GenAI Prompt skill

The GenAI (Generative AI) Prompt skill executes a chat completion request against a Large Language Model (LLM) deployed in Azure AI Foundry or Azure OpenAI in Azure AI Foundry Models.

Use this capability to create new information that can be indexed and stored as searchable content. Examples include verbalize images, summarize larger passages, simplify complex content, or any other task that an LLM can perform. The skill supports text, image, and multimodal content such as a PDF that contains text and images. It's common to use this skill combined with a data chunking skill. The following tutorials demonstrate the image verbalization scenarios with two different data chunking techniques:

• Tutorial: Index mixed content using image verbalizations and the Document Layout skill

• Tutorial: Index mixed content using image verbalizations and the Document Extraction skill

The GenAI Prompt skill is available in the 2025-05-01-preview REST API only.

Supported models

You can use any chat completion inference model deployed in AI Foundry, such as GPT models, Deepseek R#, Llama-4-Mavericj, Cohere-command-r, and so forth.

Billing is based on the pricing of the model you use.

Prerequisites

• A deployed chat completion model (for example gpt-4o or any compatible Open Source Software (OSS) model) in Azure AI Foundry or Azure OpenAI.

  • Copy the endpoint from Models + Endpoints in the Foundry portal or from the Azure OpenAI resource subdomain (*.openai.azure.com).

  • Provide this endpoint in the Uri parameter of your skill definition.

• Authentication can be key-based with an API key from your Azure AI Foundry or Azure OpenAI resource. However, we recommend role-based access using a search service managed identity assigned to a role.

  • On Azure OpenAI, assign Cognitive Services OpenAI User to the managed identity.

  • For AI Foundry models, assign Azure AI User.

@odata.type

#Microsoft.Skills.Custom.ChatCompletionSkill

Data limits

Skill parameters

* Exactly one of apiKey, authIdentity, or the service’s system-assigned identity must be used.

commonModelParameters defaults

Skill inputs

Skill outputs

Sample definitions

Text-only summarization

{
  "@odata.type": "#Microsoft.Skills.Custom.ChatCompletionSkill",
  "name": "Summarizer",
  "description": "Summarizes document content.",
  "context": "/document",
  "timeout": "PT30S",
  "inputs": [
    { "name": "text", "source": "/document/content" },
    { "name": "systemMessage", "source": "='You are a concise AI assistant.'" },
    { "name": "userMessage", "source": "='Summarize the following text:'" }
  ],
  "outputs": [ { "name": "response" } ],
  "uri": "https://demo.openai.azure.com/openai/deployments/gpt-4o/chat/completions",
  "apiKey": "<api-key>",
  "commonModelParameters": { "temperature": 0.3 }
}

Text + image description

{
  "@odata.type": "#Microsoft.Skills.Custom.ChatCompletionSkill",
  "name": "Image Describer",
  "context": "/document/normalized_images/*",
  "inputs": [
    { "name": "image", "source": "/document/normalized_images/*/data" },
    { "name": "imageDetail", "source": "=high" },
    { "name": "systemMessage", "source": "='You are a useful AI assistant.'" },
    { "name": "userMessage", "source": "='Describe this image:'" }
  ],
  "outputs": [ { "name": "response" } ],
  "uri": "https://demo.openai.azure.com/openai/deployments/gpt-4o/chat/completions",
  "authIdentity": "11111111-2222-3333-4444-555555555555",
  "responseFormat": { "type": "text" }
}

Structured numerical fact-finder

{
  "@odata.type": "#Microsoft.Skills.Custom.ChatCompletionSkill",
  "name": "NumericalFactFinder",
  "context": "/document",
  "inputs": [
    { "name": "systemMessage", "source": "='You are an AI assistant that helps people find information.'" },
    { "name": "userMessage", "source": "='Find all the numerical data and put it in the specified fact format.'"}, 
    { "name": "text", "source": "/document/content" }
  ],
  "outputs": [ { "name": "response" } ],
  "uri": "https://demo.openai.azure.com/openai/deployments/gpt-4o/chat/completions",
  "apiKey": "<api-key>",
  "responseFormat": {
    "type": "json_schema",
    "jsonSchemaProperties": {
      "name": "NumericalFactObj",
      "strict": true,
      "schema": {
        "type": "object",
        "properties": {
          "facts": {
            "type": "array",
            "items": {
              "type": "object",
              "properties": {
                "number": { "type": "number" },
                "fact": { "type": "string" }
              },
              "required": [ "number", "fact" ]
            }
          }
        },
        "required": [ "facts" ],
        "additionalProperties": false
      }
    }
  }
}

Sample output (truncated)

{
  "response": {
    "facts": [
      { "number": 32.0, "fact": "Jordan scored 32 points per game in 1986-87." },
      { "number": 6.0,  "fact": "He won 6 NBA championships." }
    ]
  },
  "usageInformation": {
    "usage": {
      "completion_tokens": 203,
      "prompt_tokens": 248,
      "total_tokens": 451
    }
  }
}

Best practices

• Chunk long documents with the Text Split skill to stay within the model’s context window.
• For high-volume indexing, dedicate a separate model deployment to this skill so that token quotas for query-time RAG workloads remain unaffected.
• To minimize latency, co-locate the model and your Azure AI Search service in the same Azure region.
• Use responseFormat.json_schema with GPT-4o for reliable structured extraction and easier mapping to index fields.
• Monitor token usage and submit quota-increase requests if the indexer saturates your Tokens per Minute (TPM) limits.

Errors and warnings

See also

• Azure AI Search built-in indexers
• Integrated vectorization
• How to define a skillset
• How to generate chat completions with Azure AI model inference (Azure AI Foundry)
• Structured outputs in Azure OpenAI