Power Platform Community Forum Thread Details

I dont get an error with:AzureAIFoundryInference.ChatCompletion(
    {
        'api-version': "2025-04-01-preview",
        model: "gpt-5-chat",
        max_tokens: 500,
        temperature: 1,
        
        messages: [
            {
                role: "user",
                content: Table(
                    {
                        Value: ParseJSON(
                            JSON(
                                {
                                    type: "text",
                                    text: TextInput2.Text
                                }
                            )
                        )
                    }
                )
            }
        ]
    }
)


but i do with:
AzureAIFoundryInference.ChatCompletion(
    {
        'api-version': "2025-04-01-preview",
        model: "gpt-5-chat",
        max_tokens: 500,
        temperature: 1,
        
        messages: [ 
            {
                role: "user",
                content: [ 
                    {
                        type: "text",
                        text: TextInput2.Text
                    }
                ]
            }
        ]
    }
)

The Core Problem

The API requires a standard content array: [{ "type": "text", "text": "..." }]. This structure works perfectly in the Power Automate version of this connector.
However, using this correct structure in Power Apps throws a validation error: Missing column 'messages.content.Value'.
If we modify the formula to satisfy this error by adding a Value column, the connector generates an incorrect JSON payload, wrapping the content inside an extra "Value": [...] layer.
The API then correctly rejects this malformed request, making a successful call from Power Apps impossible.

Any ideas on how to deal with this?

Categories:

AI Builder

Set(myVar, ParseJSON("{""myValue"" : ""Return in HTML format remove html header, " & TextInput2.Text & """}"));
Set(test,AzureAIFoundryInference.ChatCompletion( 
    {
        model:"gpt-5-chat",
        api_version :"2025-01-01-preview",
        top_p:1.0,
        temperature:1.0,
        max_tokens:16384,
        messages:([{role:"user",content:Table( {type:"text", Value:myVar.myValue})}])
        
    
    }
))

" can you try this out i found this when i was looking for some solutions for connections

If this solution helped you resolve your issue, kindly mark it as accepted — it makes it easier for others to find and also closes the discussion. If you found it useful, a Like ❤️ would be greatly appreciated!

🤝 Let’s connect on LinkedIn || 📘 Explore more on my articles