Image Transcribe Document Agent

Transcribe a scanned document image into text with a Ministral 14B agent.

Code

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

agent = Agent(
    model=MistralChat(id="ministral-14b-2512"),
    markdown=True,
)

agent.print_response(
    "Transcribe this document.",
    images=[
        Image(url="https://ciir.cs.umass.edu/irdemo/hw-demo/page_example.jpg"),
    ],
)

Usage

Set up your virtual environment

uv venv --python 3.12
source .venv/bin/activate

Set your API key

export MISTRAL_API_KEY=xxx

Install dependencies

uv pip install -U mistralai agno

Run Agent

Save the code above as image_transcribe_document_agent.py, then run:

python image_transcribe_document_agent.py