Update app.py

app.py

@@ -7,21 +7,26 @@ from langchain.embeddings import OpenAIEmbeddings, HuggingFaceEmbeddings
 from langchain.document_loaders import PyPDFLoader
 import time
 
-# Define paths for cybersecurity documents (Add your PDFs here)
-PDF_FILES = ["NIST_CSWP_04162018.pdf", "ISOIEC 27001_2ef522.pdf", "MITRE ATLAS Overview Combined_v1.pdf", "ISO-IEC-27005-2022.pdf"]
+# Define paths for cybersecurity training PDFs
+PDF_FILES = [
+    "ISOIEC 27001_2ef522.pdf",
+    "ISO-IEC-27005-2022.pdf",
+    "MITRE ATLAS Overview Combined_v1.pdf",
+    "NIST_CSWP_04162018.pdf"
+]
 
-# Choose LLM Model (Switch between OpenAI and Hugging Face)
-USE_OPENAI = False  # Change to True if you prefer OpenAI API
+# Choose whether to use OpenAI API (Online) or Hugging Face (Offline)
+USE_OPENAI = False  # Set to True if using OpenAI API for better responses
 
 def load_data():
     """Loads multiple PDFs and stores embeddings in ChromaDB"""
     all_docs = []
     for pdf in PDF_FILES:
-        if os.path.exists(pdf):
+        if os.path.exists(pdf):  # Ensure the PDF exists in the Hugging Face Space
             loader = PyPDFLoader(pdf)
             all_docs.extend(loader.load())
 
-    # Use OpenAI or Hugging Face embeddings
+    # Use OpenAI embeddings (Online) or Hugging Face embeddings (Offline)
     if USE_OPENAI:
         embeddings = OpenAIEmbeddings()
     else:
@@ -29,19 +34,19 @@ def load_data():
 
     return Chroma.from_documents(all_docs, embeddings)
 
-# Load Vector Database
+# Load the knowledge base from the uploaded PDFs
 vector_db = load_data()
 
-# Select LLM model (Online: OpenAI | Offline: Hugging Face)
+# Select the LLM model (Online: OpenAI | Offline: Hugging Face)
 if USE_OPENAI:
     llm = OpenAI()
 else:
     llm = HuggingFaceHub(repo_id="google/flan-t5-large", model_kwargs={"temperature": 0.5, "max_length": 512})
 
-# Create Retrieval QA chain
+# Create Retrieval QA chain for document-based responses
 qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=vector_db.as_retriever())
 
-# Function to simulate futuristic typing effect
+# Function to generate chatbot responses with a typing effect
 def chatbot_response(question):
     """Handles chatbot queries with a typing effect"""
     response = qa_chain.run(question)
@@ -51,7 +56,7 @@ def chatbot_response(question):
         time.sleep(0.02)  # Simulate typing delay
         yield displayed_response
 
-# Custom futuristic CSS style
+# Custom futuristic CSS styling
 custom_css = """
 body {background-color: #0f172a; color: #0ff; font-family: 'Orbitron', sans-serif;}
 #chatbot-container {border: 2px solid #00ffff; background: rgba(0, 0, 0, 0.8); padding: 20px; border-radius: 15px;}
@@ -96,13 +101,13 @@ three_js_html = """
 </div>
 """
 
-# Create Gradio Interface with Custom Styling and 3D Avatar
+# Create Gradio Chatbot Interface with Custom UI & 3D Avatar
 iface = gr.Interface(
     fn=chatbot_response,
     inputs="text",
     outputs="text",
-    title="🤖 Cybernetic AI: Your Cybersecurity Assistant",
-    description="Ask me about NIST, ISO/IEC 27001, MITRE ATT&CK, and ISO/IEC 27005. Now with a 3D Avatar!",
+    title="🤖 Cybersecurity AI Assistant",
+    description="Ask me about NIST, ISO/IEC 27001, MITRE ATLAS, and ISO/IEC 27005. Powered by AI and real-time 3D visualization.",
     theme="default",
     css=custom_css,
     live=True,  # Enables real-time updates for typing effect