Plugins not working - no audio message

[HonkXL]

What happened?

Since a ahort time, no plugin is working, there comes the following message in log. Here I tried to create a image using Dall-E. I brings a message that the model requires a in or output of audio. The model is set to "gpt-40-audio-preview-2024-10-01" per default then selecting "Plugins", but it doesn't matter if I select here anything else.

[llm/error] [1:chain:AgentExecutor > 2:llm:ChatOpenAI] [1.98s] LLM run errored with error: "400 This model requires that either input content or output modality contain audio.\n\nError: 400 This model requires that either input content or output modality contain audio.\n at APIError.generate (/app/node_modules/@langchain/openai/node_modules/openai/error.js:45:20)\n at OpenAI.makeStatusError (/app/node_modules/@langchain/openai/node_modules/openai/core.js:293:33)\n at OpenAI.makeRequest (/app/node_modules/@langchain/openai/node_modules/openai/core.js:337:30)\n at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n at async /app/node_modules/@langchain/openai/dist/chat_models.cjs:1548:29\n at async RetryOperation._fn (/app/node_modules/p-retry/index.js:50:12)"

2025-01-22 09:47:38 error: [RunManager] handleLLMError: {"context":"plugins","conversationId":"e229fcfd-ecfb-498b-819f-5761adb1962e","initialMessageCount":2} 400 This model requires that either input content or output modality contain audio.

Steps to Reproduce

1. select new chat / Plugin
2. select any plugin like Dall-E
3. enter anything
4. get error message above.

What browsers are you seeing the problem on?

Microsoft Edge, Safari, Chrome, Firefox, Mobile (iOS)

Relevant log output

[llm/error] [1:chain:AgentExecutor > 2:llm:ChatOpenAI] [1.98s] LLM run errored with error: "400 This model requires that either input content or output modality contain audio.\n\nError: 400 This model requires that either input content or output modality contain audio.\n    at APIError.generate (/app/node_modules/@langchain/openai/node_modules/openai/error.js:45:20)\n    at OpenAI.makeStatusError (/app/node_modules/@langchain/openai/node_modules/openai/core.js:293:33)\n    at OpenAI.makeRequest (/app/node_modules/@langchain/openai/node_modules/openai/core.js:337:30)\n    at process.processTicksAndRejections (node:internal/process/task_queues:95:5)\n    at async /app/node_modules/@langchain/openai/dist/chat_models.cjs:1548:29\n    at async RetryOperation._fn (/app/node_modules/p-retry/index.js:50:12)"

2025-01-22 09:47:38 error: [RunManager] handleLLMError: {"context":"plugins","conversationId":"e229fcfd-ecfb-498b-819f-5761adb1962e","initialMessageCount":2} 400 This model requires that either input content or output modality contain audio.

Screenshots

No response

Code of Conduct

• I agree to follow this project's Code of Conduct

[danny-avila]

Please read this comment and the one under it:
#3291 (comment)