> ## Documentation Index
> Fetch the complete documentation index at: https://phidatainc.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Mistral Image OCR With Structured Output

> Extract receipt data into a structured schema with Ministral 14B.

The source-fidelity code uses deprecated `pixtral-12b-2409`. Replace it with `ministral-14b-2512` before running the example.

```python image_ocr_with_structured_output.py theme={null}
"""
Mistral Image Ocr With Structured Output
========================================

Cookbook example for `mistral/image_ocr_with_structured_output.py`.
"""

from typing import List

from agno.agent import Agent
from agno.media import Image
from agno.models.mistral.mistral import MistralChat
from pydantic import BaseModel

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------


class GroceryItem(BaseModel):
    item_name: str
    price: float


class GroceryListElements(BaseModel):
    bill_number: str
    items: List[GroceryItem]
    total_price: float


agent = Agent(
    model=MistralChat(id="pixtral-12b-2409"),
    instructions=[
        "Extract the text elements described by the user from the picture",
    ],
    output_schema=GroceryListElements,
    markdown=True,
)

agent.print_response(
    "From this restaurant bill, extract the bill number, item names and associated prices, and total price and return it as a string in a Json object",
    images=[Image(url="https://i.imghippo.com/files/kgXi81726851246.jpg")],
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------

if __name__ == "__main__":
    pass
```

## Run the Example

<Steps>
  <Snippet file="create-venv-step.mdx" />

  <Step title="Install dependencies">
    ```bash theme={null}
    uv pip install -U agno mistralai
    ```
  </Step>

  <Step title="Export your Mistral API key">
    <CodeGroup>
      ```bash Mac/Linux theme={null}
      export MISTRAL_API_KEY="your_mistral_api_key_here"
      ```

      ```bash Windows theme={null}
      $Env:MISTRAL_API_KEY="your_mistral_api_key_here"
      ```
    </CodeGroup>
  </Step>

  <Step title="Update the model">
    When saving the code, replace `pixtral-12b-2409` with `ministral-14b-2512`.
  </Step>

  <Step title="Run the example">
    Save the code above as `image_ocr_with_structured_output.py`, then run:

    ```bash theme={null}
    python image_ocr_with_structured_output.py
    ```
  </Step>
</Steps>

Full source: [cookbook/90\_models/mistral/image\_ocr\_with\_structured\_output.py](https://github.com/agno-agi/agno/blob/main/cookbook/90_models/mistral/image_ocr_with_structured_output.py)