Update app.py

app.py

@@ -1,233 +1,341 @@
-import os
-import json
-from datetime import datetime
-import streamlit as st
-from langchain_huggingface import HuggingFaceEmbeddings
-from langchain_chroma import Chroma
-from langchain_groq import ChatGroq
-from langchain.memory import ConversationBufferMemory
-from langchain.chains import ConversationalRetrievalChain
-
-
-from vectorize_documents import embeddings
-
-working_dir = os.path.dirname(os.path.abspath(__file__))
-config_data = json.load(open(f"{working_dir}/config.json"))
-GROQ_API_KEY = config_data["GROQ_API_KEY"]
-os.environ["GROQ_API_KEY"]= GROQ_API_KEY
-
-# Ensure the JSON file exists
-chat_history_file = "chat_histories.json"
-if not os.path.exists(chat_history_file):
-    with open(chat_history_file, "w") as f:
-        json.dump({}, f)
-
-# Functions to handle chat history
-def load_chat_history():
-    with open(chat_history_file, "r") as f:
-        return json.load(f)
-
-def save_chat_history(chat_histories):
-    with open(chat_history_file, "w") as f:
-        json.dump(chat_histories, f, indent=4)
-
-# Function to set up vectorstore
-def setup_vectorstore():
-    embeddings = HuggingFaceEmbeddings()
-    vectorstore = Chroma(persist_directory="vector_db_dir_notes_ai",
-                         embedding_function=embeddings)
-    return vectorstore
-
-# Function to set up chatbot chain
-def chat_chain(vectorstore):
-    llm = ChatGroq(
-        model="llama-3.1-70b-versatile",
-        temperature=0
-    )
-    retriever = vectorstore.as_retriever()
-    memory = ConversationBufferMemory(
-        llm=llm,
-        output_key="answer",
-        memory_key="chat_history",
-        return_messages=True
-    )
-    chain = ConversationalRetrievalChain.from_llm(
-        llm=llm,
-        retriever=retriever,
-        chain_type="stuff",
-        memory=memory,
-        verbose=True,
-        return_source_documents=True
-    )
-    return chain
-
-# Streamlit UI
-st.set_page_config(
-    page_title="Notes.AI",
-    page_icon="🤖AI",
-    layout="centered"
-)
-
-st.title("🤖 Notes.AI")
-st.subheader("Hey! Here you can search for notes of CSE 7th Sem! Read Notes, Read PYQ answers also!!")
-
-# Step 1: Input user's name
-if "username" not in st.session_state:
-    username = st.text_input("Enter your name to proceed:")
-    if username:
-        with st.spinner("Loading chatbot interface... Please wait."):
-            st.session_state.username = username
-            st.session_state.chat_history = []  # Initialize empty chat history
-            st.session_state.vectorstore = setup_vectorstore()
-            st.session_state.conversational_chain = chat_chain(st.session_state.vectorstore)
-            st.success(f"Welcome, {username}! The chatbot interface is ready.")
-else:
-    username = st.session_state.username
-
-# Step 2: Initialize components if not already set
-if "conversational_chain" not in st.session_state:
-    st.session_state.vectorstore = setup_vectorstore()
-    st.session_state.conversational_chain = chat_chain(st.session_state.vectorstore)
-
-# Step 3: Show chatbot interface
-if "username" in st.session_state:
-    st.subheader(f"Hello {username}, start your query below!")
-
-    # Display existing chat history dynamically
-    for message in st.session_state.chat_history:
-        if message["role"] == "user":
-            with st.chat_message("user"):
-                st.markdown(message["content"])
-        elif message["role"] == "assistant":
-            with st.chat_message("assistant"):
-                st.markdown(message["content"])
-
-    # User input section
-    user_input = st.chat_input("Ask AI....")
