Azure AI Search
An Azure search service with built-in artificial intelligence capabilities that enrich information to help identify and explore relevant content at scale.
Unable to create vector index manually
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(121.6, 60%, 21%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EHK%3C/text%3E%3C/svg%3E)
Hari Krishna, Gudditi
0
Reputation points
Hi team,
I am trying to create a vector index manually creating index, skillset and indexer by json. But I am endedup in getting empty output. I am using a csv file as data source. Please verify below json and help me to find and fix the issue.
Below is the output I am getting:-
{
"@odata.context": "https://somename.search.windows.net/indexes('ritm-index')/$metadata#docs(*)",
"@odata.count": 0,
"value": []
}
Index:-
{
"@odata.etag": "\"0x8DE12CDD7065E6F\"",
"name": "ritm-index",
"fields": [
{
"name": "id",
"type": "Edm.String",
"searchable": false,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": true,
"synonymMaps": []
},
{
"name": "text_vector",
"type": "Collection(Edm.Single)",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"dimensions": 1536,
"vectorSearchProfile": "vector-profile-1761289758044",
"synonymMaps": []
},
{
"name": "number",
"type": "Edm.String",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"analyzer": "standard.lucene",
"synonymMaps": []
},
{
"name": "active",
"type": "Edm.String",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"analyzer": "standard.lucene",
"synonymMaps": []
},
{
"name": "createdBy",
"type": "Edm.String",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"analyzer": "standard.lucene",
"synonymMaps": []
},
{
"name": "description",
"type": "Edm.String",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"analyzer": "standard.lucene",
"synonymMaps": []
},
{
"name": "comments",
"type": "Edm.String",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"analyzer": "standard.lucene",
"synonymMaps": []
},
{
"name": "closedBy",
"type": "Edm.String",
"searchable": true,
"filterable": false,
"retrievable": true,
"stored": true,
"sortable": false,
"facetable": false,
"key": false,
"analyzer": "standard.lucene",
"synonymMaps": []
},
{
"name": "mergedText",
"type": "Edm.String",
"searchable": true,
"filterable": true,
"retrievable": true,
"stored": true,
"sortable": true,
"facetable": false,
"key": false,
"analyzer": "standard.lucene",
"synonymMaps": []
}
],
"scoringProfiles": [],
"suggesters": [],
"analyzers": [],
"normalizers": [],
"tokenizers": [],
"tokenFilters": [],
"charFilters": [],
"similarity": {
"@odata.type": "#Microsoft.Azure.Search.BM25Similarity"
},
"vectorSearch": {
"algorithms": [
{
"name": "vector-config-1761289760260",
"kind": "hnsw",
"hnswParameters": {
"metric": "cosine",
"m": 4,
"efConstruction": 400,
"efSearch": 500
}
}
],
"profiles": [
{
"name": "vector-profile-1761289758044",
"algorithm": "vector-config-1761289760260",
"vectorizer": "vectorizer-1761289808681"
}
],
"vectorizers": [
{
"name": "vectorizer-1761289808681",
"kind": "azureOpenAI",
"azureOpenAIParameters": {
"resourceUri": "https://somename.openai.azure.com",
"deploymentId": "text-embedding-ada-002",
"apiKey": "<redacted>",
"modelName": "text-embedding-ada-002"
}
}
],
"compressions": []
}
}
SkillSet:-
{
"@odata.etag": "\"0x8DE12CDF027244A\"",
"name": "ritm-skillset",
"description": "Merge multiple fields into a single merged text and generate embeddings for vector search",
"skills": [
{
"@odata.type": "#Microsoft.Skills.Util.ShaperSkill",
"name": "shaper-merge-fields",
"description": "Combine fields into a single merged text",
"context": "/document",
"inputs": [
{
"name": "number",
"source": "/document/number",
"inputs": []
},
{
"name": "createdBy",
"source": "/document/createdBy",
"inputs": []
},
{
"name": "description",
"source": "/document/description",
"inputs": []
},
{
"name": "comments",
"source": "/document/comments",
"inputs": []
},
{
"name": "closedBy",
"source": "/document/closedBy",
"inputs": []
}
],
"outputs": [
{
"name": "output",
"targetName": "mergedText"
}
]
},
{
"@odata.type": "#Microsoft.Skills.Text.AzureOpenAIEmbeddingSkill",
"name": "#2",
"context": "/document",
"resourceUri": "https://somename.openai.azure.com",
