Update app.py

app.py

@@ -8,7 +8,6 @@ from langchain.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.vectorstores import FAISS
-from langchain_core.vectorstores import InMemoryVectorStore
 from groq import Groq
 from langchain.memory import ConversationBufferMemory  
 
@@ -28,7 +27,6 @@ client = Groq(api_key=groq_api_key)
 hf_token = hf_api_key
 
 embeddings = HuggingFaceEmbeddings(model_name="heydariAI/persian-embeddings")
-vector_store = InMemoryVectorStore(embeddings)
 
 DATASET_NAME = "chat_history"
 try:
@@ -51,13 +49,17 @@ def save_chat_to_dataset(user_message, bot_message):
         logger.error(f"Error saving chat history to dataset: {e}")
 
 def process_pdf_with_langchain(pdf_path):
+    """Process a PDF file and create a FAISS retriever."""
     try:
+        # Load the PDF
         loader = PyPDFLoader(pdf_path)
         documents = loader.load()
+
         text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
         split_documents = text_splitter.split_documents(documents)
-        
+
         vectorstore = FAISS.from_documents(split_documents, embeddings)
+
         retriever = vectorstore.as_retriever(search_kwargs={"k": 3})
         return retriever
     except Exception as e:
@@ -65,6 +67,7 @@ def process_pdf_with_langchain(pdf_path):
         raise
 
 def generate_response(query, memory, retriever=None, use_pdf_context=False):
+    """Generate a response using the Groq model and retrieved PDF context."""
     try:
         knowledge = ""
 
@@ -88,7 +91,6 @@ def generate_response(query, memory, retriever=None, use_pdf_context=False):
         context += f"\n\nYou: {query}\nParvizGPT:"
 
         response = "در حال پردازش..."
-
         retries = 3
         for attempt in range(retries):
             try:
@@ -109,7 +111,9 @@ def generate_response(query, memory, retriever=None, use_pdf_context=False):
         return f"Error: {e}", memory
 
 def gradio_interface(user_message, chat_box, memory, pdf_file=None, use_pdf_context=False):
+    """Handle the Gradio interface interactions."""
     global retriever
+
     if pdf_file is not None and use_pdf_context:  
         try:
             retriever = process_pdf_with_langchain(pdf_file.name)
@@ -117,7 +121,6 @@ def gradio_interface(user_message, chat_box, memory, pdf_file=None, use_pdf_cont
             return chat_box + [("Error", f"Error processing PDF: {e}")], memory
 
     chat_box.append(("ParvizGPT", "در حال پردازش..."))
-    
     response, memory = generate_response(user_message, memory, retriever=retriever, use_pdf_context=use_pdf_context)
     
     chat_box[-1] = ("You", user_message) 
@@ -128,6 +131,7 @@ def gradio_interface(user_message, chat_box, memory, pdf_file=None, use_pdf_cont
     return chat_box, memory
 
 def clear_memory(memory):
+    """Clear the conversation memory."""
     memory.clear()
     return [], memory
 
@@ -137,7 +141,7 @@ with gr.Blocks() as interface:
     gr.Markdown("## ParvizGPT")
     chat_box = gr.Chatbot(label="Chat History", value=[])
     user_message = gr.Textbox(label="Your Message", placeholder="Type your message here and press Enter...", lines=1, interactive=True)
-    use_pdf_context = gr.Checkbox(label="Use PDF Context", value=False, interactive=True)  # Checkbox for PDF context
+    use_pdf_context = gr.Checkbox(label="Use PDF Context", value=False, interactive=True)
     clear_memory_btn = gr.Button("Clear Memory", interactive=True)
     pdf_file = gr.File(label="Upload PDF for Context (Optional)", type="filepath", interactive=True, scale=1)
     submit_btn = gr.Button("Submit")