@baseUrl = PUT-YOUR-SEARCH-SERVICE-URL-HERE @apiKey = PUT-YOUR-SEARCH-SERVICE-ADMIN-API-KEY-HERE @storageConnectionString = PUT-YOUR-STORAGE-CONNECTION-STRING-HERE @blobContainer = PUT-YOUR-CONTAINER-NAME-HERE
### List existing indexes by name GET {{baseUrl}}/indexes?api-version=2023-11-01&$select=name HTTP/1.1 Content-Type: application/json api-key: {{apiKey}}
### Create a data source POST {{baseUrl}}/datasources?api-version=2023-11-01 HTTP/1.1 Content-Type: application/json api-key: {{apiKey}}
- {
"name": "clinical-trials-ds", "description": null, "type": "azureblob", "subtype": null, "credentials": { "connectionString": "{{storageConnectionString}}" }, "container": { "name": "{{blobContainer}}", "query": null }, "dataChangeDetectionPolicy": null, "dataDeletionDetectionPolicy": null
}
### Create an index POST {{baseUrl}}/indexes?api-version=2023-11-01 HTTP/1.1 Content-Type: application/json api-key: {{apiKey}}
- {
"name": "clinical-trials", "defaultScoringProfile": null, "fields": [ { "name": "content", "type": "Edm.String", "searchable": true, "filterable": false, "retrievable": true, "sortable": false, "facetable": false, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": "standard.lucene", "synonymMaps": [] }, { "name": "metadata_storage_content_type", "type": "Edm.String", "searchable": false, "filterable": false, "retrievable": false, "sortable": false, "facetable": false, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": null, "synonymMaps": [] }, { "name": "metadata_storage_name", "type": "Edm.String", "searchable": false, "filterable": false, "retrievable": false, "sortable": false, "facetable": false, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": null, "synonymMaps": [] }, { "name": "metadata_storage_path", "type": "Edm.String", "searchable": false, "filterable": false, "retrievable": true, "sortable": false, "facetable": false, "key": true, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": null, "synonymMaps": [] }, { "name": "organizations", "type": "Collection(Edm.String)", "searchable": true, "filterable": false, "retrievable": true, "sortable": false, "facetable": true, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": "standard.lucene", "synonymMaps": [] }, { "name": "locations", "type": "Collection(Edm.String)", "searchable": true, "filterable": false, "retrievable": true, "sortable": false, "facetable": true, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": "standard.lucene", "synonymMaps": [] }, { "name": "keyphrases", "type": "Collection(Edm.String)", "searchable": true, "filterable": true, "retrievable": true, "sortable": false, "facetable": true, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": "standard.lucene", "synonymMaps": [] }, { "name": "language", "type": "Edm.String", "searchable": true, "filterable": false, "retrievable": true, "sortable": false, "facetable": true, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": "standard.lucene", "synonymMaps": [] }, { "name": "translated_text", "type": "Edm.String", "searchable": true, "filterable": false, "retrievable": true, "sortable": false, "facetable": false, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": "en.lucene", "synonymMaps": [] }, { "name": "merged_content", "type": "Edm.String", "searchable": true, "filterable": false, "retrievable": true, "sortable": false, "facetable": false, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": "standard.lucene", "synonymMaps": [] }, { "name": "text", "type": "Collection(Edm.String)", "searchable": true, "filterable": false, "retrievable": true, "sortable": false, "facetable": false, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": "standard.lucene", "synonymMaps": [] }, { "name": "layoutText", "type": "Collection(Edm.String)", "searchable": true, "filterable": false, "retrievable": true, "sortable": false, "facetable": false, "key": false, "indexAnalyzer": null, "searchAnalyzer": null, "analyzer": "standard.lucene", "synonymMaps": [] } ], "scoringProfiles": [], "corsOptions": null, "suggesters": [ { "name": "sg", "searchMode": "analyzingInfixMatching", "sourceFields": [ "keyphrases" ] } ], "analyzers": [], "tokenizers": [], "tokenFilters": [], "charFilters": [], "encryptionKey": null
}
### Create a skillset POST {{baseUrl}}/skillsets?api-version=2023-11-01 HTTP/1.1 Content-Type: application/json api-key: {{apiKey}}
- {