"apiKey": "<redacted>",
"deploymentId": "text-embedding-ada-002",
"dimensions": 1536,
"modelName": "text-embedding-ada-002",
"inputs": [
{
"name": "text",
"source": "/document/mergedText",
"inputs": []
}
],
"outputs": [
{
"name": "embedding",
"targetName": "text_vector"
}
]
}
]
}
Indexer :-
{
"@odata.context": "https://somename.search.windows.net/$metadata#indexers/$entity",
"@odata.etag": "\"0x8DE12CE03BB9B6C\"",
"name": "ritm-indexer",
"description": "Indexer to load data, merge text fields, and generate embeddings for vector search",
"dataSourceName": "ritms",
"skillsetName": "ritm-skillset",
"targetIndexName": "ritm-index",
"disabled": null,
"schedule": null,
"parameters": {
"batchSize": null,
"maxFailedItems": null,
"maxFailedItemsPerBatch": null,
"configuration": {
"parsingMode": "delimitedText",
"firstLineContainsHeaders": true,
"delimitedTextDelimiter": ","
}
},
"fieldMappings": [
{
"sourceFieldName": "number",
"targetFieldName": "number",
"mappingFunction": null
},
{
"sourceFieldName": "description",
"targetFieldName": "description",
"mappingFunction": null
},
{
"sourceFieldName": "comments",
"targetFieldName": "comments",
"mappingFunction": null
},
{
"sourceFieldName": "createdBy",
"targetFieldName": "createdBy",
"mappingFunction": null
},
{
"sourceFieldName": "closedBy",
"targetFieldName": "closedBy",
"mappingFunction": null
},
{
"sourceFieldName": "active",
"targetFieldName": "active",
"mappingFunction": null
}
],
"outputFieldMappings": [
{
"sourceFieldName": "/document/mergedText",
"targetFieldName": "mergedText",
"mappingFunction": null
},
{
"sourceFieldName": "/document/text_vector",
"targetFieldName": "text_vector",
"mappingFunction": null
}
],
"cache": null,
"encryptionKey": null
}
the vector index quota usage size is also 0. Issue is with the vector, but I am unable to find or fix this. Please help me to fix this.
My requirement is, I need my mergedText to have all the data of fields and it must be vectorized.
Azure AI Search
{count} votes
-
![](data:image/svg+xml, %3Csvg xmlns='http://www.w3.org/2000/svg' height='64' class='font-weight-bold' style='font: 600 30.11764705882353px "SegoeUI", Arial' width='64'%3E%3Ccircle fill='hsl(112.00000000000001, 86%, 20%)' cx='32' cy='32' r='32' /%3E%3Ctext x='50%25' y='55%25' dominant-baseline='middle' text-anchor='middle' fill='%23FFF' %3EVL%3C/text%3E%3C/svg%3E)
Vimal Lalani 1,735 Reputation points Microsoft External Staff Moderator2025-10-24T07:59:47.25+00:00 Could you please share the Sample.csv file, if possible, so that we can check for any errors during the index creation process?
-
Hari Krishna, Gudditi 0 Reputation points
2025-10-24T08:34:43.63+00:00 Hi @Vimal Lalani , Thanks for quick response.
The below is image is sample of csv file (unable to upload csv files here). The headers closed, closedBy and dayactive are empty or it may have values. I have around 900 rows of values. But the issue here is not with the csv file, I guess. because without vectorizer and text_vector field, this is working file, I am able to create an index correclt. Issue happens only when I try to create vector index, with text_vector and vector profile.
-
Hari Krishna, Gudditi 0 Reputation points
2025-10-24T08:59:23.2766667+00:00 Hi @Vimal Lalani , unable to upload csv here, so sending a sample excel below. Please check
number active created createdBy description comments closed closedBy day active TKT123456 TRUE 21/08/2025 15:18:19 m.a.sharma some text info some info and closed 21/08/2025 10:30:51 hari.g.krishna 45890.64 TKT123457 FALSE 25/08/2025 15:18:19 hari.g.krishna some description -
Hari Krishna, Gudditi 0 Reputation points
2025-10-25T13:25:39.6566667+00:00 Hi @Vimal Lalani ,
The above issue is because of skill AzureOpenAIEmbeddingSkill execution fail. Below is the error:
"Could not execute skill because one or more skill input was invalid.Required skill input was not of the expected type 'String'. Name: 'text', Source: '/document/mergedText'. Expression language parsing issues"
The shaperskill is returning output in json form but the input AzureOpenAIEmbeddingSkill is expecting string.Please help me how can I concatenate or merge my fields to a single string.
Sign in to comment
Sign in to answer