Update app.py

app.py

@@ -18,55 +18,79 @@ from langchain_core.chat_history import BaseChatMessageHistory
 from langchain.memory import ConversationBufferMemory
 from langchain_core.runnables.history import RunnableWithMessageHistory
 
-@st.cache_resource
-def get_llm_chain():
-    return custom_chain_with_history(llm=CustomLLM(repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1", model_type='text-generation', api_token=API_TOKEN, stop=["\n<|","<|"]), memory=st.session_state.memory)
 
-if 'memory' not in st.session_state:
-    st.session_state['memory'] = ConversationBufferMemory(return_messages=True)
-    st.session_state.memory.chat_memory.add_ai_message("Hello there! I'm AI assistant of Lintas Media Danawa. How can I help you today?")
 
-if 'chain' not in st.session_state:
-    # st.session_state['chain'] = custom_chain_with_history(llm=CustomLLM(repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1", model_type='text-generation', api_token=API_TOKEN, stop=["\n<|","<|"]), memory=st.session_state.memory)
-    st.session_state['chain'] = get_llm_chain()
-    # st.session_state['chain'] = custom_chain_with_history(llm=InferenceClient("https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1", headers = {"Authorization": f"Bearer {API_TOKEN}"}, stream=True, max_new_tokens=512, temperature=0.01), memory=st.session_state.memory)
 st.title("LMD Chatbot Tiket Ebesha Management")
 st.subheader("Monthly Ticket Sample")
 
-# Initialize chat history
-if "messages" not in st.session_state:
-    st.session_state.messages = [{"role":"assistant", "content":"Hello there! I'm AI assistant of Lintas Media Danawa. How can I help you today?"}]
 
-# Display chat messages from history on app rerun
-for message in st.session_state.messages:
-    with st.chat_message(message["role"]):
-        st.markdown(message["content"])
+uploaded_files = st.file_uploader("Choose CSV or XLSX files", accept_multiple_files=True, type=["csv", "xlsx"])
+df_temp = []
+for uploaded_file in uploaded_files:
+    if uploaded_file.name.split(".")[-1] != 'csv':
+        a = pd.read_excel(uploaded_file)
+        uploaded_file = uploaded_file.name.split(".")[0]+".csv"
+        a.to_csv(uploaded_file, encoding="utf8", header=True, index=False)
+        
+    df_temp.append(pd.read_csv(uploaded_file))
 
-# React to user input
-if prompt := st.chat_input("Ask me anything.."):
-    # Display user message in chat message container
-    st.chat_message("User").markdown(prompt)
-    # Add user message to chat history
-    st.session_state.messages.append({"role": "User", "content": prompt})
-    
-    # full_response = st.session_state.chain.invoke(prompt).split("\n<|")[0]
-    full_response = st.session_state.chain.invoke({"question":prompt, "memory":st.session_state.memory}).split("\n<|")[0]
-    
 
-    with st.chat_message("assistant"):
-        st.markdown(full_response)
 
-    # Display assistant response in chat message container
-    # with st.chat_message("assistant"):
-    #     message_placeholder = st.empty()
-    #     full_response = ""
-    #     for chunk in st.session_state.chain.stream(prompt):
-    #         full_response += chunk + " "
-    #         message_placeholder.markdown(full_response + " ")
-    #         if full_response[-4:] == "\n<|":
-    #             break
-        # st.markdown(full_response)
-    st.session_state.memory.save_context({"question":prompt}, {"output":full_response})
-    st.session_state.memory.chat_memory.messages = st.session_state.memory.chat_memory.messages[-15:]
-    # Add assistant response to chat history
-    st.session_state.messages.append({"role": "assistant", "content": full_response})
+if uploaded_file:
+    
+    if "df" not in st.session_state:
+        st.session_state.df = pd.concat(df_temp)
+
+    @st.cache_resource
+    def get_llm_chain():
+        return custom_chain_with_history(llm=CustomLLM(repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1", model_type='text-generation', api_token=API_TOKEN, stop=["\n<|","<|"]), memory=st.session_state.memory, dataframe=st.session_state.df)
+    
+    if 'memory' not in st.session_state:
+        st.session_state['memory'] = ConversationBufferMemory(return_messages=True)
+        st.session_state.memory.chat_memory.add_ai_message("Hello there! I'm AI assistant of Lintas Media Danawa. How can I help you today?")
+    
+    if 'chain' not in st.session_state:
+        # st.session_state['chain'] = custom_chain_with_history(llm=CustomLLM(repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1", model_type='text-generation', api_token=API_TOKEN, stop=["\n<|","<|"]), memory=st.session_state.memory)
+        st.session_state['chain'] = get_llm_chain()
+        # st.session_state['chain'] = custom_chain_with_history(llm=InferenceClient("https://api-inference.huggingface.co/models/mistralai/Mixtral-8x7B-Instruct-v0.1", headers = {"Authorization": f"Bearer {API_TOKEN}"}, stream=True, max_new_tokens=512, temperature=0.01), memory=st.session_state.memory)
+    
+        
+    # Initialize chat history
+    if "messages" not in st.session_state:
+        st.session_state.messages = [{"role":"assistant", "content":"Hello there! I'm AI assistant of Lintas Media Danawa. How can I help you today?"}]
+    
+    # Display chat messages from history on app rerun
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"]):
+            st.markdown(message["content"])
+    
+    
+    
+    # React to user input
+    if prompt := st.chat_input("Ask me anything.."):
+        # Display user message in chat message container
+        st.chat_message("User").markdown(prompt)
+        # Add user message to chat history
+        st.session_state.messages.append({"role": "User", "content": prompt})
+        
+        # full_response = st.session_state.chain.invoke(prompt).split("\n<|")[0]
+        full_response = st.session_state.chain.invoke({"question":prompt, "memory":st.session_state.memory}).split("\n<|")[0]
+        
+    
+        with st.chat_message("assistant"):
+            st.markdown(full_response)
+    
+        # Display assistant response in chat message container
+        # with st.chat_message("assistant"):
+        #     message_placeholder = st.empty()
+        #     full_response = ""
+        #     for chunk in st.session_state.chain.stream(prompt):
+        #         full_response += chunk + " "
+        #         message_placeholder.markdown(full_response + " ")
+        #         if full_response[-4:] == "\n<|":
+        #             break
+            # st.markdown(full_response)
+        st.session_state.memory.save_context({"question":prompt}, {"output":full_response})
+        st.session_state.memory.chat_memory.messages = st.session_state.memory.chat_memory.messages[-15:]
+        # Add assistant response to chat history
+        st.session_state.messages.append({"role": "assistant", "content": full_response})