Update app.py

app.py

@@ -9,62 +9,88 @@ from langchain_community.vectorstores import FAISS
 from langchain_community.document_loaders import PyPDFDirectoryLoader
 from langchain_google_genai import GoogleGenerativeAIEmbeddings
 from dotenv import load_dotenv
-import os
-load_dotenv()
+import time
 
-## load the GROQ And OpenAI API 
+# Load environment variables
+load_dotenv()
 
-groq_api_key=os.getenv('groqapi')
-os.environ["GOOGLE_API_KEY"]=os.getenv("GOOGLE_API_KEY")
+groq_api_key = os.getenv('groqapi')
+google_api_key = os.getenv("GOOGLE_API_KEY")
 
-st.title("Legal Assistant")
+if not groq_api_key or not google_api_key:
+    st.error("API keys are missing. Please check your environment variables.")
+    st.stop()
 
-llm=ChatGroq(groq_api_key=groq_api_key,
-             model_name="Llama3-8b-8192")
+os.environ["GOOGLE_API_KEY"] = google_api_key
 
-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}
+st.title("Legal Assistant")
 
-"""
+# Initialize LLM
+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}
+    """
 )
 
+@st.cache_resource
 def vector_embedding():
-
-    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) #vector OpenAI embeddings
-
-vector_embedding()
-
-
-
-prompt1=st.text_input("Enter Your Question From Doduments")
-
-
-
-
-import time
-
-
+    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
+
+st.session_state.vectors = 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")
+    if st.session_state.chat_history:
+        for idx, chat in enumerate(st.session_state.chat_history):
+            st.write(f"Q{idx+1}: {chat['question']}")
+            st.write(f"A{idx+1}: {chat['answer']}")
+    else:
+        st.write("No chat history yet.")
+
+# User input for question
+prompt1 = st.text_input("Enter Your Question From Documents")
 
 if prompt1:
-    document_chain=create_stuff_documents_chain(llm,prompt)
-    retriever=st.session_state.vectors.as_retriever()
-    retrieval_chain=create_retrieval_chain(retriever,document_chain)
-    start=time.process_time()
-    response=retrieval_chain.invoke({'input':prompt1})
-    print("Response time :",time.process_time()-start)
-    st.write(response['answer'])
-
-    
+    with st.spinner("Retrieving the best answer..."):
+        document_chain = create_stuff_documents_chain(llm, prompt)
+        retriever = st.session_state.vectors.as_retriever()
+        retrieval_chain = create_retrieval_chain(retriever, document_chain)
+        
+        start = time.process_time()
+        response = retrieval_chain.invoke({'input': prompt1})
+        elapsed_time = time.process_time() - start
+        
+        answer = response.get('answer', "No answer found.")
+        st.success(f"Response Time: {elapsed_time:.2f} seconds")
+        st.write(answer)
+        
+        # Store the question and answer in chat history
+        st.session_state.chat_history.append({"question": prompt1, "answer": answer})