-    if user_input:
-        with st.spinner("Processing your query... Please wait."):
-            # Save user input to session state
-            st.session_state.chat_history.append({"role": "user", "content": user_input})
-
-            # Display user's message
-            with st.chat_message("user"):
-                st.markdown(user_input)
-
-            # Get assistant's response
-            with st.chat_message("assistant"):
-                response = st.session_state.conversational_chain({"question": user_input})
-                assistant_response = response["answer"]
-                st.markdown(assistant_response)
-
-                # Save assistant's response to session state
-                st.session_state.chat_history.append({"role": "assistant", "content": assistant_response})
-
-                # Save chat history to file with timestamp
-                chat_histories = load_chat_history()
-                timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
-                if username not in chat_histories:
-                    chat_histories[username] = []
-                chat_histories[username].append({
-                    "timestamp": timestamp,
-                    "user": user_input,
-                    "assistant": assistant_response
-                })
-                save_chat_history(chat_histories)
-
-
-
-
-
-
-
-
-
-
-# import os
-# import json
-
-# import streamlit as st
-# from langchain_huggingface import HuggingFaceEmbeddings
-# from langchain_chroma import Chroma
-# from langchain_groq import ChatGroq
-# from langchain.memory import ConversationBufferMemory
-# from langchain.chains import ConversationalRetrievalChain
-
-# from vectorize_documents import embeddings
-
-
-# working_dir = os.path.dirname(os.path.abspath(__file__))
-# config_data = json.load(open(f"{working_dir}/config.json"))
-# GROQ_API_KEY = config_data["GROQ_API_KEY"]
-# os.environ["GROQ_API_KEY"]= GROQ_API_KEY
-
-
-# def setup_vectorstore():
-#     persist_directory = f"{working_dir}/vector_db_dir_notes_ai"
-#     embeddings = HuggingFaceEmbeddings()
-#     vectorstore = Chroma(persist_directory=persist_directory,
-#                          embedding_function=embeddings)
-#     return vectorstore
-
-# def chat_chain(vectorstore):
-#     llm = ChatGroq(
-#         model = "llama-3.1-70b-versatile",
-#         temperature = 0
-#     )
-#     retriever = vectorstore.as_retriever()
-#     memory = ConversationBufferMemory(
-#         llm = llm,
-#         output_key = "answer",
-#         memory_key = "chat_history",
-#         return_messages = True
-#     )
-#     chain = ConversationalRetrievalChain.from_llm(
-#         llm=llm,
-#         retriever = retriever,
-#         chain_type = "stuff",
-#         memory = memory,
-#         verbose=True,
-#         return_source_documents= True
-#     )
-#     return chain
-
-# st.set_page_config(
-#     page_title="Notes.AI",
-#     page_icon="🤖AI",
-#     layout="centered"
-# )
-
-# st.title("🤖 Notes.AI")
-
-# # st.title("🤖 Hey! Here you can search for notes of CSE 7th Sem! Read Notes, Read PYQ answers also!!")
-
-# st.subheader("Hey! Here you can search for notes of CSE 7th Sem! Read Notes, Read PYQ answers also!!")
-
-# # Additional subheading
-# st.subheader("Start your query below to get instant help!")
-
-# if "chat_history" not in st.session_state:
-#     st.session_state.chat_history = []
-
-# if "vectorstore" not in st.session_state:
-#     st.session_state.vectorstore = setup_vectorstore()
-
-# if "conversational_chain" not in st.session_state:
-#     st.session_state.conversational_chain = chat_chain(st.session_state.vectorstore)
-
-# for message in st.session_state.chat_history:
-#     with st.chat_message(message["role"]):
-#         st.markdown(message["content"])
-# user_input = st.chat_input("Ask AI....")
-
-# if user_input:
-#     st.session_state.chat_history.append({"role":"user", "content":user_input})
-
-#     with st.chat_message("user"):
-#         st.markdown(user_input)
-
-#     with st.chat_message("assistant"):
-#         response = st.session_state.conversational_chain({"question":user_input})
-#         assistant_response = response["answer"]
-#         st.markdown(assistant_response)
-#         st.session_state.chat_history.append({"role":"assistant","content": assistant_response})
+import os
+import json
+from datetime import datetime
+import streamlit as st
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_chroma import Chroma
+from langchain_groq import ChatGroq
+from langchain.memory import ConversationBufferMemory
+from langchain.chains import ConversationalRetrievalChain
+from vectorize_documents import embeddings
+
+working_dir = os.path.dirname(os.path.abspath(__file__))
+config_data = json.load(open(f"{working_dir}/config.json"))
+GROQ_API_KEY = config_data["GROQ_API_KEY"]
+os.environ["GROQ_API_KEY"] = GROQ_API_KEY
+
+# Ensure the JSON file exists
+chat_history_file = "chat_histories.json"
+if not os.path.exists(chat_history_file):
+    with open(chat_history_file, "w") as f:
+        json.dump({}, f)
+
+# Functions to handle chat history
+def load_chat_history():
+    with open(chat_history_file, "r") as f:
+        return json.load(f)
+
+def save_chat_history(chat_histories):
+    with open(chat_history_file, "w") as f:
+        json.dump(chat_histories, f, indent=4)
+
+# Function to set up vectorstore
+def setup_vectorstore():
+    embeddings = HuggingFaceEmbeddings()
+    vectorstore = Chroma(persist_directory="vector_db_dir_notes_ai",
+                         embedding_function=embeddings)
+    return vectorstore
+
+# Function to set up chatbot chain
+def chat_chain(vectorstore):
+    llm = ChatGroq(
+        model="llama-3.1-70b-versatile",
+        temperature=0
+    )
+    retriever = vectorstore.as_retriever()
+    memory = ConversationBufferMemory(
+        llm=llm,
+        output_key="answer",
+        memory_key="chat_history",
+        return_messages=True
+    )
+    chain = ConversationalRetrievalChain.from_llm(
+        llm=llm,
+        retriever=retriever,
+        chain_type="stuff",
+        memory=memory,
+        verbose=True,
+        return_source_documents=True
+    )
+    return chain
+
+# Streamlit UI
+st.set_page_config(
+    page_title="Notes.AI",
+    page_icon="🤖AI",
+    layout="centered"
+)
+
+st.title("🤖 Notes.AI")
+st.subheader("Hey! Upload your question bank and get answers instantly!")
