Skip to content

OCR data extraction example gives an ValidationError: 2 validation errors for Unmarshaller Azure Foundry Model #242

@jdvala-hash

Description

@jdvala-hash

Hi,

I was trying out the data extraction notebook example (product_datasheet_analysis) and came across an error.

ValidationError: 2 validation errors for Unmarshaller
body.nullable[ResponseFormat]
  Input should be a valid dictionary or instance of ResponseFormat [type=model_type, input_value=ResponseFormat(type='json...n=Unset(), strict=True)), input_type=ResponseFormat]
    For further information visit https://errors.pydantic.dev/2.12/v/model_type
body.Unset
  Input should be a valid dictionary or instance of Unset [type=model_type, input_value=ResponseFormat(type='json...n=Unset(), strict=True)), input_type=ResponseFormat]
    For further information visit https://errors.pydantic.dev/2.12/v/model_type

The only difference is that I am not using Mistral API directly rather I am using MistralAzure client.

It would be awesome to know what is going on here.

P.S. I haven't tested it with Mistral API (Company does not allow).

Thank you.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions