init project

.env

@@ -0,0 +1 @@
+API_KEY = "AIzaSyCmchquNos99yozM_hN-kBQVAY4YDPOSxA"

api.py

@@ -0,0 +1,73 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import asyncio
+from typing import List, Union
+import uvicorn
+import logging
+from datetime import datetime
+import pytz
+from main import main
+
+# Logging setup
+logging.basicConfig(filename="dataExtractOCR.log", filemode='w')
+logger = logging.getLogger("NID")
+logger.setLevel(logging.DEBUG)
+file_handler = logging.FileHandler("dataExtractOCR.log")
+logger.addHandler(file_handler)
+
+total_done = 0
+total_error = 0
+
+app = FastAPI()
+
+class Item(BaseModel):
+    url: str
+
+def get_bd_time():
+    bd_timezone = pytz.timezone("Asia/Dhaka")
+    time_now = datetime.now(bd_timezone)
+    current_time = time_now.strftime("%I:%M:%S %p")
+    return current_time
+
+async def process_item(item: Item):
+    try:
+        result = await main(item.url)
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error in process_item: {str(e)}")
+
+async def process_items(items: Union[Item, List[Item]]):
+    try:
+        if isinstance(items, list):
+            coroutines = [process_item(item) for item in items]
+            results = await asyncio.gather(*coroutines)
+        else:
+            results = await process_item(items)
+        return results
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Error in process_items: {str(e)}")
+
+@app.get("/status")
+async def status():
+    try:
+        return "Server is running"
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=f"Status Error: {str(e)}")
+
+@app.post("/ocr")
+async def create_items(items: Union[Item, List[Item]]):
+    global total_done, total_error
+    try:
+        total_done += 1
+        results = await process_items(items)
+        if results:
+            logger.info(f"Time: {get_bd_time()}, Successful Execution: {total_done}, BODY: {items}, Result: {results}")
+        return {"extractedData": results}
+    except Exception as e:
+        total_error += 1
+        logger.info(f"Time: {get_bd_time()}, Failed Execution: {total_error}, BODY: {items}")
+        logger.error(str(e))
+        raise HTTPException(status_code=500, detail=f"create_items Error: {str(e)}")
+
+if __name__ == "__main__":
+    uvicorn.run(app, host="127.0.0.1", port=8080)

cloudVisionAPI.json

@@ -0,0 +1,13 @@
+{
+  "type": "service_account",
+  "project_id": "our-card-401407",
+  "private_key_id": "356ef6d1447b5273c1545a07a06c28a376e021cb",
+  "private_key": "-----BEGIN PRIVATE KEY-----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\nfINloLJG9khxEi/5SP1ZqAz8\n-----END PRIVATE KEY-----\n",
+  "client_email": "md-rakibul-hasan-naym@our-card-401407.iam.gserviceaccount.com",
+  "client_id": "111450790892641364901",
+  "auth_uri": "https://accounts.google.com/o/oauth2/auth",
+  "token_uri": "https://oauth2.googleapis.com/token",
+  "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
+  "client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/md-rakibul-hasan-naym%40our-card-401407.iam.gserviceaccount.com",
+  "universe_domain": "googleapis.com"
+}

dataExtractOCR.log

@@ -0,0 +1 @@
+INFO:NID:Time: 07:09:50 PM, Successful Execution: 1, BODY: url='https://bl-bucket.sgp1.digitaloceanspaces.com/mmauto/batb-ocr/2025-04-07T13:00:26/image.jpg-original', Result: মুসি ভয়ালি আল হাসান নিঝুম মদর মেহেদী মোহাম্মদ হিসেল সাইদুল আলম নাঈম বেনসন গোল্ড লিফ লাকি স্ট্রাইক রয়েল বেডল টাইগার রাকিবুল হাসান

