Upstage Information ExtractionInstall

Summary

Extract structured data from documents or images using the Upstage API and a user-defined JSON schema.

Inputs

• Input Type (required) — Source of the document or image: 'Binary (from previous node)' or 'Image URL'.
• Binary Property — Name of the binary property containing the file (required if Input Type is binary).
• Image URL — URL of the image to analyze (required if Input Type is url).
• Model (required) — The AI model to use for extraction.
• Schema Input Type (required) — How to provide the extraction schema: 'Schema Only' or 'Full Response Format'.
• Schema Name — Name for the JSON schema in the response_format object (required when Schema Input Type is Schema Only).
• JSON Schema (object) — Target JSON schema defining the structure of the data to extract (required when Schema Input Type is Schema Only).
• Full Response Format JSON — Complete response_format JSON object (required when Schema Input Type is Full Response Format).
• Pages per Chunk — Number of pages to process simultaneously (0 disables chunking).
• Return (required) — Output format: 'Extracted JSON Only', 'Schema JSON Only', or 'Full Response'.

Output shape

A list of items where each item contains the extracted data in a '' field.

When Return Mode is 'Extracted JSON Only', the output includes 'extracted', 'model', and 'usage' fields. When Return Mode is 'Full Response', the entire API response is returned.

Examples

Example 1: Extract structured data from a binary file using a custom JSON schema.

Input Type: Binary; Binary Property: 'data'; Schema Input Type: Schema Only; JSON Schema: Custom object definition; Return: Extracted JSON Only.

Example 2: Extract data from a remote image URL with default settings.

Input Type: URL; Return: Extracted JSON Only.

Example 3: Retrieve the full API response to access metadata like usage statistics.

Input Type: Binary; Return: Full Response.