Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

422 status code "invalid input" from Azure AI (OpenAI compatible) #83

Open
johnib opened this issue Feb 12, 2025 · 0 comments
Open

422 status code "invalid input" from Azure AI (OpenAI compatible) #83

johnib opened this issue Feb 12, 2025 · 0 comments

Comments

@johnib
Copy link

johnib commented Feb 12, 2025

I am unable to use my Azure AI instance running deepseek-r1 model.

After filling in the prompts depth/etc, I'm getting this exception:

Creating research plan...
APICallError [AI_APICallError]: invalid input error
    at <anonymous> (~/repos/deep-research/node_modules/@ai-sdk/provider-utils/src/response-handler.ts:59:16)
    at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
    at async postToApi (~/repos/deep-research/node_modules/@ai-sdk/provider-utils/src/post-to-api.ts:81:28)
    at async OpenAIChatLanguageModel.doGenerate (~/repos/deep-research/node_modules/@ai-sdk/openai/src/openai-chat-language-model.ts:367:50)
    at async fn (~/repos/deep-research/node_modules/ai/core/generate-object/generate-object.ts:489:32)
    at async <anonymous> (~/repos/deep-research/node_modules/ai/core/telemetry/record-span.ts:18:22)
    at async _retryWithExponentialBackoff (~/repos/deep-research/node_modules/ai/util/retry-with-exponential-backoff.ts:36:12)
    at async fn (~/repos/deep-research/node_modules/ai/core/generate-object/generate-object.ts:457:34)
    at async <anonymous> (~/repos/deep-research/node_modules/ai/core/telemetry/record-span.ts:18:22)
    at async generateFeedback (~/repos/deep-research/src/feedback.ts:14:24) {
  cause: undefined,
  url: 'https://DeepSeek-R1-<redacted>.eastus2.models.ai.azure.com/v1/chat/completions',
  requestBodyValues: {
    model: 'deepseek-r1',
    logit_bias: undefined,
    logprobs: undefined,
    top_logprobs: undefined,
    user: undefined,
    parallel_tool_calls: undefined,
    max_tokens: undefined,
    temperature: 0,
    top_p: undefined,
    frequency_penalty: undefined,
    presence_penalty: undefined,
    response_format: { type: 'json_schema', json_schema: [Object] },
    stop: undefined,
    seed: undefined,
    max_completion_tokens: undefined,
    store: undefined,
    metadata: undefined,
    prediction: undefined,
    reasoning_effort: undefined,
    messages: [ [Object], [Object] ]
  },
  statusCode: 422,
  responseHeaders: {
    'azureml-model-session': 'dep-dpr1-eu2-250211023104',
    'content-length': '292',
    'content-type': 'application/json',
    date: 'Wed, 12 Feb 2025 21:43:45 GMT',
    'ms-azureml-model-error-reason': 'model_error',
    'ms-azureml-model-error-statuscode': '422',
    'request-context': 'appId=cid-v1:b80100f5-1286-423d-967f-3517f665186d',
    'x-ms-client-request-id': '6307a972-af27-4161-8b29-33d8faa10810',
    'x-ms-rai-invoked': 'false',
    'x-request-id': '1f04a13e-8025-40a6-abc2-ce17bce584e2'
  },
  responseBody: `{"error":{"code":"Invalid input","status":422,"message":"invalid input error","details":[{"type":"value_error","loc":["body","response_format","type"],"msg":"Value error, Response format was json_schema but must be either 'text' or 'json_object'.","input":"json_schema","ctx":{"error":{}}}]}}`,
  isRetryable: false,
  data: { error: { message: 'invalid input error', code: 'Invalid input' } },
  [Symbol(vercel.ai.error)]: true,
  [Symbol(vercel.ai.error.AI_APICallError)]: true

What can I do? thanks

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant