changes

advance-river-381411-c7be39c33cff.json

@@ -1,12 +0,0 @@
-{
-  "type": "service_account",
-  "project_id": "advance-river-381411",
-  "private_key_id": "c7be39c33cff4f7d73235768c604b45d34b70828",
-  "private_key": "-----BEGIN PRIVATE KEY-----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\nqKGloin1O/cM+JHXtcm1QhwS\n-----END PRIVATE KEY-----\n",
-  "client_email": "test-983@advance-river-381411.iam.gserviceaccount.com",
-  "client_id": "117808812221688451309",
-  "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/test-983%40advance-river-381411.iam.gserviceaccount.com"
-}

app.py

@@ -9,14 +9,14 @@ from google.cloud import documentai_v1 as documentai
 import json
 from google.cloud import vision
 import time
-from settings import char_remove, gpt_api_key, gpt_model, RPFAAP2, RPFAAP1, project_id, project_location, processor_id
+from settings import char_remove, gpt_model, RPFAAP2, RPFAAP1, project_id, project_location, processor_id
 from tqdm import tqdm
 import logging
 
 logging.basicConfig(filename='app.log', level=logging.INFO, format='%(asctime)s - %(levelname)s - %(message)s')
 
 def chat_gpt_image(content, context):
-    openai.api_key = gpt_api_key
+    openai.api_key = os.environ['GPT_API_KEY']
     prompt = "You are an expert at identifying OCR errors and correcting them with the help of context, intuition and logic."
     document = "The following text was scanned using OCR, your goal is to return a corrected version of the text"
     prefix = "Additionally"
@@ -46,7 +46,7 @@ def remove_na(string):
     return string
 
 def chat_gpt_document(content, document_type, context):
-    openai.api_key = gpt_api_key
+    openai.api_key = os.environ['GPT_API_KEY']
     prompt = "You are an expert at identifying OCR errors and correcting them with the help of context, intuition and logic."
     document_prefix = "The following text was scanned using OCR, your goal is to extract the important entities from the text and correct them with the help of the restrictions placed in the desired format. Remember to not make any changes on the labels of the desired format, simply extract the text, correct it and return only the desired format. Text:"
     additional_prefix = "Additionally the text"
@@ -100,36 +100,12 @@ def chat_gpt_document(content, document_type, context):
                     property_info[key] = value.strip()
     return json.dumps(property_info, indent=4)
 
-# def get_openai_api_usage():
-#     openai.api_key = "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"
-#     api_key = "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"
-#     org_id = "org-lqZ72EJMjCjjXdRwPNfys6YO"
-#     session = requests.Session()
-#     headers = {
-#         "Authorization": f"Bearer {api_key}",
-#         "OpenAI-Organization": org_id
-#     }
-
-#     # Define the start and end dates for the usage data
-#     today = datetime.date.today()
-#     start_date = today - datetime.timedelta(days=30)
-#     end_date = today
-
-#     # Make the API call to retrieve the usage data
-#     url = f"https://api.openai.com/v1/usage?date=2023-03-29"
-#     response = session.get(url, headers=headers)
-#     response.raise_for_status()
-#     usage_data = response.json().get("data", [])
-#     print(usage_data)
-#     for item in usage_data:
-#         print(f"Date: {item['aggregation_timestamp']}")
-#         print(f"Requests: {item['n_requests']}")
-#         print(f"Tokens: {item['n_context_tokens_total']}")
-#         print(f"Model ID: {item['n_generated_tokens_total']}")
-
 def detect_image(content, lang):
-
-    os.environ['GOOGLE_APPLICATION_CREDENTIALS']=r'advance-river-381411-c7be39c33cff.json'
+    credentials = os.environ['CREDENTIALS']
+    temp_file_path = 'temp_credentials.json'
+    with open(temp_file_path, 'w') as file:
+        json.dump(credentials, file)
+    os.environ['GOOGLE_APPLICATION_CREDENTIALS']=r'temp_credentials.json'
     client = vision.ImageAnnotatorClient()
     buffer = BytesIO()
     content.save(buffer, format="PNG")
@@ -147,10 +123,16 @@ def detect_image(content, lang):
             '{}\nFor more info on error messages, check: '
             'https://cloud.google.com/apis/design/errors'.format(
                 response.error.message))
+    
+    os.remove(temp_file_path)
     return(response.full_text_annotation.text)
 
 def detect_document(content):
-    os.environ['GOOGLE_APPLICATION_CREDENTIALS']=r'advance-river-381411-c7be39c33cff.json'
+    credentials = os.environ['CREDENTIALS']
+    temp_file_path = 'temp_credentials.json'
+    with open(temp_file_path, 'w') as file:
+        json.dump(credentials, file)
+    os.environ['GOOGLE_APPLICATION_CREDENTIALS']=r'temp_credentials.json'
     PROJECT_ID = project_id
     LOCATION = project_location  # Format is 'us' or 'eu'
     PROCESSOR_ID = processor_id  # Create processor in Cloud Console
@@ -188,6 +170,8 @@ def detect_document(content):
     name = name.split("/")[-1]
     name = name.split('.')[0]
 
+    os.remove(temp_file_path)
+
     return(document_object.text, name)
 
 def image(content, lang, context):
@@ -230,7 +214,7 @@ def save_json(text, filename):
         json.dump(text, outfile)
     return filename
 
-with gr.Blocks(title="Ottico OCR", css=".markdown {text-align: center;}", theme='SebastianBravo/simci_css') as app:
+with gr.Blocks(title="Ottico OCR", css=".markdown {text-align: center;}", theme='freddyaboulton/dracula_revamped') as app:
     gr.Markdown("""# Ottico OCR
     Attach Images or Files below and convert them to Text.""", elem_classes="markdown")
     with gr.Tab("Scan Image"):

settings.py

@@ -1,5 +1,4 @@
 #OpenAI Variables
-gpt_api_key = "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"
 gpt_model = "gpt-3.5-turbo"
 
 #Google Variables