I had an existing AI Search resource. I added a new filed in the index called top_words. Then I created a skillset as Azure Function which count words from a document and add the value in the new field of the index.
After creating the skillset and index, I ran the indexer.
However, when I query the index, the top_words value is coming as null. What I might have missed here?
Update
One issue I found is that I didn’t add the new field in the field mapping.
After adding the following object in outputFieldMappings array,
{
"sourceFieldName": "/document/topWords",
"targetFieldName": "top_words"
}
when I reset the indexer and ran it again, I see error Could not map output field 'top_words' to search index. Check the 'outputFieldMappings' property of your indexer.
However, top_words field exists in the index.
Following are the files
- function
module.exports = async function (context, req) {
context.log('JavaScript HTTP trigger function processed a request. req:'+JSON.stringify(req));
if (req.body && req.body.values) {
vals = req.body.values;
// Array of stop words to be ignored
var stopwords = ['', 'i', 'me', 'my', 'myself', 'we', 'our', 'ours', 'ourselves', 'you',
"youre", "youve", "youll", "youd", 'your', 'yours', 'yourself',
'yourselves', 'he', 'him', 'his', 'himself', 'she', "shes", 'her',
'hers', 'herself', 'it', "its", 'itself', 'they', 'them',
'their', 'theirs', 'themselves', 'what', 'which', 'who', 'whom',
'this', 'that', "thatll", 'these', 'those', 'am', 'is', 'are', 'was',
'were', 'be', 'been', 'being', 'have', 'has', 'had', 'having', 'do',
'does', 'did', 'doing', 'a', 'an', 'the', 'and', 'but', 'if', 'or',
'because', 'as', 'until', 'while', 'of', 'at', 'by', 'for', 'with',
'about', 'against', 'between', 'into', 'through', 'during', 'before',
'after', 'above', 'below', 'to', 'from', 'up', 'down', 'in', 'out',
'on', 'off', 'over', 'under', 'again', 'further', 'then', 'once', 'here',
'there', 'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each',
'few', 'more', 'most', 'other', 'some', 'such', 'no', 'nor', 'not',
'only', 'own', 'same', 'so', 'than', 'too', 'very', 'can', 'will',
'just', "dont", 'should', "shouldve", 'now', "arent", "couldnt",
"didnt", "doesnt", "hadnt", "hasnt", "havent", "isnt", "mightnt", "mustnt",
"neednt", "shant", "shouldnt", "wasnt", "werent", "wont", "wouldnt"];
res = {"values":[]};
for (rec in vals)
{
// Get the record ID and text for this input
resVal = {recordId:vals[rec].recordId, data:{}};
txt = vals[rec].data.text;
// remove punctuation and numerals
txt = txt.replace(/[^ A-Za-z_]/g,"").toLowerCase();
// Get an array of words
words = txt.split(" ")
// count instances of non-stopwords
wordCounts = {}
for(var i = 0; i < words.length; ++i) {
word = words[i];
if (stopwords.includes(word) == false )
{
if (wordCounts[word])
{
wordCounts[word] ++;
}
else
{
wordCounts[word] = 1;
}
}
}
// Convert wordcounts to an array
var topWords = [];
for (var word in wordCounts) {
topWords.push([word, wordCounts[word]]);
}
// Sort in descending order of count
topWords.sort(function(a, b) {
return b[1] - a[1];
});
// Get the first ten words from the first array dimension
resVal.data.text = topWords.slice(0,9)
.map(function(value,index) { return value[0]; });
res.values[rec] = resVal;
};
context.res = {
body: JSON.stringify(res),
headers: {
'Content-Type': 'application/json'
}
};
context.log('returning res :'+JSON.stringify(res));
}
else {
context.res = {
status: 400,
body: {"errors":[{"message": "Invalid input"}]},
headers: {
'Content-Type': 'application/json'
}
};
context.log('returning error res :'+JSON.stringify(context.res));
}
};
- indexer.json
{
"@odata.context": "https://aisearchdemomc.search.windows.net/$metadata#indexers/$entity",
"@odata.etag": ""0x8DCA8159277DA50"",
"name": "margies-indexer",
"description": "Indexer for Margies Travel",
"dataSourceName": "margies-data",
"skillsetName": "margies-skillset",
"targetIndexName": "margies-index",
"disabled": null,
"schedule": null,
"parameters": {
"batchSize": null,
"maxFailedItems": -1,
"maxFailedItemsPerBatch": -1,
"base64EncodeKeys": null,
"configuration": {
"dataToExtract": "contentAndMetadata",
"parsingMode": "default",
"imageAction": "generateNormalizedImages"
}
},
"fieldMappings": [
{
"sourceFieldName": "metadata_storage_path",
"targetFieldName": "metadata_storage_path",
"mappingFunction": {
"name": "base64Encode",
"parameters": null
}
},
{
"sourceFieldName": "metadata_storage_path",
"targetFieldName": "url",
"mappingFunction": null
}
],
"outputFieldMappings": [
{
"sourceFieldName": "/document/merged_content/locations",
"targetFieldName": "locations"
},
{
"sourceFieldName": "/document/merged_content/keyphrases",
"targetFieldName": "keyphrases"
},
{
"sourceFieldName": "/document/language",
"targetFieldName": "language"
},