+
+# Step 1: Input user's name
+if "username" not in st.session_state:
+    username = st.text_input("Enter your name to proceed:")
+    if username:
+        with st.spinner("Loading chatbot interface... Please wait."):
+            st.session_state.username = username
+            st.session_state.chat_history = []  # Initialize empty chat history
+            st.session_state.vectorstore = setup_vectorstore()
+            st.session_state.conversational_chain = chat_chain(st.session_state.vectorstore)
+            st.success(f"Welcome, {username}! The chatbot interface is ready.")
+else:
+    username = st.session_state.username
+
+# Step 2: Initialize components if not already set
+if "conversational_chain" not in st.session_state:
+    st.session_state.vectorstore = setup_vectorstore()
+    st.session_state.conversational_chain = chat_chain(st.session_state.vectorstore)
+
+# Step 3: File upload for question bank
+st.subheader("Upload your question bank (PDF or DOC):")
+uploaded_file = st.file_uploader("Choose a file", type=["pdf", "doc", "docx"])
+
+if uploaded_file:
+    # Process the uploaded file
+    with st.spinner("Reading and processing your question bank..."):
+        import docx2txt
+        from PyPDF2 import PdfReader
+
+        # Extract questions from the file
+        def extract_questions(file):
+            if file.name.endswith(".pdf"):
+                reader = PdfReader(file)
+                text = "\n".join([page.extract_text() for page in reader.pages])
+            elif file.name.endswith((".doc", ".docx")):
+                text = docx2txt.process(file)
+            else:
+                text = ""
+            return text.strip().split("\n")
+
+        questions = extract_questions(uploaded_file)
+
+        # Generate answers using the LLM
+        answers = []
+        for question in questions:
+            if question.strip():
+                response = st.session_state.conversational_chain({"question": question})
+                answers.append({"question": question, "answer": response["answer"]})
+
+        # Save Q&A to a file
+        output_file_path = f"question_answers_{username}.txt"
+        with open(output_file_path, "w") as f:
+            for qa in answers:
+                f.write(f"Q: {qa['question']}\nA: {qa['answer']}\n\n")
+
+        st.success("All questions have been answered and saved!")
+
+        # Provide download link
+        with open(output_file_path, "rb") as f:
+            st.download_button(
+                label="Download Q&A File",
+                data=f,
+                file_name=output_file_path,
+                mime="text/plain"
+            )
+
+# Chatbot interface for additional questions
+st.subheader(f"Hello {username}, ask additional questions below!")
+if "username" in st.session_state:
+    # Display existing chat history dynamically
+    for message in st.session_state.chat_history:
+        if message["role"] == "user":
+            with st.chat_message("user"):
+                st.markdown(message["content"])
+        elif message["role"] == "assistant":
+            with st.chat_message("assistant"):
+                st.markdown(message["content"])
+
+    # User input section
+    user_input = st.chat_input("Ask AI....")