main.py

@@ -0,0 +1,263 @@
+# import os
+# import re
+# from aiohttp import ClientSession
+# from google.cloud import vision
+# from io import BytesIO
+# import google.generativeai as genai
+# import traceback
+# import nltk
+# from nltk.corpus import stopwords
+# from nltk.tokenize import word_tokenize
+# from nltk.stem import WordNetLemmatizer
+# from string import punctuation
+# from PIL import Image
+# import io
+# from PIL import Image, ImageEnhance, ImageFilter
+
+# # Download necessary NLTK resources
+# nltk.download('punkt')
+# nltk.download('stopwords')
+# nltk.download('wordnet')
+
+# os.environ['GOOGLE_API_KEY'] = "AIzaSyA9sqz4YKQHKXR9TU1imw0DPOghzHOMiBo"
+# # genai.configure(api_key = os.environ['GOOGLE_API_KEY'])
+
+# os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'cloudVisionAPI.json'
+
+# # model = genai.GenerativeModel('gemini-pro')
+# # model = genai.GenerativeModel('gemini-1.5-flash')
+
+# async def remove_text_from_field(texts_to_remove, text_field):
+#     for pattern in texts_to_remove:
+#         text_field = re.sub(pattern, "", text_field)
+#     return text_field
+
+# async def getImage(img_url):
+#     try:
+#         async with ClientSession() as session:
+#             async with session.get(img_url) as response:
+#                 img_data = await response.read()
+#                 return BytesIO(img_data)
+#     except Exception as e:
+#         raise ValueError(f"Error in getImage: {str(e)}")
+
+# # async def detectText(url):
+# #     try:
+# #         client = vision.ImageAnnotatorClient()
+# #         image_bytes = await getImage(url)
+# #         image = vision.Image(content=image_bytes.getvalue())
+        
+# #         image_response = client.document_text_detection(image=image)
+# #         if image_response.error.message:
+# #             raise Exception("{}\nFor more info on error messages, check: ""https://cloud.google.com/apis/design/errors".format(image_response.error.message))
+        
+# #         image_texts = image_response.text_annotations
+# #         imageData = image_texts[0].description
+# #         return imageData
+# #     except Exception as e:
+# #         traceback.print_exc()
+# #         raise ValueError(f"Error in detectText: {str(e)}")
+
+
+# async def detectText(url, threshold=0.0):
+#     try:
+#         client = vision.ImageAnnotatorClient()
+#         image_bytes = await getImage(url)
+#         image = vision.Image(content=image_bytes.getvalue())
+#         image_response = client.document_text_detection(image=image)
+
+#         if image_response.error.message:
+#             raise Exception(
+#                 "{}\nFor more info on error messages, check: "
+#                 "https://cloud.google.com/apis/design/errors".format(image_response.error.message)
+#             )
+
+#         image_texts = image_response.full_text_annotation
+
+#         bangla_words = []
+#         for page in image_texts.pages:
+#             for block in page.blocks:
+#                 for paragraph in block.paragraphs:
+#                     for word in paragraph.words:
+#                         word_text = ''.join([symbol.text for symbol in word.symbols])
+#                         if word.confidence >= threshold:
+#                             # Check if the word contains any Bangla character
+#                             if re.search(r'[\u0980-\u09FF]', word_text):
+#                                 bangla_words.append(word_text)
+
+#         return ' '.join(bangla_words)
+
+#     except Exception as e:
+#         traceback.print_exc()
+#         raise ValueError(f"Error in detectText: {str(e)}")
+
+# def clean_text(text):
+#     tokens = word_tokenize(text)
+#     tokens = [word for word in tokens if word not in punctuation]
+#     lemmatizer = WordNetLemmatizer()
+#     tokens = [lemmatizer.lemmatize(word) for word in tokens]
+#     clean_tokens = [i for i in tokens if i != '·']
+#     print("Cleaned Tokens:", clean_tokens)         
+#     return ' '.join(clean_tokens)
+
+# async def main(url):
+#     try:
+#         data = await detectText(url)
+#         # myQue = f"Extract only name from {data} also correct the name of Cigarettes and person name if the name is wrong. Dont give any other information except those name."
+#         # response = model.generate_content(myQue)
+#         # text = response.text
+        
+#         cleaned_text = clean_text(data)
+
+#         return cleaned_text
+#     except Exception as e:
+#         traceback.print_exc()
+#         raise ValueError(f"Error in main: {str(e)}")
+
+
+
+
+
+
+
+
+
+
+import os
+import re
+import io
+import traceback
+import nltk
+from aiohttp import ClientSession
+from google.cloud import vision
+from io import BytesIO
