[BUG CLIENT]: OCR data extraction example gives an ValidationError: 2 validation errors for Unmarshaller Azure Foundry Model

[jdvala-hash]

Python -VV

Python 3.12.12 (main, Dec 17 2025, 21:07:08) [Clang 21.1.4]

Pip Freeze

alembic==1.18.3
annotated-doc==0.0.4
annotated-types==0.7.0
anyio==4.12.1
appnope==0.1.4
argon2-cffi==25.1.0
argon2-cffi-bindings==25.1.0
arrow==1.4.0
asgiref==3.11.0
asttokens==3.0.1
async-lru==2.1.0
attrs==25.4.0
azure-ai-ml==1.24.0
azure-common==1.1.28
azure-core==1.38.0
azure-core-tracing-opentelemetry==1.0.0b12
azure-identity==1.19.0
azure-mgmt-core==1.6.0
azure-monitor-opentelemetry==1.8.4
azure-monitor-opentelemetry-exporter==1.0.0b46
azure-storage-blob==12.28.0
azure-storage-file-datalake==12.23.0
azure-storage-file-share==12.24.0
babel==2.18.0
bandit==1.8.0
beautifulsoup4==4.14.3
bidict==0.23.1
bleach==6.3.0
boolean.py==5.0
boto3==1.42.41
botocore==1.42.41
bpemb==0.3.6
build==1.4.0
CacheControl==0.14.4
certifi==2026.1.4
cffi==2.0.0
cfgv==3.5.0
charset-normalizer==3.4.4
cleanco==2.3
click==8.3.1
cloudpathlib==0.23.0
colorama==0.4.6
comm==0.2.3
coverage==7.13.1
cramjam==2.11.0
cryptography==46.0.5
cyclonedx-python-lib==7.6.2
debugpy==1.8.20
decorator==5.2.1
deepparse==0.9.14
defusedxml==0.7.1
detect-secrets==1.5.0
distlib==0.4.0
dnspython==2.8.0
DoubleMetaphone==1.2
email-validator==2.3.0
et_xmlfile==2.0.0
eval_type_backport==0.3.1
Events==0.5
executing==2.2.1
fastapi==0.128.0
fastapi-cli==0.0.20
fastapi-cloud-cli==0.11.0
fastar==0.8.0
fasteners==0.20
fastjsonschema==2.21.2
fastparquet==2025.12.0
fasttext-wheel==0.9.2
filelock==3.20.3
fqdn==1.5.1
fsspec==2026.1.0
gensim==4.4.0
google-api-core==2.29.0
google-auth==2.48.0
google-cloud-core==2.5.0
google-cloud-storage==3.9.0
google-crc32c==1.8.0
google-resumable-media==2.8.0
googleapis-common-protos==1.72.0
granian==2.7.0
grpcio==1.76.0
h11==0.16.0
hf-xet==1.2.0
html5lib==1.1
httpcore==1.0.9
httptools==0.7.1
httpx==0.28.1
huggingface_hub==1.4.0
identify==2.6.16
idna==3.11
importlib_metadata==8.7.1
iniconfig==2.3.0
invoke==2.2.1
ipdb==0.13.13
ipykernel==7.2.0
ipython==9.10.0
ipython_pygments_lexers==1.1.1
ipywidgets==8.1.8
isodate==0.7.2
isoduration==20.11.0
jedi==0.19.2
Jinja2==3.1.6
jmespath==1.1.0
json5==0.13.0
jsonpointer==3.0.0
jsonschema==4.26.0
jsonschema-specifications==2025.9.1
jupyter-events==0.12.0
jupyter-lsp==2.3.0
jupyter_client==8.8.0
jupyter_core==5.9.1
jupyter_server==2.17.0
jupyter_server_terminals==0.5.4
jupyterlab==4.5.3
jupyterlab_pygments==0.3.0
jupyterlab_server==2.28.0
jupyterlab_widgets==3.0.16
lark==1.3.1
license-expression==30.4.4
lightning-utilities==0.15.2
lz4==4.4.5
Mako==1.3.10
markdown-it-py==4.0.0
MarkupSafe==3.0.3
marshmallow==4.2.0
matplotlib-inline==0.2.1
mdurl==0.1.2
mistralai==1.12.3
mistune==3.2.0
mpmath==1.3.0
msal==1.34.0
msal-extensions==1.3.1
msgpack==1.1.2
msrest==0.7.1
mypy==1.13.0
mypy_extensions==1.1.0
nbclient==0.10.4
nbconvert==7.17.0
nbformat==5.10.4
nbstripout==0.8.1
nest-asyncio==1.6.0
networkx==3.6.1
nodeenv==1.10.0
notebook_shim==0.2.4
numpy==2.4.1
oauthlib==3.3.1
openpyxl==3.1.5
opensearch-protobufs==0.19.0
opensearch-py==3.1.0
opentelemetry-api==1.39.1
opentelemetry-exporter-otlp-proto-common==1.39.1
opentelemetry-exporter-otlp-proto-http==1.39.1
opentelemetry-instrumentation==0.60b0
opentelemetry-instrumentation-asgi==0.60b0
opentelemetry-instrumentation-dbapi==0.60b0
opentelemetry-instrumentation-django==0.60b0
opentelemetry-instrumentation-fastapi==0.60b0
opentelemetry-instrumentation-flask==0.60b0
opentelemetry-instrumentation-psycopg2==0.60b0
opentelemetry-instrumentation-requests==0.60b0
opentelemetry-instrumentation-urllib==0.60b0