+    if user_input:
+        with st.spinner("Processing your query... Please wait."):
+            # Save user input to session state
+            st.session_state.chat_history.append({"role": "user", "content": user_input})
+
+            # Display user's message
+            with st.chat_message("user"):
+                st.markdown(user_input)
+
+            # Get assistant's response
+            with st.chat_message("assistant"):
+                response = st.session_state.conversational_chain({"question": user_input})
+                assistant_response = response["answer"]
+                st.markdown(assistant_response)
+
+                # Save assistant's response to session state
+                st.session_state.chat_history.append({"role": "assistant", "content": assistant_response})
+
+                # Save chat history to file with timestamp
+                chat_histories = load_chat_history()
+                timestamp = datetime.now().strftime("%Y-%m-%d %A")  # Added day to timestamp
+                if username not in chat_histories:
+                    chat_histories[username] = []
+                chat_histories[username].append({
+                    "timestamp": timestamp,
+                    "user": user_input,
+                    "assistant": assistant_response
+                })
+                save_chat_history(chat_histories)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+# all working but file upload is not added in below code 
+
+# import os
+# import json
+# from datetime import datetime
+# import streamlit as st
+# from langchain_huggingface import HuggingFaceEmbeddings
+# from langchain_chroma import Chroma
+# from langchain_groq import ChatGroq
+# from langchain.memory import ConversationBufferMemory
+# from langchain.chains import ConversationalRetrievalChain
+
+
+# from vectorize_documents import embeddings
+
+# working_dir = os.path.dirname(os.path.abspath(__file__))
+# config_data = json.load(open(f"{working_dir}/config.json"))
+# GROQ_API_KEY = config_data["GROQ_API_KEY"]
+# os.environ["GROQ_API_KEY"]= GROQ_API_KEY
+
+# # Ensure the JSON file exists
+# chat_history_file = "chat_histories.json"
+# if not os.path.exists(chat_history_file):
+#     with open(chat_history_file, "w") as f:
+#         json.dump({}, f)
+
+# # Functions to handle chat history
+# def load_chat_history():
+#     with open(chat_history_file, "r") as f:
+#         return json.load(f)
+
+# def save_chat_history(chat_histories):
+#     with open(chat_history_file, "w") as f:
+#         json.dump(chat_histories, f, indent=4)
+
+# # Function to set up vectorstore
+# def setup_vectorstore():
+#     embeddings = HuggingFaceEmbeddings()
+#     vectorstore = Chroma(persist_directory="vector_db_dir_notes_ai",
+#                          embedding_function=embeddings)
+#     return vectorstore
+
+# # Function to set up chatbot chain
+# def chat_chain(vectorstore):
+#     llm = ChatGroq(
+#         model="llama-3.1-70b-versatile",
+#         temperature=0
+#     )
+#     retriever = vectorstore.as_retriever()
+#     memory = ConversationBufferMemory(
+#         llm=llm,
+#         output_key="answer",
+#         memory_key="chat_history",
+#         return_messages=True
+#     )
+#     chain = ConversationalRetrievalChain.from_llm(
+#         llm=llm,
+#         retriever=retriever,
+#         chain_type="stuff",
+#         memory=memory,
+#         verbose=True,
+#         return_source_documents=True
+#     )
+#     return chain
+
+# # Streamlit UI
+# st.set_page_config(
+#     page_title="Notes.AI",
+#     page_icon="🤖AI",
+#     layout="centered"
+# )
+
+# st.title("🤖 Notes.AI")
+# st.subheader("Hey! Here you can search for notes of CSE 7th Sem! Read Notes, Read PYQ answers also!!")
+
+# # Step 1: Input user's name
+# if "username" not in st.session_state:
+#     username = st.text_input("Enter your name to proceed:")
+#     if username:
+#         with st.spinner("Loading chatbot interface... Please wait."):
+#             st.session_state.username = username
+#             st.session_state.chat_history = []  # Initialize empty chat history
+#             st.session_state.vectorstore = setup_vectorstore()
+#             st.session_state.conversational_chain = chat_chain(st.session_state.vectorstore)
+#             st.success(f"Welcome, {username}! The chatbot interface is ready.")
+# else:
+#     username = st.session_state.username
+
+# # Step 2: Initialize components if not already set
+# if "conversational_chain" not in st.session_state:
+#     st.session_state.vectorstore = setup_vectorstore()
+#     st.session_state.conversational_chain = chat_chain(st.session_state.vectorstore)
+
+# # Step 3: Show chatbot interface
+# if "username" in st.session_state:
+#     st.subheader(f"Hello {username}, start your query below!")
+
+#     # Display existing chat history dynamically
+#     for message in st.session_state.chat_history:
+#         if message["role"] == "user":
+#             with st.chat_message("user"):
+#                 st.markdown(message["content"])
+#         elif message["role"] == "assistant":
+#             with st.chat_message("assistant"):
+#                 st.markdown(message["content"])
+
+#     # User input section
+#     user_input = st.chat_input("Ask AI....")
+#     if user_input:
+#         with st.spinner("Processing your query... Please wait."):
+#             # Save user input to session state
+#             st.session_state.chat_history.append({"role": "user", "content": user_input})
+
+#             # Display user's message
+#             with st.chat_message("user"):
+#                 st.markdown(user_input)
+
+#             # Get assistant's response
+#             with st.chat_message("assistant"):
+#                 response = st.session_state.conversational_chain({"question": user_input})
+#                 assistant_response = response["answer"]
+#                 st.markdown(assistant_response)
+
+#                 # Save assistant's response to session state
+#                 st.session_state.chat_history.append({"role": "assistant", "content": assistant_response})
+
+#                 # Save chat history to file with timestamp
+#                 chat_histories = load_chat_history()
+#                 timestamp = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
+#                 if username not in chat_histories:
+#                     chat_histories[username] = []
+#                 chat_histories[username].append({
+#                     "timestamp": timestamp,
+#                     "user": user_input,
+#                     "assistant": assistant_response
+#                 })
+#                 save_chat_history(chat_histories)
+
+
+
+
+
+
+
+