+from string import punctuation
+from PIL import Image, ImageEnhance, ImageFilter, ImageDraw, ImageFont
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+import google.generativeai as genai
+
+# Environment variables
+os.environ['GOOGLE_API_KEY'] = "AIzaSyA9sqz4YKQHKXR9TU1imw0DPOghzHOMiBo"
+os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'cloudVisionAPI.json'
+
+genai.configure(api_key = os.environ['GOOGLE_API_KEY'])
+
+# # model = genai.GenerativeModel('gemini-pro')
+model = genai.GenerativeModel('gemini-1.5-flash')
+
+# ========== Utility Functions ==========
+
+async def getImage(img_url):
+    try:
+        async with ClientSession() as session:
+            async with session.get(img_url) as response:
+                img_data = await response.read()
+                return BytesIO(img_data)
+    except Exception as e:
+        raise ValueError(f"Error in getImage: {str(e)}")
+
+counter = 0
+
+async def preprocess_image_for_ocr(image_bytes):
+    global counter
+    image = Image.open(image_bytes).convert('L')  # Convert to grayscale
+
+    # Save image to a bytes buffer
+    byte_arr = io.BytesIO()
+    image.save(byte_arr, format='PNG')
+    counter +=1
+    image.save(f"images/{counter}_image.jpg", format='PNG')
+    return byte_arr.getvalue()
+
+async def detectText(url, threshold=0.0):
+    try:
+        # Initialize the Vision client
+        client = vision.ImageAnnotatorClient()
+        
+        # Fetch and preprocess image
+        image_bytes = await getImage(url)
+        processed_image_bytes = await preprocess_image_for_ocr(image_bytes)
+
+        # Create Image object for Google Vision API
+        image = vision.Image(content=processed_image_bytes)
+        
+        # Perform document text detection
+        response = client.document_text_detection(image=image)
+
+        # Check for errors in the API response
+        if response.error.message:
+            raise Exception(f"API Error: {response.error.message}\nCheck: https://cloud.google.com/apis/design/errors")
+
+        # Extract text from the response
+        image_texts = response.full_text_annotation
+        bangla_words = []
+
+        # Loop through the detected text and filter Bangla words
+        for page in image_texts.pages:
+            for block in page.blocks:
+                for paragraph in block.paragraphs:
+                    for word in paragraph.words:
+                        word_text = ''.join([symbol.text for symbol in word.symbols])
+                        if word.confidence >= threshold and re.search(r'[\u0980-\u09FF]', word_text):
+                            bangla_words.append(word_text)
+
+        # Return Bangla words as a space-separated string
+        return ' '.join(bangla_words)
+
+    except Exception as e:
+        traceback.print_exc()
+        raise ValueError(f"Error in detectText: {str(e)}")    
+    
+    
+def clean_text(text):
+    tokens = word_tokenize(text)
+    tokens = [word for word in tokens if word not in punctuation]
+    lemmatizer = WordNetLemmatizer()
+    tokens = [lemmatizer.lemmatize(word) for word in tokens]
+    clean_tokens = [i for i in tokens if i != '·']
+    print("Cleaned Tokens:", clean_tokens)
+    return ' '.join(clean_tokens)
+
+    
+    
+    
+    
+    
+async def main(url):
+    try:
+        dic = ['গোল্ডলিফ', 'লাকি স্ট্রাইক', 'বেনসন']
+        
+        # Extract the data using detectText function
+        data = await detectText(url)
+        
+        # Define the query (myQue) to pass to the model
+        myQue = f"""
+        Extract and correct the names of cigarette brands and Bangladeshi people's names from the following text. The text may contain spelling errors, grammatical issues, and improperly formatted names. 
+
+        Your task:
+        - Extract and correct the names of cigarette brands and Bangladeshi people also bangla writings.
+        - Return only the corrected data (in Bangla), with no additional information or explanations.
+
+        Here is the provided text: 
+        {data}
+
+        Only return the corrected names, no extra text.
+        """
+
+        print("Query to Model:", myQue)  # Optional: For debugging to see the query sent to the model
+        
+        # Generate the response from the model
+        response = model.generate_content(myQue)
+        text = response.text.strip()
+        clean_txt = clean_text(text)
+        print("Response Text:", clean_txt)
+
+        # Return the cleaned response with only the extracted names
+        return clean_txt
+
+    except Exception as e:
+        # Print and raise a detailed error message for debugging
+        traceback.print_exc()
+        raise ValueError(f"Error in main: {str(e)}")

