File size: 3,912 Bytes
acc9eef 00665aa acc9eef 4d80aaf acc9eef |
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 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 |
import streamlit as st
from utils import *
# clear the chat history from streamlit session state
def clear_history():
if 'history' in st.session_state:
del st.session_state['history']
if __name__ == "__main__":
import os
# loading the OpenAI api key from .env
from dotenv import load_dotenv, find_dotenv
load_dotenv(find_dotenv(), override=True)
# st.image('img.png')
st.subheader('Load a Document and Ask a Question')
with st.sidebar:
# text_input for the OpenAI API key (alternative to python-dotenv and .env)
api_key = st.text_input('OpenAI API Key:', type='password')
if api_key:
os.environ['OPENAI_API_KEY'] = api_key
# file uploader widget
uploaded_file = st.file_uploader('To upload a file drag and drop it on the area below:', type=['pdf', 'docx', 'txt'])
# chunk size number widget
chunk_size = st.number_input('Chunk size:', min_value=100, max_value=2048, value=512, on_change=clear_history)
# k number input widget
k = st.number_input('k', min_value=1, max_value=20, value=3, on_change=clear_history)
# add data button widget
add_data = st.button('Add Data', on_click=clear_history)
if add_data:
if api_key:
if uploaded_file and add_data: # if the user browsed a file
with st.spinner('Reading, chunking and embedding file ...'):
# writing the file from RAM to the current directory on disk
bytes_data = uploaded_file.read()
file_name = os.path.join('./', uploaded_file.name)
with open(file_name, 'wb') as f:
f.write(bytes_data)
data = load_document(file_name)
chunks = chunk_data(data, chunk_size=chunk_size)
st.write(f'Chunk size: {chunk_size}, Chunks: {len(chunks)}')
tokens, embedding_cost = calculate_embedding_cost(chunks)
st.write(f'Embedding cost: ${embedding_cost:.4f}')
# creating the embeddings and returning the Chroma vector store
vector_store = create_embeddings(chunks)
# saving the vector store in the streamlit session state (to be persistent between reruns)
st.session_state.vs = vector_store
st.success('File uploaded, chunked and embedded successfully.')
else:
st.error("Please drag and drop your file to the upload area above.....")
else:
st.error("Please provide your OpenAI API key above.....")
# user's question text input widget
q = st.text_input('Ask a question about the content of your file:')
if q: # if the user entered a question and hit enter
if 'vs' in st.session_state: # if there's the vector store (user uploaded, split and embedded a file)
vector_store = st.session_state.vs
st.write(f'k: {k}')
answer = ask_and_get_answer(vector_store, q, k)
# text area widget for the LLM answer
st.text_area('LLM Answer: ', value=answer)
st.divider()
# if there's no chat history in the session state, create it
if 'history' not in st.session_state:
st.session_state.history = ''
# the current question and answer
value = f'Q: {q} \nA: {answer}'
st.session_state.history = f'{value} \n {"-" * 100} \n {st.session_state.history}'
h = st.session_state.history
# text area widget for the chat history
st.text_area(label='Chat History', value=h, key='history', height=400)
# run the app: streamlit run ./chat_with_documents.py
|