to each input for downstream workflow automation.

Do I need API authentication to classify documents and extract confidence scores?

Yes, you need API authentication to classify documents and extract confidence scores. The document classification API requires valid credentials to process inputs and return structured outputs including category labels.

What is the best way to organize mixed document sets for downstream search and analytics?

The best way to organize mixed document sets is to classify them into predefined categories with confidence scores, enabling structured routing and archival workflows for downstream automation, search, and analytics.

Does document classification return confidence scores for category routing?

Yes, document classification returns confidence scores for category routing. The API provides structured outputs that include both the assigned category labels and their corresponding confidence scores for each document.