main_old.py

@@ -0,0 +1,324 @@
+# import os
+# import re
+# from aiohttp import ClientSession
+# from google.cloud import vision
+# from io import BytesIO
+# import google.generativeai as genai
+# import traceback
+# import nltk
+# from nltk.corpus import stopwords
+# from nltk.tokenize import word_tokenize
+# from nltk.stem import WordNetLemmatizer
+# from string import punctuation
+# from PIL import Image
+# import io
+# from PIL import Image, ImageEnhance, ImageFilter
+
+# # Download necessary NLTK resources
+# nltk.download('punkt')
+# nltk.download('stopwords')
+# nltk.download('wordnet')
+
+# os.environ['GOOGLE_API_KEY'] = "AIzaSyA9sqz4YKQHKXR9TU1imw0DPOghzHOMiBo"
+# # genai.configure(api_key = os.environ['GOOGLE_API_KEY'])
+
+# os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'cloudVisionAPI.json'
+
+# # model = genai.GenerativeModel('gemini-pro')
+# # model = genai.GenerativeModel('gemini-1.5-flash')
+
+# async def remove_text_from_field(texts_to_remove, text_field):
+#     for pattern in texts_to_remove:
+#         text_field = re.sub(pattern, "", text_field)
+#     return text_field
+
+# async def getImage(img_url):
+#     try:
+#         async with ClientSession() as session:
+#             async with session.get(img_url) as response:
+#                 img_data = await response.read()
+#                 return BytesIO(img_data)
+#     except Exception as e:
+#         raise ValueError(f"Error in getImage: {str(e)}")
+
+# # async def detectText(url):
+# #     try:
+# #         client = vision.ImageAnnotatorClient()
+# #         image_bytes = await getImage(url)
+# #         image = vision.Image(content=image_bytes.getvalue())
+        
+# #         image_response = client.document_text_detection(image=image)
+# #         if image_response.error.message:
+# #             raise Exception("{}\nFor more info on error messages, check: ""https://cloud.google.com/apis/design/errors".format(image_response.error.message))
+        
+# #         image_texts = image_response.text_annotations
+# #         imageData = image_texts[0].description
+# #         return imageData
+# #     except Exception as e:
+# #         traceback.print_exc()
+# #         raise ValueError(f"Error in detectText: {str(e)}")
+
+
+# async def detectText(url, threshold=0.0):
+#     try:
+#         client = vision.ImageAnnotatorClient()
+#         image_bytes = await getImage(url)
+#         image = vision.Image(content=image_bytes.getvalue())
+#         image_response = client.document_text_detection(image=image)
+
+#         if image_response.error.message:
+#             raise Exception(
+#                 "{}\nFor more info on error messages, check: "
+#                 "https://cloud.google.com/apis/design/errors".format(image_response.error.message)
+#             )
+
+#         image_texts = image_response.full_text_annotation
+
+#         bangla_words = []
+#         for page in image_texts.pages:
+#             for block in page.blocks:
+#                 for paragraph in block.paragraphs:
+#                     for word in paragraph.words:
+#                         word_text = ''.join([symbol.text for symbol in word.symbols])
+#                         if word.confidence >= threshold:
+#                             # Check if the word contains any Bangla character
+#                             if re.search(r'[\u0980-\u09FF]', word_text):
+#                                 bangla_words.append(word_text)
+
+#         return ' '.join(bangla_words)
+
+#     except Exception as e:
+#         traceback.print_exc()
+#         raise ValueError(f"Error in detectText: {str(e)}")
+
+# def clean_text(text):
+#     tokens = word_tokenize(text)
+#     tokens = [word for word in tokens if word not in punctuation]
+#     lemmatizer = WordNetLemmatizer()
+#     tokens = [lemmatizer.lemmatize(word) for word in tokens]
+#     clean_tokens = [i for i in tokens if i != '·']
+#     print("Cleaned Tokens:", clean_tokens)         
