import streamlit as st from streamlit_lottie import st_lottie import fitz # PyMuPDF import requests import os, shutil import sidebar import llm_model @st.cache_data(experimental_allow_widgets=True) def index_document(uploaded_file): if uploaded_file is not None: # Specify the folder path where you want to store the uploaded file in the 'assets' folder assets_folder = "assets/uploaded_files" if not os.path.exists(assets_folder): os.makedirs(assets_folder) # Save the uploaded file to the specified folder file_path = os.path.join(assets_folder, uploaded_file.name) with open(file_path, "wb") as f: f.write(uploaded_file.getvalue()) file_name = os.path.join(assets_folder, uploaded_file.name) st.success(f"File '{file_name}' uploaded !") with st.spinner("Indexing document... This is a free CPU version and may take a while⏳"): llm_model.create_vector_db(file_name, instructor_embeddings) return file_name else: return None def load_lottieurl(url: str): r = requests.get(url) if r.status_code != 200: return None return r.json() def is_query_valid(query: str) -> bool: if not query: st.error("Please enter a question!") return False return True # Function to load model parameters @st.cache_resource() def load_model(): return llm_model.load_model_params() st.set_page_config(page_title="Document QA Bot") lottie_book = load_lottieurl("https://assets4.lottiefiles.com/temp/lf20_aKAfIn.json") st_lottie(lottie_book, speed=1, height=200, key="initial") # Place the title below the Lottie animation st.title("Document Q&A Bot 🤖") # Left Sidebar sidebar.sidebar() # st.sidebar.header("Upload PDF") # load model parameters llm, instructor_embeddings = load_model() # Upload file through Streamlit uploaded_file = st.file_uploader("Upload a file", type=["pdf", "doc", "docx", "txt"]) filename = index_document(uploaded_file) print(filename) if not filename: st.stop() with st.form(key="qa_form"): query = st.text_area("Ask a question about the document") submit = st.form_submit_button("Submit") if submit: if not is_query_valid(query): st.stop() # Output Columns answer_col, sources_col = st.columns(2) qa_chain = llm_model.document_parser(instructor_embeddings, llm) result = qa_chain(query) with answer_col: st.markdown("#### Answer") st.markdown(result["result"]) with sources_col: st.markdown("#### Sources") if not ("i don't know" in result["result"].lower()): for source in result["source_documents"]: st.markdown(source.page_content) st.markdown(source.metadata["source"]) st.markdown("--------------------------")