app.py

from Functions.write_stream import user_data
import streamlit as st
from llama_index.core import SimpleDirectoryReader, VectorStoreIndex, ServiceContext
from llama_index.llms.llama_cpp import LlamaCPP
from llama_index.llms.llama_cpp.llama_utils import messages_to_prompt, completion_to_prompt
from langchain.embeddings.huggingface import HuggingFaceEmbeddings


directory = "Knowledge Base/"


documents = SimpleDirectoryReader(directory).load_data()

llm = LlamaCPP(
# You can pass in the URL to a GGML model to download it automatically
model_url='https://huggingface.co/TheBloke/Mistral-7B-Instruct-v0.1-GGUF/resolve/main/mistral-7b-instruct-v0.1.Q4_K_M.gguf',
# optionally, you can set the path to a pre-downloaded model instead of model_url
model_path=None,
temperature=0.75,
max_new_tokens=256,
# llama2 has a context window of 4096 tokens, but we set it lower to allow for some wiggle room
context_window=3900,
messages_to_prompt=messages_to_prompt,
completion_to_prompt=completion_to_prompt,
verbose=True,
)
print("working -3")

embed_model = HuggingFaceEmbeddings(model_name="thenlper/gte-large")

print("working -2")

service_context = ServiceContext.from_defaults(
    chunk_size= 256,
    llm=llm,
    embed_model=embed_model
)
print("working -1")

index = VectorStoreIndex.from_documents(documents, service_context=service_context, show_progress=True)
print("working 0")

query_engine = index.as_query_engine()



###############=============    USER INTERFACE (UI    )###############=============


st.title("Wiki Bot")

if "messages" not in st.session_state:
    st.session_state.messages = []


for message in st.session_state.messages:
    with st.chat_message(message["role"]):
        st.markdown(message["content"])


prompt = st.chat_input("Enter Your Question:")


if prompt:

    with st.chat_message("user"):
        st.markdown(prompt)
    st.session_state.messages.append({"role":"user","content":prompt})
    
    reply= query_engine.query(prompt)
    response = user_data(function_name=reply)

    with st.chat_message("assistant"):
        st.write_stream(response)
    print("working!!")
    st.session_state.messages.append({"role":"assistant","content":reply})