app.py

import streamlit as st
import random
import time
import os
from langchain_together import ChatTogether
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.document_loaders import TextLoader
from langchain_core.prompts import ChatPromptTemplate
from langchain_community.vectorstores import FAISS
from langchain_core.output_parsers import StrOutputParser
from langchain_core.runnables import RunnablePassthrough
from langchain_together import TogetherEmbeddings

os.environ["TOGETHER_API_KEY"] = "6216ce36aadcb06c35436e7d6bbbc18b354d8140f6e805db485d70ecff4481d0"

#load
loader = TextLoader("Resume_data.txt")
documents = loader.load()

# split it into chunks
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
docs = text_splitter.split_documents(documents)
vectorstore = FAISS.from_documents(docs,
     TogetherEmbeddings(model="togethercomputer/m2-bert-80M-8k-retrieval")
)

retriever = vectorstore.as_retriever()
print("assigning model")
model = ChatTogether(
    model="meta-llama/Llama-3-70b-chat-hf",    
    temperature=0.0,
    max_tokens=500,)

# template = """<s>[INST] answer from context only as if person is responding (use i instead of you in response). and always answer in short answer.
# answer for asked question only, if he greets greet back.
template = """
{context}
Question: {question} [/INST] 
"""
prompt = ChatPromptTemplate.from_template(template) 

chain = (
    {"context": retriever, "question": RunnablePassthrough()}
    | prompt
    | model
    | StrOutputParser()
)


st.title("Simple chat")

# Initialize chat history
if "messages" not in st.session_state:
    st.session_state.messages = []

# 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"])

# Accept user input
if prompt := st.chat_input("What is up?"):
    # Display user message in chat message container
    with st.chat_message("user"):
        st.markdown(prompt)
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})

############################################
# Streamed response emulator
def response_generator():
    query = f"echo {prompt}"
    # for m in chain.stream(query):
    #     print(m)
    #     yield m + " "
    #     time.sleep(0.05)
    return chain.invoke(query)
###########################################
# Display assistant response in chat message container
with st.chat_message("assistant"):
    response = st.markdown(response_generator())
# Add assistant response to chat history
st.session_state.messages.append({"role": "assistant", "content": response})