Skip to main content
"""
This agent transcribes an old written document from an image.
"""

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

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

agent = Agent(
    model=MistralChat(id="pixtral-12b-2409"),
    markdown=True,
)

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

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

if __name__ == "__main__":
    pass

Run the Example

# Clone and setup repo
git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/90_models/mistral

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python image_transcribe_document_agent.py