ocr with gemini over

Author: ked1108

.gitignore

@@ -1,2 +1,3 @@
 __pycache__/
 django
+.env

backend/ehr/ocr.py

@@ -1,51 +1,22 @@
-# import pytesseract
-# from PIL import Image
-# import io
-
-# def ocr_from_image(img):
-#     img = Image.open(io.BytesIO(img))
-#     text = pytesseract.image_to_string(img)
-#     return text
-
-# -*- coding: utf-8 -*-
-"""unisnipp_gemini.py
-
-Automatically generated by Colaboratory.
-
-Original file is located at
-    https://colab.research.google.com/drive/1JqguW6zZXGR67GygUfDqXGR9d-gLowuV
-"""
-
-import pathlib
+from dotenv import dotenv_values
 import textwrap
-
+from PIL import Image
+import io
 import google.generativeai as genai
-
-from IPython.display import display
-from IPython.display import Markdown
-from google.colab import userdata
-
+from IPython.display import Markdown    
 
 def to_markdown(text):
   text = text.replace('•', '  *')
   return Markdown(textwrap.indent(text, '> ', predicate=lambda _: True))
 
 
-GOOGLE_API_KEY=userdata.get('GOOGLE_API_KEY')
+GOOGLE_API_KEY=dotenv_values('.env')['GOOGLE_API_KEY']
 genai.configure(api_key=GOOGLE_API_KEY)
 
-import PIL.Image
-
-img = PIL.Image.open('jk.jpg')
-img
-
-model = genai.GenerativeModel('gemini-pro-vision')
-
-response = model.generate_content(["extract the text in proper way from this image", img], stream=True)
-response.resolve()
-to_markdown(response.text)
-
-response1 = model.generate_content(["Understand what the extracted text is completely and format it in key-value pair with proper indentation", img], stream=True)
-response1.resolve()
+def ocr_to_text(img):
+    img = Image.open(io.BytesIO(img))
+    model = genai.GenerativeModel('gemini-pro-vision')
 
-print(response1.text)
+    response = model.generate_content(["extract the text in proper way from this image", img], stream=True)
+    response.resolve()
+    return response.text