Update app.py

app.py

@@ -14,90 +14,90 @@ import time
 # Load environment variables
 load_dotenv()
 
-groq_api_key = os.getenv('groqapi')
-google_api_key = os.getenv("GOOGLE_API_KEY")
-
-if not groq_api_key or not google_api_key:
-    st.error("API keys are missing. Please check your environment variables.")
-    st.stop()
+# Set page configuration
+st.set_page_config(page_title="Legal Assistant", layout="wide")
 
-os.environ["GOOGLE_API_KEY"] = google_api_key
+# Initialize session state for chat history if not exists
+if 'chat_history' not in st.session_state:
+    st.session_state.chat_history = []
 
+# Title
 st.title("Legal Assistant")
 
-# Initialize LLM
-llm = ChatGroq(groq_api_key=groq_api_key, model_name="Llama3-8b-8192")
+# Sidebar setup
+st.sidebar.title("Chat History")
+
+# API Key Configuration
+groq_api_key = os.getenv('groqapi')
+os.environ["GOOGLE_API_KEY"] = os.getenv("GOOGLE_API_KEY")
 
+# LLM and Prompt Setup
+llm = ChatGroq(groq_api_key=groq_api_key, model_name="Llama3-8b-8192")
 prompt = ChatPromptTemplate.from_template(
-    """
-    Answer the questions based on the provided context only.
-    Please provide the most accurate response based on the question.
-    <context>
-    {context}
-    <context>
-    Questions: {input}
-    """
+"""
+Answer the questions based on the provided context only.
+Please provide the most accurate response based on the question
+<context>
+{context}
+<context>
+Questions:{input}
+"""
 )
 
-@st.cache_resource
 def vector_embedding():
-    embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-    loader = PyPDFDirectoryLoader("./new")
-    
-    # Check if directory exists
-    if not os.path.exists("./new"):
-        st.error("The directory './new' does not exist. Please provide the correct path.")
-        st.stop()
-    
-    docs = loader.load()
-    if not docs:
-        st.error("No PDF files found in the './new' directory.")
-        st.stop()
-
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    final_documents = text_splitter.split_documents(docs[:20])
-    vectors = FAISS.from_documents(final_documents, embeddings)
-    return vectors
+    """Perform vector embedding of documents"""
+    if "vectors" not in st.session_state:
+        st.session_state.embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
+        st.session_state.loader = PyPDFDirectoryLoader("./new")  # Data Ingestion
+        st.session_state.docs = st.session_state.loader.load()  # Document Loading
+        st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)  # Chunk Creation
+        st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs[:20])  # splitting
+        st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents, st.session_state.embeddings)
 
-st.session_state.vectors = vector_embedding()
+# Perform vector embedding
+vector_embedding()
 
-# Initialize chat history
-if "chat_history" not in st.session_state:
-    st.session_state.chat_history = []
-
-# Sidebar for chat history
-with st.sidebar:
-    st.title("Chat History")
-    for idx, chat in enumerate(st.session_state.chat_history):
-        # Create a button for each question
-        if st.button(f"Q{idx+1}: {chat['question']}"):
-            # When the button is clicked, display the corresponding answer below the question
-            st.session_state.selected_answer = chat['answer']
-            st.session_state.selected_question = chat['question']
-
-# Show selected chat history question and answer
-if 'selected_answer' in st.session_state:
-    st.write(f"**Q:** {st.session_state.selected_question}")
-    st.write(f"**A:** {st.session_state.selected_answer}")
-else:
-    st.write("No question selected from chat history yet.")
-
-# User input for new question
+# Main input area
 prompt1 = st.text_input("Enter Your Question From Documents")
 
+# Function to add to chat history
+def add_to_chat_history(question, answer):
+    st.session_state.chat_history.append({
+        'question': question,
+        'answer': answer
+    })
+
+# Process question and generate response
 if prompt1:
-    with st.spinner("Retrieving the best answer..."):
+    try:
+        # Create document and retrieval chains
         document_chain = create_stuff_documents_chain(llm, prompt)
         retriever = st.session_state.vectors.as_retriever()
         retrieval_chain = create_retrieval_chain(retriever, document_chain)
         
+        # Generate response
         start = time.process_time()
         response = retrieval_chain.invoke({'input': prompt1})
-        elapsed_time = time.process_time() - start
+        response_time = time.process_time() - start
         
-        answer = response.get('answer', "No answer found.")
-        st.success(f"Response Time: {elapsed_time:.2f} seconds")
-        st.write(answer)
+        # Display response
+        st.write(response['answer'])
         
-        # Store the question and answer in chat history
-        st.session_state.chat_history.append({"question": prompt1, "answer": answer})
+        # Add to chat history
+        add_to_chat_history(prompt1, response['answer'])
+    
+    except Exception as e:
+        st.error(f"An error occurred: {e}")
+
+# Sidebar content
+# Clear chat history button
+if st.sidebar.button("Clear Chat History"):
+    st.session_state.chat_history = []
+
+# Display chat history
+st.sidebar.write("### Previous Questions")
+for idx, chat in enumerate(reversed(st.session_state.chat_history), 1):
+    # Create a button for each previous question
+    if st.sidebar.button(f"Question {len(st.session_state.chat_history) - idx + 1}: {chat['question']}"):
+        # Display the corresponding answer when the button is clicked
+        st.sidebar.write(f"**Answer:** {chat['answer']}")