Usage Instructions
Integrate AWS Textract into your workflow to extract text, tables, forms, and key-value pairs from documents. Single-page mode supports JPEG, PNG, and single-page PDF. Multi-page mode supports multi-page PDF and TIFF.
Tools
textract_parser
Input
| Parameter | Type | Required | Description |
|---|---|---|---|
accessKeyId | string | Yes | No description |
secretAccessKey | string | Yes | No description |
region | string | Yes | No description |
processingMode | string | No | No description |
filePath | string | No | No description |
file | file | No | No description |
s3Uri | string | No | No description |
featureTypes | array | No | Feature types to detect: TABLES, FORMS, QUERIES, SIGNATURES, LAYOUT. If not specified, only text detection is performed. |
items | string | No | No description |
queries | array | No | Custom queries to extract specific information. Only used when featureTypes includes QUERIES. |
items | object | No | Query configuration |
properties | string | No | No description |
Text | string | No | No description |
Alias | string | No | No description |
Output
This tool does not produce any outputs.