Major update. Support for 15 LLMs, World Flora Online taxonomy validation, geolocation, 2 OCR methods, significant UI changes, stability improvements, consistent JSON parsing

app.py

@@ -2454,4 +2454,29 @@ if st.session_state.proceed_to_build_llm_prompt:
 # elif st.session_state.proceed_to_private and not st.session_state['is_hf']:
 #     create_private_file()
 elif st.session_state.proceed_to_main:
-    main()
+    main()
+
+
+
+
+
+
+
+# print(f"proceed_to_main3 {st.session_state['proceed_to_main']}")
+# print(f"is_hf3 {st.session_state['is_hf']}")
+# print(f"private_file3 {st.session_state['private_file']}")
+# print(f"proceed_to_build_llm_prompt3 {st.session_state['proceed_to_build_llm_prompt']}")
+# print(f"proceed_to_private3 {st.session_state['proceed_to_private']}")
+
+# # if not st.session_state.private_file and not st.session_state['is_hf']:
+# #     create_private_file()
+# # elif st.session_state.proceed_to_build_llm_prompt:
+# if st.session_state.proceed_to_build_llm_prompt:
+#     build_LLM_prompt_config()
+# # elif st.session_state.proceed_to_private and not st.session_state['is_hf']:
+# #     create_private_file()
+# elif st.session_state.proceed_to_main:
+#     main()
+
+
+

vouchervision/API_validation.py

@@ -48,51 +48,51 @@ class APIvalidation:
         except:
             return False
         
-    def check_google_ocr_api_key(self):
-        # if os.path.exists(self.cfg_private['google_cloud']['path_json_file']):
-        #     os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = self.cfg_private['google_cloud']['path_json_file']
-        # elif os.path.exists(self.cfg_private['google_cloud']['path_json_file_service_account2']):
-        #     os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = self.cfg_private['google_cloud']['path_json_file_service_account2']
-        # else:
-        #     return False
+    # def check_google_ocr_api_key(self): ##################################################################################### maybe check without initi, post the vertexai
+    #     # if os.path.exists(self.cfg_private['google_cloud']['path_json_file']):
+    #     #     os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = self.cfg_private['google_cloud']['path_json_file']
+    #     # elif os.path.exists(self.cfg_private['google_cloud']['path_json_file_service_account2']):
+    #     #     os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = self.cfg_private['google_cloud']['path_json_file_service_account2']
+    #     # else:
+    #     #     return False
         
-        try:
-            if not self.cfg_private:
-                # Convert JSON key from string to a dictionary
-                service_account_json_str = os.getenv('google_service_account_json')
-                if not service_account_json_str:
-                    print("Service account JSON not found in environment variables.")
-                    return False
-
-                # Convert JSON string to a dictionary
-                service_account_info = json.loads(service_account_json_str)
-                # Create credentials from the service account info
-                credentials = service_account.Credentials.from_service_account_info(service_account_info)
-                # Initialize the client with the credentials
-                client = vision.ImageAnnotatorClient(credentials=credentials)
-                logo_path = os.path.join(self.dir_home, 'img','logo.png')
-                with io.open(logo_path, 'rb') as image_file:
-                    content = image_file.read()
-                image = vision.Image(content=content)
-                response = client.document_text_detection(image=image)
-                texts = response.text_annotations       
-                normal_cleaned_text = texts[0].description if texts else None
-                print(f"OCR TEST: {normal_cleaned_text}")
-            else:
-                logo_path = os.path.join(self.dir_home, 'img','logo.png')
-                client = vision.ImageAnnotatorClient()
-                with io.open(logo_path, 'rb') as image_file:
-                    content = image_file.read()
-                image = vision.Image(content=content)
-                response = client.document_text_detection(image=image)
-                texts = response.text_annotations       
-                normal_cleaned_text = texts[0].description if texts else None
-            if normal_cleaned_text:
-                return True
-            else:
-                return False
-        except:
-            return False
+    #     try:
+    #         if not self.cfg_private:
+    #             # Convert JSON key from string to a dictionary
+    #             service_account_json_str = os.getenv('google_service_account_json')
+    #             if not service_account_json_str:
+    #                 print("Service account JSON not found in environment variables.")
+    #                 return False
+
+    #             # Convert JSON string to a dictionary
+    #             service_account_info = json.loads(service_account_json_str)
+    #             # Create credentials from the service account info
+    #             credentials = service_account.Credentials.from_service_account_info(service_account_info)
+    #             # Initialize the client with the credentials
+    #             client = vision.ImageAnnotatorClient(credentials=credentials)
+    #             logo_path = os.path.join(self.dir_home, 'img','logo.png')
+    #             with io.open(logo_path, 'rb') as image_file:
+    #                 content = image_file.read()
+    #             image = vision.Image(content=content)
+    #             response = client.document_text_detection(image=image)
+    #             texts = response.text_annotations       
+    #             normal_cleaned_text = texts[0].description if texts else None
+    #             print(f"OCR TEST: {normal_cleaned_text}")
+    #         else:
+    #             logo_path = os.path.join(self.dir_home, 'img','logo.png')
+    #             client = vision.ImageAnnotatorClient()
+    #             with io.open(logo_path, 'rb') as image_file:
+    #                 content = image_file.read()
+    #             image = vision.Image(content=content)
+    #             response = client.document_text_detection(image=image)
+    #             texts = response.text_annotations       
+    #             normal_cleaned_text = texts[0].description if texts else None
+    #         if normal_cleaned_text:
+    #             return True
+    #         else:
+    #             return False
+    #     except:
+    #         return False
         
