Update app.py

app.py

@@ -4,7 +4,6 @@ import fitz  # PyMuPDF
 import numpy as np
 from sklearn.metrics.pairwise import cosine_similarity
 from io import BytesIO
-import time
 
 # Function to extract text from the uploaded PDF file
 def extract_pdf_text(pdf_file):
@@ -25,21 +24,28 @@ def get_embeddings(texts):
 
 # Function to get the most relevant context from the PDF for the query
 def get_relevant_context(pdf_text, query, num_contexts=3):
+    # Split the PDF text into chunks for better matching
     pdf_text_chunks = [pdf_text[i:i+1500] for i in range(0, len(pdf_text), 1500)]
+    # Get embeddings for both the document and the query
     pdf_embeddings = get_embeddings(pdf_text_chunks)
     query_embedding = get_embeddings([query])[0]
+    
+    # Compute cosine similarity between query and document chunks
     similarities = cosine_similarity([query_embedding], pdf_embeddings)
     top_indices = similarities[0].argsort()[-num_contexts:][::-1]
+    
+    # Combine the top context pieces
     relevant_context = " ".join([pdf_text_chunks[i] for i in top_indices])
     return relevant_context
 
 # Function to generate a response from GPT-4 chat model
-def generate_response(context, question, chat_history):
-    messages = [{"role": "system", "content": "You are a helpful assistant expert on GPT-4."}]
-    messages.extend(chat_history)
-    messages.append({"role": "user", "content": f"Context: {context}\nQuestion: {question}"})
+def generate_response(context, question):
+    messages = [
+        {"role": "system", "content": "You are a helpful assistant expert on GPT-4."},
+        {"role": "user", "content": f"Context: {context}\nQuestion: {question}"}
+    ]
     response = openai.ChatCompletion.create(
-        model="gpt-4o-mini",
+        model="gpt-4o-mini",  # Use the GPT-4 chat model
         messages=messages,
         max_tokens=1200,
         temperature=0.7,
@@ -51,44 +57,44 @@ def is_irrelevant_question(question):
     irrelevant_keywords = ["life", "love", "meaning", "future", "philosophy"]
     return any(keyword in question.lower() for keyword in irrelevant_keywords)
 
-# Streamlit Chat UI
+# Streamlit UI
 def main():
     st.title("📄 GPT-4 Research Paper Chatbot")
-    st.write("Ask any question related to the GPT-4 paper, and I'll try to answer it!")
-
+    st.write("💬 Ask any question related to the GPT-4 paper, and I'll try to answer it!")
+    
+    # User input: OpenAI API key
     openai_api_key = st.text_input("🔑 Enter your OpenAI API Key:", type="password")
+    
     if openai_api_key:
         openai.api_key = openai_api_key
         st.success("API Key successfully set!")
 
+        # Upload the PDF file
         pdf_file = st.file_uploader("📂 Upload GPT-4 Research Paper PDF", type="pdf")
+        
         if pdf_file is not None:
-            if "pdf_text" not in st.session_state:
-                st.session_state.pdf_text = extract_pdf_text(pdf_file)
-                st.session_state.chat_history = []
-                st.session_state.conversation_active = True
-
+            # Extract text from the uploaded PDF
+            pdf_text = extract_pdf_text(pdf_file)
             st.write("✅ PDF content loaded successfully! Start asking questions.")
-            question = st.text_input("💬 Ask your question:")
-            
-            if st.button("🚪 End Conversation"):
-                st.write("👋 Conversation ended. Refreshing...")
-                st.session_state.conversation_active = False
-                time.sleep(2)
-                st.rerun()
-            
-            if question and st.session_state.conversation_active:
+
+            # User input: the question they want to ask
+            question = st.text_input("Ask your question:")
+
+            if question:
+                # Check if the question is irrelevant
                 if is_irrelevant_question(question):
-                    response = "Sorry, I can only answer questions related to GPT-4."
+                    st.write("Sorry, I don't know the answer to this question. I am an expert on GPT-4 knowledge.")
                 else:
-                    relevant_context = get_relevant_context(st.session_state.pdf_text, question)
-                    response = generate_response(relevant_context, question, st.session_state.chat_history)
-                    st.session_state.chat_history.append({"role": "user", "content": question})
-                    st.session_state.chat_history.append({"role": "assistant", "content": response})
-                
-                st.write(f"🤖 **GPT-4:** {response}")
+                    # Get the most relevant context from the document
+                    relevant_context = get_relevant_context(pdf_text, question)
+                    
+                    # Generate the response from GPT-4 chat model
+                    answer = generate_response(relevant_context, question)
+                    
+                    # Display the answer
+                    st.write(f"🤖 Answer: {answer}")
     else:
         st.warning("⚠️ Please enter your OpenAI API Key to use the chatbot.")
 
 if __name__ == "__main__":
-    main()
+    main()