+#     return ' '.join(clean_tokens)
+
+# async def main(url):
+#     try:
+#         data = await detectText(url)
+#         # myQue = f"Extract only name from {data} also correct the name of Cigarettes and person name if the name is wrong. Dont give any other information except those name."
+#         # response = model.generate_content(myQue)
+#         # text = response.text
+        
+#         cleaned_text = clean_text(data)
+
+#         return cleaned_text
+#     except Exception as e:
+#         traceback.print_exc()
+#         raise ValueError(f"Error in main: {str(e)}")
+
+
+
+
+
+
+
+
+
+
+import os
+import re
+import io
+import traceback
+import nltk
+from aiohttp import ClientSession
+from google.cloud import vision
+from io import BytesIO
+from string import punctuation
+from PIL import Image, ImageEnhance, ImageFilter, ImageDraw, ImageFont
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+
+# # Download necessary NLTK resources
+# nltk.download('punkt')
+# nltk.download('stopwords')
+# nltk.download('wordnet')
+
+# Environment variables
+os.environ['GOOGLE_API_KEY'] = "AIzaSyA9sqz4YKQHKXR9TU1imw0DPOghzHOMiBo"
+os.environ['GOOGLE_APPLICATION_CREDENTIALS'] = 'cloudVisionAPI.json'
+
+# ========== Utility Functions ==========
+
+async def getImage(img_url):
+    try:
+        async with ClientSession() as session:
+            async with session.get(img_url) as response:
+                img_data = await response.read()
+                return BytesIO(img_data)
+    except Exception as e:
+        raise ValueError(f"Error in getImage: {str(e)}")
+
+# async def preprocess_image_for_ocr(image_bytes):
+#     image = Image.open(io.BytesIO(image_bytes)).convert('L')
+#     contrast = ImageEnhance.Contrast(image)
+#     image = contrast.enhance(2.0)
+#     image = image.point(lambda x: 0 if x < 140 else 255, '1')
+#     image = image.filter(ImageFilter.SHARPEN)
+#     image = image.filter(ImageFilter.MedianFilter())
+    
+#     # Resize image (scale up)
+#     new_size = (image.size[0] * 2, image.size[1] * 2)
+#     image = image.resize(new_size)
+    
+#     # Generate thumbnail (optional)
+#     thumb_size = (640, 640)
+#     image.thumbnail(thumb_size)
+
+#     # Convert PIL image to bytes for Google Vision
+#     byte_arr = io.BytesIO()
+#     image.save("preprocessed_output.png")
+#     return byte_arr.getvalue()
+
+
+counter = 0
+
+# async def preprocess_image_for_ocr(image_bytes):
+#     image = Image.open(io.BytesIO(image_bytes)).convert('L')  # Convert to grayscale
+
+#     # Enhance contrast
+#     contrast = ImageEnhance.Contrast(image)
+#     image = contrast.enhance(2.0)
+
+#     # Binarize image
+#     image = image.point(lambda x: 0 if x < 140 else 255, '1')
+
+#     # Apply filters
+#     image = image.filter(ImageFilter.SHARPEN)
+#     image = image.filter(ImageFilter.MedianFilter())
+
+#     # Resize image (scale up)
+#     new_size = (image.size[0] * 2, image.size[1] * 2)
+#     image = image.resize(new_size)
+
+#     # # Generate thumbnail (optional)
+#     thumb_size = (640, 640)
+#     image.thumbnail(thumb_size)
+
+#     # Convert PIL image to bytes for Google Vision
+#     byte_arr = io.BytesIO(image.getvalue())
+#     # image.save(byte_arr, format='PNG')  # Save to buffer instead of disk
+#     return byte_arr.getvalue()
+
+
+async def preprocess_image_for_ocr(image_bytes):
+    global counter
+    # Since image_bytes is already a BytesIO object, we can directly use it
+    image = Image.open(image_bytes).convert('L')  # Convert to grayscale
+
+    # Enhance contrast
+    # contrast = ImageEnhance.Contrast(image)
+    # image = contrast.enhance(2.0)
+
+    # # Binarize image
+    # image = image.point(lambda x: 0 if x < 140 else 255, '1')
+
+    # # Apply filters
+    # image = image.filter(ImageFilter.SHARPEN)
+    # image = image.filter(ImageFilter.MedianFilter())
+
+    # # Resize image (scale up)
