Update app.py

app.py

@@ -9,7 +9,7 @@ from langchain_cohere import CohereEmbeddings
 from langchain.vectorstores import FAISS
 from langchain.memory import ConversationBufferMemory
 from langchain.chains import ConversationalRetrievalChain
-from cohere.errors import TooManyRequestsError
+from langchain_groq import ChatGroq
 
 # Load environment variables
 load_dotenv()
@@ -40,39 +40,37 @@ def get_text_chunks(text):
     chunks = text_splitter.split_text(text)
     return chunks
 
-# Function to create a FAISS vectorstore with error handling for rate limits
+# Function to create a FAISS vectorstore with rate limiting
 def get_vectorstore(text_chunks):
     cohere_api_key = os.getenv("COHERE_API_KEY")
     embeddings = CohereEmbeddings(model="embed-english-v3.0", cohere_api_key=cohere_api_key)
 
-    retries = 5  # Number of retries before giving up
-    for attempt in range(retries):
-        try:
-            vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
-            return vectorstore
-        except TooManyRequestsError as e:
-            logging.warning(f"Rate limit exceeded: {e}. Retrying in {attempt + 1} seconds...")
-            time.sleep(attempt + 1)  # Exponential backoff
-        except Exception as e:
-            logging.error(f"Error creating vectorstore: {e}")
-            st.error("An error occurred while creating the vectorstore.")
-            break
-
-    st.error("Failed to create vectorstore after multiple attempts due to rate limits.")
-    return None
+    # Rate limiting: Ensure no more than 40 requests per minute
+    max_requests_per_minute = 40
+    wait_time = 60 / max_requests_per_minute
+
+    vectorstore = None
+    try:
+        vectorstore = FAISS.from_texts(texts=text_chunks, embedding=embeddings)
+        time.sleep(wait_time)  # Sleep to avoid hitting API rate limit
+    except Exception as e:
+        logging.error(f"Error creating vectorstore: {e}")
+        st.error("An error occurred while creating the vectorstore.")
+    
+    return vectorstore
 
 # Function to set up the conversational retrieval chain
 def get_conversation_chain(vectorstore):
     try:
         llm = ChatGroq(model="llama-3.1-70b-versatile", temperature=0.5)
         memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
-        
+
         conversation_chain = ConversationalRetrievalChain.from_llm(
             llm=llm,
             retriever=vectorstore.as_retriever(),
             memory=memory
         )
-        
+
         logging.info("Conversation chain created successfully.")
         return conversation_chain
     except Exception as e:
@@ -105,6 +103,7 @@ def main():
 
     st.header("Chat with multiple PDFs :books:")
     user_question = st.text_input("Ask a question about your documents:")
+    
     if user_question:
         handle_userinput(user_question)
 
@@ -113,14 +112,16 @@ def main():
         pdf_docs = st.file_uploader(
             "Upload your PDFs here and click on 'Process'", accept_multiple_files=True
         )
+        
         if st.button("Process"):
             with st.spinner("Processing..."):
                 raw_text = get_pdf_text(pdf_docs)
                 text_chunks = get_text_chunks(raw_text)
                 vectorstore = get_vectorstore(text_chunks)
-                if vectorstore is not None:  # Only proceed if vectorstore creation was successful
+                if vectorstore is not None:  # Ensure vectorstore was created successfully
                     st.session_state.conversation = get_conversation_chain(vectorstore)
 
 if __name__ == '__main__':
     main()
 
+