Image to Text with Gemini Pro Vision Model in Python Notebook

!pip install -q -U google-generativeai

import pathlib
import textwrap

import google.generativeai as genai

from IPython.display import display
from IPython.display import Markdown


def to_markdown(text):
  text = text.replace('•', '  *')
  return Markdown(textwrap.indent(text, '> ', predicate=lambda _: True))

import os

gemini_api_key = os.environ["GEMINI_API_KEY"]
genai.configure(api_key=gemini_api_key)

#list of available models

for m in genai.list_models():
  if 'generateContent' in m.supported_generation_methods:
    print(m.name)

model = genai.GenerativeModel('gemini-pro-vision')

import PIL.Image

img = PIL.Image.open('invoice_test.jpg')
img

response = model.generate_content(img)

to_markdown(response.text)