app.py

import os
import streamlit as st
from model import ChatModel
import rag_util

st.title("RAG By Karim Ben Khaled")

@st.cache_resource
def load_model():
    model = ChatModel(model_id="microsoft/Phi-3-mini-4k-instruct", device="cpu")
    return model

@st.cache_resource
def load_encoder():
    encoder = rag_util.Encoder(
        model_name="sentence-transformers/all-MiniLM-L12-v2", device="cpu"
    )
    return encoder

model = load_model()  # load our models once and then cache it
encoder = load_encoder()

def save_file(uploaded_file):
    """helper function to save documents to disk"""
    file_path = uploaded_file.name
    with open(file_path, "wb") as f:
        f.write(uploaded_file.getbuffer())
    return file_path

with st.sidebar:
    max_new_tokens = st.number_input("max_new_tokens", 128, 4096, 512)
    k = st.number_input("k", 1, 10, 3)
    uploaded_files = st.file_uploader(
        "Upload PDFs, CSVs, or JSONs for context", 
        type=["PDF", "pdf", "csv", "json"], 
        accept_multiple_files=True
    )
    file_paths = []
    for uploaded_file in uploaded_files:
        file_paths.append(save_file(uploaded_file))
    if uploaded_files:
        docs = []
        for file_path in file_paths:
            if file_path.endswith(".pdf"):
                docs.extend(rag_util.load_and_split_pdfs([file_path]))
            elif file_path.endswith(".csv"):
                docs.extend(rag_util.load_and_split_csv(file_path))
            elif file_path.endswith(".json"):
                docs.extend(rag_util.load_and_split_json(file_path))
        DB = rag_util.FaissDb(docs=docs, embedding_function=encoder.embedding_function)

# 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("Ask me anything!"):
    # Add user message to chat history
    st.session_state.messages.append({"role": "user", "content": prompt})
    # Display user message in chat message container
    with st.chat_message("user"):
        st.markdown(prompt)

    # Display assistant response in chat message container
    with st.chat_message("assistant"):
        user_prompt = st.session_state.messages[-1]["content"]
        context = (
            None if not uploaded_files else DB.similarity_search(user_prompt, k=k)
        )
        answer = model.generate(
            user_prompt, context=context, max_new_tokens=max_new_tokens
        )

        response = st.write(answer)
    st.session_state.messages.append({"role": "assistant", "content": answer})