     def check_azure_openai_api_key(self):
         if self.cfg_private:
@@ -171,30 +171,30 @@ class APIvalidation:
         except Exception as e:  # Replace with a more specific exception if possible
             return False
         
-    def get_google_credentials(self):
-        # Convert JSON key from string to a dictionary
-        service_account_json_str = os.getenv('google_service_account_json')
+    # def get_google_credentials(self):
+    #     # Convert JSON key from string to a dictionary
+    #     service_account_json_str = os.getenv('google_service_account_json')
 
-        with tempfile.NamedTemporaryFile(mode="w+", delete=False,suffix=".json") as temp:
-            temp.write(service_account_json_str)
-            temp_filename = temp.name
+    #     with tempfile.NamedTemporaryFile(mode="w+", delete=False,suffix=".json") as temp:
+    #         temp.write(service_account_json_str)
+    #         temp_filename = temp.name
         
-        return temp_filename
+    #     return temp_filename
 
-    def init_google_client(opt, opt2):
-        # Fetch the credentials JSON string from Hugging Face Secrets
-        creds_json_str = os.getenv('google_service_account_json')
+    # def init_google_client(opt, opt2):
+    #     # Fetch the credentials JSON string from Hugging Face Secrets
+    #     creds_json_str = os.getenv('google_service_account_json')
 
-        if creds_json_str:
-            creds_dict = json.loads(creds_json_str)
-            credentials = service_account.Credentials.from_service_account_info(creds_dict)
+    #     if creds_json_str:
+    #         creds_dict = json.loads(creds_json_str)
+    #         credentials = service_account.Credentials.from_service_account_info(creds_dict)
 
-            # Initialize Google API client (if needed for your use case)
-            client = build(opt, opt2, credentials=credentials)  # Adjust with actual service details
+    #         # Initialize Google API client (if needed for your use case)
+    #         client = build(opt, opt2, credentials=credentials)  # Adjust with actual service details
 
-            return client, credentials
-        else:
-            print("Google API credentials not found.")
+    #         return client, credentials
+    #     else:
+    #         print("Google API credentials not found.")
 
