Created
March 3, 2021 01:31
-
-
Save Sealjay/f640c01e6b374cd37dd8e87581c8f895 to your computer and use it in GitHub Desktop.
cognitivesearch - ai skillset - merge text
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
{ | |
"name": "mergetext", | |
"description": "Extract text from images and merge with content text to produce merged_text", | |
"skills": [ | |
{ | |
"@odata.type": "#Microsoft.Skills.Vision.OcrSkill", | |
"name": "#1", | |
"description": "Extract text (plain and structured) from image.", | |
"context": "/document/normalized_images/*", | |
"textExtractionAlgorithm": null, | |
"lineEnding": "Space", | |
"defaultLanguageCode": "en", | |
"detectOrientation": true, | |
"inputs": [ | |
{ | |
"name": "image", | |
"source": "/document/normalized_images/*" | |
} | |
], | |
"outputs": [ | |
{ | |
"name": "text", | |
"targetName": "text" | |
} | |
] | |
}, | |
{ | |
"@odata.type": "#Microsoft.Skills.Text.MergeSkill", | |
"name": "#2", | |
"description": "Create merged_text, which includes all the textual representation of each image inserted at the right location in the content field.", | |
"context": "/document", | |
"insertPreTag": " ", | |
"insertPostTag": " ", | |
"inputs": [ | |
{ | |
"name": "text", | |
"source": "/document/content" | |
}, | |
{ | |
"name": "itemsToInsert", | |
"source": "/document/normalized_images/*/text" | |
}, | |
{ | |
"name": "offsets", | |
"source": "/document/normalized_images/*/contentOffset" | |
} | |
], | |
"outputs": [ | |
{ | |
"name": "mergedText", | |
"targetName": "merged_text" | |
} | |
] | |
} | |
], | |
"cognitiveServices": null, | |
"knowledgeStore": null, | |
"encryptionKey": null | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment