Dall-e-3 on Azure ENV Variables

[mrmarten]

Hello,

Is it possible to still configure dall-e-3 using only environment variables?

Regular GPT models work fine.

dall-e-3 distrubutions are working fine on other services on Azure.

Here is the log:
2024-07-04T09:14:12.2583639Z 2024-07-04T09:14:12.258Z error: Failed to get voices: Configuration or TTS schema is missing 2024-07-04T09:14:14.3317799Z 2024-07-04T09:14:14.331Z error: Failed to get voices: Configuration or TTS schema is missing 2024-07-04T09:14:32.3887954Z 2024-07-04T09:14:32.388Z debug: [AskController] 2024-07-04T09:14:32.3925193Z { 2024-07-04T09:14:32.3932777Z text: "Skapa en bild på en stol", 2024-07-04T09:14:32.3940424Z conversationId: null, 2024-07-04T09:14:32.3947819Z endpoint: "azureOpenAI", 2024-07-04T09:14:32.3955586Z chatGptLabel: null, 2024-07-04T09:14:32.3963196Z promptPrefix: null, 2024-07-04T09:14:32.3970989Z resendFiles: true, 2024-07-04T09:14:32.3976339Z imageDetail: "auto", 2024-07-04T09:14:32.3981376Z iconURL: undefined, 2024-07-04T09:14:32.3986339Z greeting: undefined, 2024-07-04T09:14:32.3992353Z spec: undefined, 2024-07-04T09:14:32.3998467Z maxContextTokens: undefined, 2024-07-04T09:14:32.4003512Z modelOptions.model: "dall-e-3", 2024-07-04T09:14:32.4009636Z modelOptions.temperature: 1, 2024-07-04T09:14:32.4015607Z modelOptions.top_p: 1, 2024-07-04T09:14:32.4020560Z modelOptions.presence_penalty: 0, 2024-07-04T09:14:32.4026243Z modelOptions.frequency_penalty: 0, 2024-07-04T09:14:32.4032456Z modelOptions.stop: undefined, 2024-07-04T09:14:32.4038397Z modelOptions.max_tokens: undefined, 2024-07-04T09:14:32.4043388Z // 21 openAI(s) 2024-07-04T09:14:32.4049097Z modelsConfig.openAI: ["gpt-4o","gpt-3.5-turbo","gpt-3.5-turbo-0125","gpt-4-turbo","gpt-4-turbo-2024-04-09","gpt-4-0125-preview","gpt-4-turbo-preview","gpt-4-1106-preview","gpt-3.5-turbo-1106","gpt-3.5-turbo-16k-0613","gpt-3.5-turbo-16k","gpt-4","gpt-4-0314","gpt-4-32k-0314","gpt-4-0613","gpt-3.5-turbo-0613","gpt-4-vision-preview","gpt-3.5-turbo-instruct-0914","gpt-3.5-turbo-0301","gpt-3.5-turbo-instruct","text-davinci-003"], 2024-07-04T09:14:32.4055082Z // 12 google(s) 2024-07-04T09:14:32.4060943Z modelsConfig.google: ["gemini-pro","gemini-pro-vision","chat-bison","chat-bison-32k","codechat-bison","codechat-bison-32k","text-bison","text-bison-32k","text-unicorn","code-gecko","code-bison","code-bison-32k"], 2024-07-04T09:14:32.4066067Z // 10 anthropic(s) 2024-07-04T09:14:32.4072145Z modelsConfig.anthropic: ["claude-3-opus-20240229","claude-3-sonnet-20240229","claude-3-haiku-20240307","claude-2.1","claude-2","claude-1.2","claude-1","claude-1-100k","claude-instant-1","claude-instant-1-100k"], 2024-07-04T09:14:32.4078278Z // 5 gptPlugin(s) 2024-07-04T09:14:32.4083763Z modelsConfig.gptPlugins: ["gpt-35-turbo","gpt-4","gpt-4o","gpt-4-vision-preview","dall-e-3"], 2024-07-04T09:14:32.4088871Z // 5 azureOpenAI(s) 2024-07-04T09:14:32.4094586Z modelsConfig.azureOpenAI: ["gpt-35-turbo","gpt-4","gpt-4o","gpt-4-vision-preview","dall-e-3"], 2024-07-04T09:14:32.4101551Z // 2 bingAI(s) 2024-07-04T09:14:32.4106946Z modelsConfig.bingAI: ["BingAI","Sydney"], 2024-07-04T09:14:32.4112941Z // 2 chatGPTBrowser(s) 2024-07-04T09:14:32.4118810Z modelsConfig.chatGPTBrowser: ["text-davinci-002-render-sha","gpt-4"], 2024-07-04T09:14:32.4124372Z // 16 assistant(s) 2024-07-04T09:14:32.4129587Z modelsConfig.assistants: ["gpt-4o","gpt-3.5-turbo","gpt-3.5-turbo-0125","gpt-4-turbo","gpt-4-turbo-2024-04-09","gpt-4-0125-preview","gpt-4-turbo-preview","gpt-4-1106-preview","gpt-3.5-turbo-1106","gpt-3.5-turbo-16k-0613","gpt-3.5-turbo-16k","gpt-4","gpt-4-0314","gpt-4-32k-0314","gpt-4-0613","gpt-3.5-turbo-0613"], 2024-07-04T09:14:32.4135451Z // 21 azureAssistant(s) 2024-07-04T09:14:32.4141259Z modelsConfig.azureAssistants: ["gpt-4o","gpt-3.5-turbo","gpt-3.5-turbo-0125","gpt-4-turbo","gpt-4-turbo-2024-04-09","gpt-4-0125-preview","gpt-4-turbo-preview","gpt-4-1106-preview","gpt-3.5-turbo-1106","gpt-3.5-turbo-16k-0613","gpt-3.5-turbo-16k","gpt-4","gpt-4-0314","gpt-4-32k-0314","gpt-4-0613","gpt-3.5-turbo-0613","gpt-4-vision-preview","gpt-3.5-turbo-instruct-0914","gpt-3.5-turbo-0301","gpt-3.5-turbo-instruct","text-davinci-003"], 2024-07-04T09:14:32.4146227Z } 2024-07-04T09:14:32.4152432Z 2024-07-04T09:14:32.389Z debug: [BaseClient] Loading history: 2024-07-04T09:14:32.4158358Z { 2024-07-04T09:14:32.4163292Z conversationId: "63bc6044-9846-4304-9b3d-5f36c163b2b1", 2024-07-04T09:14:32.4168963Z parentMessageId: "00000000-0000-0000-0000-000000000000", 2024-07-04T09:14:32.4174870Z } 2024-07-04T09:14:32.7390638Z 2024-07-04T09:14:32.738Z error: [handleAbortError] AI response error; aborting request: Failed to send message. HTTP 400 - {"error":{"code":"OperationNotSupported","message":"The cha... [truncated]

[jsiegmund]

It's been a while, but have you managed to get this working and could you maybe share your config in that case? I'm facing the exact same issue using DALL-E-3 deployed in Azure OpenAI.