+    # new_size = (image.size[0] * 2, image.size[1] * 2)
+    # image = image.resize(new_size)
+
+    # Save image to a bytes buffer
+    byte_arr = io.BytesIO()
+    image.save(byte_arr, format='PNG')
+    counter +=1
+    image.save(f"images/{counter}_image.jpg", format='PNG')
+    return byte_arr.getvalue()
+
+async def detectText(url, threshold=0.0):
+    try:
+        # Initialize the Vision client
+        client = vision.ImageAnnotatorClient()
+        
+        # Fetch and preprocess image
+        image_bytes = await getImage(url)
+        processed_image_bytes = await preprocess_image_for_ocr(image_bytes)
+
+        # Create Image object for Google Vision API
+        image = vision.Image(content=processed_image_bytes)
+        
+        # Perform document text detection
+        response = client.document_text_detection(image=image)
+
+        # Check for errors in the API response
+        if response.error.message:
+            raise Exception(f"API Error: {response.error.message}\nCheck: https://cloud.google.com/apis/design/errors")
+
+        # Extract text from the response
+        image_texts = response.full_text_annotation
+        bangla_words = []
+
+        # Loop through the detected text and filter Bangla words
+        for page in image_texts.pages:
+            for block in page.blocks:
+                for paragraph in block.paragraphs:
+                    for word in paragraph.words:
+                        word_text = ''.join([symbol.text for symbol in word.symbols])
+                        if word.confidence >= threshold and re.search(r'[\u0980-\u09FF]', word_text):
+                            bangla_words.append(word_text)
+
+        # Return Bangla words as a space-separated string
+        return ' '.join(bangla_words)
+
+    except Exception as e:
+        traceback.print_exc()
+        raise ValueError(f"Error in detectText: {str(e)}")    
+    
+    
+# async def detectText(url, threshold=0.0):
+#     try:
+#         client = vision.ImageAnnotatorClient()
+#         image_bytes = await getImage(url)
+#         processed_image_bytes = await preprocess_image_for_ocr(image_bytes.getvalue())
+
+#         image = vision.Image(content=processed_image_bytes)
+#         response = client.document_text_detection(image=image)
+
+#         if response.error.message:
+#             raise Exception(f"{response.error.message}\nCheck: https://cloud.google.com/apis/design/errors")
+
+#         image_texts = response.full_text_annotation
+
+#         bangla_words = []
+#         for page in image_texts.pages:
+#             for block in page.blocks:
+#                 for paragraph in block.paragraphs:
+#                     for word in paragraph.words:
+#                         word_text = ''.join([symbol.text for symbol in word.symbols])
+#                         if word.confidence >= threshold and re.search(r'[\u0980-\u09FF]', word_text):
+#                             bangla_words.append(word_text)
+
+#         return ' '.join(bangla_words)
+
+#     except Exception as e:
+#         traceback.print_exc()
+#         raise ValueError(f"Error in detectText: {str(e)}")
+
+def clean_text(text):
+    tokens = word_tokenize(text)
+    tokens = [word for word in tokens if word not in punctuation]
+    lemmatizer = WordNetLemmatizer()
+    tokens = [lemmatizer.lemmatize(word) for word in tokens]
+    clean_tokens = [i for i in tokens if i != '·']
+    print("Cleaned Tokens:", clean_tokens)
+    return ' '.join(clean_tokens)
+
+async def main(url):
+    try:
+        data = await detectText(url)
+        cleaned_text = clean_text(data)
+        return cleaned_text
+    except Exception as e:
+        traceback.print_exc()
+        raise ValueError(f"Error in main: {str(e)}")

requirements.txt

@@ -0,0 +1,16 @@
+pillow
+fastapi
+pydantic
+uvicorn
+pytz
+aiohttp
+pandas
+google-cloud-vision
+google-generativeai
+requests
+numpy
+face_recognition
+hypercorn
+
+# easyocr
+# pytesseract