Update app.py

app.py

@@ -9,100 +9,62 @@ 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 time
-
-# Load environment variables
+import os
 load_dotenv()
-groq_api_key = os.getenv('groqapi')
-os.environ["GOOGLE_API_KEY"] = os.getenv("GOOGLE_API_KEY")
 
-# Check for missing API keys
-if not groq_api_key or not os.environ["GOOGLE_API_KEY"]:
-    st.error("API keys are missing. Check your .env file.")
-    st.stop()
+## load the GROQ And OpenAI API 
+
+groq_api_key=os.getenv('groqapi')
+os.environ["GOOGLE_API_KEY"]=os.getenv("GOOGLE_API_KEY")
 
-# Title
 st.title("Legal Assistant")
 
-# Initialize LLM
-llm = ChatGroq(
-    groq_api_key=groq_api_key,
-    model_name="Llama3-8b-8192"
-)
+llm=ChatGroq(groq_api_key=groq_api_key,
+             model_name="Llama3-8b-8192")
 
-# Define prompt
-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}
-    """
+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}
+
+"""
 )
 
-# Function to handle vector embedding
 def vector_embedding():
+
     if "vectors" not in st.session_state:
-        try:
-            # Initialize embeddings
-            st.session_state.embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")
-            
-            # Load documents
-            st.session_state.loader = PyPDFDirectoryLoader("./new")  # Data ingestion
-            st.session_state.docs = st.session_state.loader.load()
-            
-            if not st.session_state.docs:
-                st.error("No documents found in the directory './new'. Please add PDFs.")
-                return
-            
-            # Split documents into chunks
-            st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-            st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs)
-            
-            if not st.session_state.final_documents:
-                st.error("Document splitting failed. Check the loaded documents.")
-                return
-            
-            # Generate vector embeddings
-            st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents, st.session_state.embeddings)
-        
-        except Exception as e:
-            st.error(f"Error during vector embedding: {e}")
-
-# Call vector_embedding function
+
+        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()
 
-# User input for query
-prompt1 = st.text_input("Enter Your Question From Documents")
+
+
+prompt1=st.text_input("Enter Your Question From Doduments")
+
+
+
+
+import time
+
+
 
 if prompt1:
-    try:
-        # Create document chain and retrieval chain
-        document_chain = create_stuff_documents_chain(llm, prompt)
-        retriever = st.session_state.vectors.as_retriever()
-        retrieval_chain = create_retrieval_chain(retriever, document_chain)
-        
-        # Measure response time
-        start = time.process_time()
-        response = retrieval_chain.invoke({'input': prompt1})
-        end = time.process_time()
-        
-        # Display response and response time
-        if "answer" in response:
-            st.write(response["answer"])
-        else:
-            st.error("No answer could be generated. Please try a different query.")
-        
-        st.write(f"Response time: {end - start:.2f} seconds")
-    
-    except Exception as e:
-        st.error(f"Error processing the query: {e}")
-
-# Reset session state button
-if st.button("Reset Session"):
-    for key in ["embeddings", "loader", "docs", "text_splitter", "final_documents", "vectors"]:
-        if key in st.session_state:
-            del st.session_state[key]
-    st.experimental_rerun()
+    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'])
+
+