Vector embedding is not creating from skillset in azure portal via indexer

Arunkumar B 0 Reputation points
2024-06-05T14:51:58.5466667+00:00

Hi Team,

I am using azure AI search and open AI to create vector index. Using open AI, I can be able create embedding via REST API. The same i am trying to do with skillset by adding the skillset, index, datasource in the indexer. The data source I am using is azure blob where I have it as JSON document. I can be able to perform index and indexing also happing but embedding is not creating. I have tried multiple option but nothing worked. Please help on this.

 

Skillset :

{
  "@odata.context": "",
  "@odata.etag": "",
   "name": "skillset1717573457280",
  "description": "",
  "skills": [
    {
      "@odata.type": "#Microsoft.Skills.Text.AzureOpenAIEmbeddingSkill",
      "name": "#1",
      "description": "",
      "context": "/document/content",
       "resourceUri": "<URI>",
       "apiKey": "<redacted>",
      "deploymentId": "textembeddingmodel",
      "dimensions": 1536,
      "modelName": "text-embedding-3-small",
      "inputs": [
        {
          "name": "text",
          "source": "/document/content"
         }      
 ],
      "outputs": [
        {
          "name": "embedding",
          "targetName": "embedding"
        }
      ],
      "authIdentity": null
    }
  ],
  "cognitiveServices": {
    "@odata.type": "#Microsoft.Azure.Search.DefaultCognitiveServices",
    "description": null
  },
  "knowledgeStore": null,
  "indexProjections": null,
  "encryptionKey": null
} 


JSON Document used for indexing:

{"title":"asthma","content":"asthma ..."}

Azure AI Search
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.
834 questions
Azure OpenAI Service
Azure OpenAI Service
An Azure service that provides access to OpenAI’s GPT-3 models with enterprise capabilities.
2,543 questions
{count} votes