Spaces:
Runtime error
Runtime error
File size: 3,605 Bytes
1d7dab1 841a0f0 1d7dab1 2cbe2cb 1d7dab1 750ae7b 1d7dab1 2cbe2cb 0992338 1d7dab1 c92795e 1d7dab1 7076b24 1d7dab1 c92795e 7c83c27 1d7dab1 a5d6670 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 |
import streamlit as st
# from langchain_community.llms import HuggingFaceTextGenInference
import os
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.schema import StrOutputParser
from custom_llm import CustomLLM, custom_chain_with_history
API_TOKEN = os.getenv('HF_INFER_API')
from typing import Optional
from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_community.chat_models import ChatAnthropic
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 V2 Sample")
st.subheader("Knowledge-base from web scrapping and FAQ")
# 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}) |