ds apis implemented

utils/utils.py

@@ -0,0 +1,73 @@
+import os
+import requests
+import json
+from PyPDF2 import PdfReader
+
+base_path = os.path.join("data", "config_files")
+THEME_CONTEXT_PATH = os.path.join(base_path, "theme_context.json")
+
+with open(THEME_CONTEXT_PATH, "r") as f:
+    themes = json.load(f)
+
+def delete_file(file_path):
+    try:
+        os.remove(file_path)
+        print(f"Deleted file: {file_path}")
+    except OSError as e:
+        print(f"Error deleting file {file_path}: {e}")
+
+
+
+def delete_all_files_in_directory(directory_path):
+    try:
+        for filename in os.listdir(directory_path):
+            file_path = os.path.join(directory_path, filename)
+            if os.path.isfile(file_path):
+                os.remove(file_path)
+                print(f"Deleted file: {file_path}")
+    except OSError as e:
+        print(f"Error deleting files in {directory_path}: {e}")
+
+
+def format_questions_text(questions_dict,key):
+    """Format questions as text with dashes."""
+    formatted_text = ""
+    for question in questions_dict[key]:
+        formatted_text += f"- {question['question']}\n"
+    return formatted_text.strip()
+
+
+
+def format_theme_text(theme_id):
+    """Format questions as text with dashes."""
+    formatted_text = "" 
+    matching_themes = [t for t in themes if t["id"] == theme_id]
+    current_theme = matching_themes[0]
+    formatted_text += f"- {current_theme['id']}\n"
+    formatted_text += f"- {current_theme['theme']}\n"
+    formatted_text += f"- {current_theme['context']}\n"
+    
+    return formatted_text.strip()
+
+
+
+def download_pdf_and_extract_text(url: str) -> str:
+    # Create a temporary file path
+    temp_file_path = 'temp.pdf'
+    
+    # Download the PDF from the URL
+    response = requests.get(url)
+    response.raise_for_status()  # Raise an error for bad responses
+    with open(temp_file_path, 'wb') as f:
+        f.write(response.content)
+
+    # Load the PDF
+    reader = PdfReader(temp_file_path)
+
+    # Extract text from all pages and combine into one text
+    combined_text = "\n\n".join(page.extract_text() for page in reader.pages if page.extract_text())
+
+    # Delete the temporary file
+    os.remove(temp_file_path)
+
+    return combined_text