Update app.py

app.py

@@ -2,6 +2,7 @@ import streamlit as st
 from streamlit_chat import message
 from langchain.chains import ConversationalRetrievalChain
 from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.llms import CTransformers
 from langchain.llms import Replicate
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.vectorstores import FAISS
@@ -14,8 +15,10 @@ import os
 from dotenv import load_dotenv
 import tempfile
 
+
 load_dotenv()
 
+
 def initialize_session_state():
     if 'history' not in st.session_state:
         st.session_state['history'] = []
@@ -36,31 +39,35 @@ def display_chat_history(chain):
     container = st.container()
 
     with container:
-        col1, col2 = st.columns(2)
+        with st.form(key='my_form', clear_on_submit=True):
+            user_input = st.text_input("Question:", placeholder="Ask about your Documents", key='input')
+            submit_button = st.form_submit_button(label='Send')
+
+        if submit_button and user_input:
+            with st.spinner('Generating response...'):
+                output = conversation_chat(user_input, chain, st.session_state['history'])
 
-        with col1:
-            with st.form(key='my_form', clear_on_submit=True):
-                user_input = st.text_input("Question:", placeholder="Ask about your Documents", key='input')
-                submit_button = st.form_submit_button(label='Send')
+            st.session_state['past'].append(user_input)
+            st.session_state['generated'].append(output)
 
-        with col2:
-            if st.session_state['generated']:
-                for i in range(len(st.session_state['generated'])):
-                    message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="thumbs")
-                    message(st.session_state["generated"][i], key=str(i), avatar_style="fun-emoji")
+    if st.session_state['generated']:
+        with reply_container:
+            for i in range(len(st.session_state['generated'])):
+                message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="thumbs")
+                message(st.session_state["generated"][i], key=str(i), avatar_style="fun-emoji")
 
 def create_conversational_chain(vector_store):
     load_dotenv()
-    replicate_api_token = "r8_AA3K1fhDykqLa5M74E5V0w5ss1z0P9S3foWJl"  # Replace with your actual token
-    os.environ["REPLICATE_API_TOKEN"] = replicate_api_token
-
+    # Create llm
+    #llm = CTransformers(model="llama-2-7b-chat.ggmlv3.q4_0.bin",
+                        #streaming=True,
+                        #callbacks=[StreamingStdOutCallbackHandler()],
+                        #model_type="llama", config={'max_new_tokens': 500, 'temperature': 0.01})
     llm = Replicate(
-        streaming=True,
-        model="replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781",
+        streaming = True,
+        model = "replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781",
         callbacks=[StreamingStdOutCallbackHandler()],
-        input={"temperature": 0.01, "max_length": 500, "top_p": 1},
-        replicate_api_token=replicate_api_token
-    )
+        input = {"temperature": 0.01, "max_length" :500,"top_p":1})
     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
 
     chain = ConversationalRetrievalChain.from_llm(llm=llm, chain_type='stuff',
@@ -71,10 +78,12 @@ def create_conversational_chain(vector_store):
 def main():
     load_dotenv()
     initialize_session_state()
-    st.title("Chat With Your Doc")
+    st.title("ChatBot ")
+    # Initialize Streamlit
     st.sidebar.title("Document Processing")
     uploaded_files = st.sidebar.file_uploader("Upload files", accept_multiple_files=True)
 
+
     if uploaded_files:
         text = []
         for file in uploaded_files:
@@ -98,11 +107,18 @@ def main():
         text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=100, length_function=len)
         text_chunks = text_splitter.split_documents(text)
 
+        # Create embeddings
         embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
                                            model_kwargs={'device': 'cpu'})
+
+        # Create vector store
         vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
+
+        # Create the chain object
         chain = create_conversational_chain(vector_store)
+
+
         display_chat_history(chain)
 
 if __name__ == "__main__":
-    main()
+    main()