{
"sourceFieldName": "/document/merged_content",
"targetFieldName": "merged_content"
},
{
"sourceFieldName": "/document/normalized_images/*/text",
"targetFieldName": "text"
},
{
"sourceFieldName": "/document/normalized_images/*/layoutText",
"targetFieldName": "layoutText"
},
{
"sourceFieldName": "/document/normalized_images/*/imageTags/*/name",
"targetFieldName": "imageTags"
},
{
"sourceFieldName": "/document/normalized_images/*/imageCaption",
"targetFieldName": "imageCaption"
},
{
"sourceFieldName": "/document/sentimentLabel",
"targetFieldName": "sentiment"
},
{
"sourceFieldName": "/document/topWords",
"targetFieldName": "top_words"
}
],
"cache": null,
"encryptionKey": null
}
- index.json
{
"@odata.context": "https://aisearchdemomc.search.windows.net/$metadata#indexes/$entity",
"@odata.etag": ""0x8DCA5D377A7CBE6"",
"name": "margies-index",
"defaultScoringProfile": null,
"fields": [
{
"name": "content",
"type": "Edm.String",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_storage_content_type",
"type": "Edm.String",
"searchable": false,
"filterable": false,
"retrievable": false,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_storage_size",
"type": "Edm.Int64",
"searchable": false,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": true,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_storage_last_modified",
"type": "Edm.DateTimeOffset",
"searchable": false,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": true,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_storage_content_md5",
"type": "Edm.String",
"searchable": false,
"filterable": false,
"retrievable": false,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_storage_name",
"type": "Edm.String",
"searchable": true,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": true,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_storage_path",
"type": "Edm.String",
"searchable": false,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": true,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_storage_file_extension",
"type": "Edm.String",
"searchable": false,
"filterable": false,
"retrievable": false,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_content_type",
"type": "Edm.String",
"searchable": false,
"filterable": false,
"retrievable": false,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_language",
"type": "Edm.String",
"searchable": false,
"filterable": false,
"retrievable": false,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_author",
"type": "Edm.String",
"searchable": true,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": true,
"facetable": true,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_title",
"type": "Edm.String",
"searchable": false,
"filterable": false,
"retrievable": false,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "metadata_creation_date",
"type": "Edm.DateTimeOffset",
"searchable": false,
"filterable": false,
"retrievable": false,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "locations",
"type": "Collection(Edm.String)",
"searchable": true,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "language",
"type": "Edm.String",
"searchable": true,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "keyphrases",
"type": "Collection(Edm.String)",
"searchable": true,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "merged_content",
"type": "Edm.String",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "text",
"type": "Collection(Edm.String)",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "layoutText",
"type": "Collection(Edm.String)",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "imageTags",
"type": "Collection(Edm.String)",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "imageCaption",
"type": "Collection(Edm.String)",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "sentiment",
"type": "Edm.String",
"searchable": true,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": true,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "url",
"type": "Edm.String",
"searchable": false,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": null,
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
},
{
"name": "top_words",
"type": "Edm.String",
"searchable": true,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"indexAnalyzer": null,
"searchAnalyzer": null,
"analyzer": "standard.lucene",
"normalizer": null,
"dimensions": null,
"vectorSearchProfile": null,
"vectorEncoding": null,
"synonymMaps": []
}
],
"scoringProfiles": [],
"corsOptions": null,
"suggesters": [],
"analyzers": [],
"normalizers": [],
"tokenizers": [],
"tokenFilters": [],
"charFilters": [],
"encryptionKey": null,
"similarity": {
"@odata.type": "#Microsoft.Azure.Search.BM25Similarity",
"k1": null,
"b": null
},
"semantic": null,
"vectorSearch": null
}
3