opentelemetry-instrumentation-urllib3==0.60b0
opentelemetry-instrumentation-wsgi==0.60b0
opentelemetry-proto==1.39.1
opentelemetry-resource-detector-azure==0.1.5
opentelemetry-sdk==1.39.1
opentelemetry-semantic-conventions==0.60b1
opentelemetry-util-http==0.60b0
packageurl-python==0.17.6
packaging==25.0
pandas==2.3.3
pandocfilters==1.5.1
parso==0.8.5
pexpect==4.9.0
pip-api==0.0.34
pip-requirements-parser==32.0.1
pip-tools==7.5.2
pip_audit==2.7.3
platformdirs==4.5.1
pluggy==1.6.0
postal==1.1.11
Poutyne==1.17.4
pre_commit==4.0.1
probableparsing==0.0.1
probablepeople==0.5.6
prometheus_client==0.24.1
prompt_toolkit==3.0.52
proto-plus==1.27.1
protobuf==6.33.5
psutil==7.2.1
ptyprocess==0.7.0
pure_eval==0.2.3
py-serializable==1.1.2
pyasn1==0.6.2
pyasn1_modules==0.4.2
pybind11==3.0.1
pycparser==2.23
pydantic==2.12.5
pydantic-extra-types==2.11.0
pydantic-settings==2.12.0
pydantic_core==2.41.5
pydash==8.0.5
pydocstyle==6.3.0
Pygments==2.19.2
PyJWT==2.10.1
pymagnitude-light==0.1.147
pyparsing==3.3.1
pyproject_hooks==1.2.0
pytest==8.3.4
pytest-cov==6.0.0
python-crfsuite==0.9.12
python-dateutil==2.9.0.post0
python-dotenv==1.2.1
python-engineio==4.13.0
python-json-logger==4.0.0
python-multipart==0.0.22
python-socketio==5.16.0
pytz==2025.2
PyYAML==6.0.3
pyzmq==27.1.0
RapidFuzz==3.14.3
redis==7.1.0
referencing==0.37.0
reflex==0.8.26
reflex-hosting-cli==0.1.61
regex==2026.1.15
requests==2.32.4
requests-oauthlib==2.0.0
rfc3339-validator==0.1.4
rfc3986-validator==0.1.1
rfc3987-syntax==1.1.0
rich==14.2.0
rich-toolkit==0.17.1
rignore==0.7.6
rpds-py==0.30.0
rsa==4.9.1
ruff==0.8.4
s3transfer==0.16.0
safetensors==0.7.0
scipy==1.17.0
Send2Trash==2.1.0
sentencepiece==0.2.1
sentry-sdk==2.50.0
setuptools==80.9.0
shellingham==1.5.4
simple-websocket==1.1.0
six==1.17.0
smart_open==7.5.0
snowballstemmer==3.0.1
sortedcontainers==2.4.0
soupsieve==2.8.3
SQLAlchemy==2.0.46
sqlmodel==0.0.32
stack-data==0.6.3
starlette==0.50.0
stevedore==5.6.0
strictyaml==1.7.3
structlog==25.5.0
sympy==1.14.0
terminado==0.18.1
tinycss2==1.4.0
tokenizers==0.22.2
toml==0.10.2
torch==2.10.0
torchmetrics==1.8.2
tornado==6.5.4
tqdm==4.67.1
traitlets==5.14.3
transformers==5.0.0
typer==0.21.1
typer-slim==0.21.1
typing-inspection==0.4.2
typing_extensions==4.15.0
tzdata==2025.3
uri-template==1.3.0
urllib3==2.6.3
uvicorn==0.40.0
uvloop==0.22.1
virtualenv==20.36.1
watchfiles==1.1.1
wcwidth==0.5.3
webcolors==25.10.0
webencodings==0.5.1
websocket-client==1.9.0
websockets==16.0
wheel==0.45.1
widgetsnbextension==4.0.15
wrapt==1.17.3
wsproto==1.3.2
xxhash==3.6.0
zipp==3.23.0

Reproduction Steps

1. Trying out the pdf extraction example from the cookbook (https://github.com/mistralai/cookbook/blob/main/mistral/ocr/data_extraction.ipynb)
2. Using MistralAzure client.
3. I used the following snippet

from mistralai.extra import response_format_from_pydantic_model
from pydantic import BaseModel, Field
from mistralai_azure import MistralAzure

client = MistralAzure(azure_endpoint=endpoint, azure_api_key=api_key)

class Item(BaseModel):
    item_1: str
    item_2: str

annotations_response = client.ocr.process(
    model="mistral-document-ai-2505",
    pages=[1],
    document={
        "type": "document_url",
        "document_url": f"data:image/png;base64,{b64}"
    },
    document_annotation_format=response_format_from_pydantic_model(Item),
    include_image_base64=True
)

4. I get the following 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

Expected Behavior

The model should have behaved same as in the cookbook.

P.S. I did not test with the Mistral's API.

Additional Context

No response

Suggested Solutions

No response