{"files":{"SKILL.md":"---\nname: computer-vision-client\ndescription: \"Computer Vision Client API skill. Use when working with Computer Vision Client for recognizeText, textOperations, read. Covers 4 endpoints.\"\nversion: 1.0.0\ngenerator: lapsh\n---\n\n# Computer Vision Client\nAPI version: 2.1\n\n## Auth\nApiKey Ocp-Apim-Subscription-Key in header\n\n## Base URL\nhttps://westcentralus.api.cognitive.microsoft.com/vision/v2.1\n\n## Setup\n1. Set your API key in the appropriate header\n2. GET /textOperations/{operationId} -- this interface is used for getting text operation result. the url to this interface should be retrieved from 'operation-location' field returned from recognize text interface.\n3. POST /recognizeText -- create first recognizeText\n\n## Endpoints\n4 endpoints across 3 groups. See references/api-spec.lap for full details.\n\n### RecognizeText\n| Method | Path | Description |\n|--------|------|-------------|\n| POST | /recognizeText | Recognize Text operation. When you use the Recognize Text interface, the response contains a field called 'Operation-Location'. The 'Operation-Location' field contains the URL that you must use for your Get Recognize Text Operation Result operation. |\n\n### TextOperations\n| Method | Path | Description |\n|--------|------|-------------|\n| GET | /textOperations/{operationId} | This interface is used for getting text operation result. The URL to this interface should be retrieved from 'Operation-Location' field returned from Recognize Text interface. |\n\n### Read\n| Method | Path | Description |\n|--------|------|-------------|\n| POST | /read/core/asyncBatchAnalyze | Use this interface to get the result of a Read operation, employing the state-of-the-art Optical Character Recognition (OCR) algorithms optimized for text-heavy documents. When you use the Read File interface, the response contains a field called 'Operation-Location'. The 'Operation-Location' field contains the URL that you must use for your 'GetReadOperationResult' operation to access OCR results.​ |\n| GET | /read/operations/{operationId} | This interface is used for getting OCR results of Read operation. The URL to this interface should be retrieved from 'Operation-Location' field returned from Batch Read File interface. |\n\n## Common Questions\nMatch user requests to endpoints in references/api-spec.lap. Key patterns:\n- \"Create a recognizeText?\" -> POST /recognizeText\n- \"Get textOperation details?\" -> GET /textOperations/{operationId}\n- \"Create a asyncBatchAnalyze?\" -> POST /read/core/asyncBatchAnalyze\n- \"Get operation details?\" -> GET /read/operations/{operationId}\n- \"How to authenticate?\" -> See Auth section above\n\n## Response Tips\n- Check response schemas in references/api-spec.lap for field details\n- Create/update endpoints return the modified resource on success\n\n## References\n- Full spec: See references/api-spec.lap for complete endpoint details, parameter tables, and response schemas\n\n> Generated from the official API spec by [LAP](https://lap.sh)\n","references/api-spec.lap":"@lap v0.3\n# Machine-readable API spec. Each @endpoint block is one API call.\n@api Computer Vision Client\n@base https://westcentralus.api.cognitive.microsoft.com/vision/v2.1\n@version 2.1\n@auth ApiKey Ocp-Apim-Subscription-Key in header\n@endpoints 4\n@toc recognizeText(1), textOperations(1), read(2)\n\n@group recognizeText\n@endpoint POST /recognizeText\n@desc Recognize Text operation. When you use the Recognize Text interface, the response contains a field called 'Operation-Location'. The 'Operation-Location' field contains the URL that you must use for your Get Recognize Text Operation Result operation.\n@required {ImageUrl: map # A JSON document with a URL pointing to the image that is to be analyzed., mode: any # Type of text to recognize.}\n@returns(202) The service has accepted the request and will start processing later. It will return Accepted immediately and include an 'Operation-Location' header. Client side should further query the operation status using the URL specified in this header. The operation ID will expire in 48 hours.\n\n@endgroup\n\n@group textOperations\n@endpoint GET /textOperations/{operationId}\n@desc This interface is used for getting text operation result. The URL to this interface should be retrieved from 'Operation-Location' field returned from Recognize Text interface.\n@required {operationId: any # Id of the text operation returned in the response of the 'Recognize Text'}\n@returns(200) Returns the operation status.\n\n@endgroup\n\n@group read\n@endpoint POST /read/core/asyncBatchAnalyze\n@desc Use this interface to get the result of a Read operation, employing the state-of-the-art Optical Character Recognition (OCR) algorithms optimized for text-heavy documents. When you use the Read File interface, the response contains a field called 'Operation-Location'. The 'Operation-Location' field contains the URL that you must use for your 'GetReadOperationResult' operation to access OCR results.​\n@required {ImageUrl: map # A JSON document with a URL pointing to the image that is to be analyzed.}\n@returns(202) The service has accepted the request and will start processing later.\n\n@endpoint GET /read/operations/{operationId}\n@desc This interface is used for getting OCR results of Read operation. The URL to this interface should be retrieved from 'Operation-Location' field returned from Batch Read File interface.\n@required {operationId: any # Id of read operation returned in the response of the 'Batch Read File' interface.}\n@returns(200) Returns the read operation status.\n\n@endgroup\n\n@end\n"}}