"name": "clinical-trials-ss", "description": "Demonstrates debug sessions. Entity Recognition has intentional errors for debug purposes.", "skills": [ { "@odata.type": "#Microsoft.Skills.Text.V3.EntityRecognitionSkill", "name": "#1", "description": null, "context": "/document", "categories": [ "Organization", "Location" ], "defaultLanguageCode": "en", "minimumPrecision": null, "inputs": [ { "name": "text", "source": "/document/content", "sourceContext": null, "inputs": [] }, { "name": "languageCode", "source": "/document/languageCode", "sourceContext": null, "inputs": [] } ], "outputs": [ { "name": "organizations", "targetName": "organizations" }, { "name": "locations", "targetName": "locations" } ] }, { "@odata.type": "#Microsoft.Skills.Text.KeyPhraseExtractionSkill", "name": "#2", "description": null, "context": "/document/merged_content", "defaultLanguageCode": "en", "maxKeyPhraseCount": null, "inputs": [ { "name": "text", "source": "/document/merged_content", "sourceContext": null, "inputs": [] }, { "name": "languageCode", "source": "/document/language", "sourceContext": null, "inputs": [] } ], "outputs": [ { "name": "keyPhrases", "targetName": "keyphrases" } ] }, { "@odata.type": "#Microsoft.Skills.Text.LanguageDetectionSkill", "name": "#3", "description": null, "context": "/document", "inputs": [ { "name": "text", "source": "/document/merged_content", "sourceContext": null, "inputs": [] } ], "outputs": [ { "name": "languageCode", "targetName": "language" } ] }, { "@odata.type": "#Microsoft.Skills.Text.TranslationSkill", "name": "#4", "description": null, "context": "/document/merged_content", "defaultFromLanguageCode": null, "defaultToLanguageCode": "en", "suggestedFrom": "en", "inputs": [ { "name": "text", "source": "/document/merged_content", "sourceContext": null, "inputs": [] } ], "outputs": [ { "name": "translatedText", "targetName": "translated_text" } ] }, { "@odata.type": "#Microsoft.Skills.Text.MergeSkill", "name": "#5", "description": null, "context": "/document", "insertPreTag": " ", "insertPostTag": " ", "inputs": [ { "name": "text", "source": "/document/content", "sourceContext": null, "inputs": [] }, { "name": "itemsToInsert", "source": "/document/normalized_images//text", "sourceContext": null, "inputs": [] }, { "name": "offsets", "source": "/document/normalized_images//contentOffset", "sourceContext": null, "inputs": [] } ], "outputs": [ { "name": "mergedText", "targetName": "merged_content" } ] }, { "@odata.type": "#Microsoft.Skills.Vision.OcrSkill", "name": "#6", "description": null, "context": "/document/normalized_images/", "textExtractionAlgorithm": null, "lineEnding": "Space", "defaultLanguageCode": "en", "detectOrientation": true, "inputs": [ { "name": "image", "source": "/document/normalized_images/", "sourceContext": null, "inputs": [] } ], "outputs": [ { "name": "text", "targetName": "text" }, { "name": "layoutText", "targetName": "layoutText" } ] } ], "cognitiveServices": null
}
### Create an indexer POST {{baseUrl}}/indexers?api-version=2023-11-01 HTTP/1.1 Content-Type: application/json api-key: {{apiKey}}
- {
"name": "clinical-trials-idxr", "description": null, "dataSourceName": "clinical-trials-ds", "skillsetName": "clinical-trials-ss", "targetIndexName": "clinical-trials", "disabled": null, "schedule": null, "parameters": { "batchSize": null, "maxFailedItems": 0, "maxFailedItemsPerBatch": 0, "base64EncodeKeys": null, "configuration": { "imageAction": "generateNormalizedImages", "dataToExtract": "contentAndMetadata", "parsingMode": "default" } }, "fieldMappings": [ { "sourceFieldName": "metadata_storage_path", "targetFieldName": "metadata_storage_path", "mappingFunction": { "name": "base64Encode", "parameters": null } } ], "outputFieldMappings": [ { "sourceFieldName": "/document/merged_content/organizations", "targetFieldName": "organizations", "mappingFunction": null }, { "sourceFieldName": "/document/merged_content/locations", "targetFieldName": "locations", "mappingFunction": null }, { "sourceFieldName": "/document/merged_content/keyphrases", "targetFieldName": "keyphrases", "mappingFunction": null }, { "sourceFieldName": "/document/language", "targetFieldName": "language", "mappingFunction": null }, { "sourceFieldName": "/document/merged_content/translated_text", "targetFieldName": "translated_text", "mappingFunction": null }, { "sourceFieldName": "/document/merged_content", "targetFieldName": "merged_content", "mappingFunction": null }, { "sourceFieldName": "/document/normalized_images//text", "targetFieldName": "text", "mappingFunction": null }, { "sourceFieldName": "/document/normalized_images//layoutText", "targetFieldName": "layoutText", "mappingFunction": null } ]
}