     def check_google_vertex_genai_api_key(self):
         results = {"palm2": False, "gemini": False}
@@ -236,10 +236,14 @@ class APIvalidation:
             try:
                 # Assuming genai and vertexai are clients for Google services
                 # os.environ["GOOGLE_API_KEY"] = os.getenv('PALM_API_KEY')
-                os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = self.get_google_credentials()
-                client, credentials = self.init_google_client('gemini-pro', 'v1')
-                print(credentials)
-                vertexai.init(project= os.getenv('GOOGLE_PROJECT_ID'), location=os.getenv('GOOGLE_LOCATION'), credentials=credentials)
+                # os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = self.get_google_credentials()
+                # client, credentials = self.init_google_client('gemini-pro', 'v1')
+                # print(credentials)
+                palm_api_key = os.getenv('PALM_API_KEY')
+                google_project_id = os.getenv('GOOGLE_PROJECT_ID')
+                google_location = os.getenv('GOOGLE_LOCATION')
+
+                vertexai.init(project=google_project_id, location=google_location)#, credentials=credentials)
 
                 try:
                     model = TextGenerationModel.from_pretrained("text-bison@001")
@@ -305,7 +309,7 @@ class APIvalidation:
         # Check each key and add to the respective list
         # Google OCR key check
         if self.has_API_key(k_google_palm_api) and self.has_API_key(k_project_id) and self.has_API_key(k_location):
-            is_valid = self.check_google_ocr_api_key()
+            is_valid = True #self.check_google_ocr_api_key() ###############################################################################################################################
             if is_valid:
                 present_keys.append('Google OCR (Valid)')
             else:

vouchervision/utils_VoucherVision.py

@@ -410,30 +410,30 @@ class VoucherVision():
         else:
             return False
         
-    def get_google_credentials(self):
-        # Convert JSON key from string to a dictionary
-        service_account_json_str = os.getenv('google_service_account_json')
+    # def get_google_credentials(self):
+    #     # Convert JSON key from string to a dictionary
+    #     service_account_json_str = os.getenv('google_service_account_json')
 
-        with tempfile.NamedTemporaryFile(mode="w+", delete=False,suffix=".json") as temp:
-            temp.write(service_account_json_str)
-            temp_filename = temp.name
+    #     with tempfile.NamedTemporaryFile(mode="w+", delete=False,suffix=".json") as temp:
+    #         temp.write(service_account_json_str)
+    #         temp_filename = temp.name
         
-        return temp_filename   
+    #     return temp_filename   
     
-    def init_google_client(opt, opt2):
-        # Fetch the credentials JSON string from Hugging Face Secrets
-        creds_json_str = os.getenv('google_service_account_json')
+    # def init_google_client(opt, opt2):
+    #     # Fetch the credentials JSON string from Hugging Face Secrets
+    #     creds_json_str = os.getenv('google_service_account_json')
 
-        if creds_json_str:
-            creds_dict = json.loads(creds_json_str)
-            credentials = service_account.Credentials.from_service_account_info(creds_dict)
+    #     if creds_json_str:
+    #         creds_dict = json.loads(creds_json_str)
+    #         credentials = service_account.Credentials.from_service_account_info(creds_dict)
 
-            # Initialize Google API client (if needed for your use case)
-            client = build(opt, opt2, credentials=credentials)  # Adjust with actual service details
+    #         # Initialize Google API client (if needed for your use case)
+    #         client = build(opt, opt2, credentials=credentials)  # Adjust with actual service details
 
-            return client, credentials
-        else:
-            print("Google API credentials not found.")
+    #         return client, credentials
+    #     else:
+    #         print("Google API credentials not found.")
 
         
     def set_API_keys(self):
@@ -465,17 +465,17 @@ class VoucherVision():
             google_project_id = os.getenv('GOOGLE_PROJECT_ID')
             google_location = os.getenv('GOOGLE_LOCATION')
 
-            try:
-                if genai_api_key:
-                    genai.configure(api_key=genai_api_key)
-            except:
-                print(f"failed genai.configure")
+            # try:
+                # if genai_api_key:
+                    # genai.configure(api_key=genai_api_key)
+            # except:
+                # print(f"failed genai.configure")
 
             try:
                 if google_project_id and google_location:
-                    clien, credentials = self.init_google_client('gemini-pro', 'v1')
-                    print(credentials)
-                    vertexai.init(project=google_project_id, location=google_location, credentials=credentials)
+                    # clien, credentials = self.init_google_client('gemini-pro', 'v1')
+                    # print(credentials)
+                    vertexai.init(project=google_project_id, location=google_location)#, credentials=credentials)
             except:
                 print(f"failed vertexai.init")
             # if self.has_key_openai: