Spaces:
Build error
Build error
| import streamlit as st | |
| from utils import * | |
| # streamlit session state holds history, this mehtods cleas that history. Note: as our applications become more complicated session state will be used more. | |
| def clear_history(): | |
| if 'history' in st.session_state: | |
| del st.session_state['history'] | |
| # use main function to designate as primary package | |
| if __name__ == "__main__": | |
| import os | |
| # create your side bar | |
| st.subheader('Load a Document and Ask a Question') | |
| with st.sidebar: | |
| # use text_input to bring in your OpenAI API key | |
| api_key = st.text_input('OpenAI API Key:', type='password') | |
| if api_key: | |
| os.environ['OPENAI_API_KEY'] = api_key | |
| # sidebar - file uploader widget, drag and drop, browse button works on windows not on mac | |
| uploaded_file = st.file_uploader('To upload a file drag and drop it on the area below:', type=['pdf', 'docx', 'txt', 'csv']) | |
| # call the chunk size mehtod that sets the number | |
| chunk_size = st.number_input('Chunk size:', min_value=100, max_value=2048, value=512, on_change=clear_history) | |
| # chunk Overlab | |
| chunk_overlap = st.number_input('Chunk Overlap:', min_value=0, max_value=200, value=20, on_change=clear_history) | |
| # input the top-k number, k increase the search effectiveness, but is more expensive | |
| k = st.number_input('top-k most salient docs', min_value=1, max_value=20, value=3, on_change=clear_history) | |
| # click this sidebard button to add data | |
| add_data = st.button('Add Data', on_click=clear_history) | |
| #chekc if data button has been clicked,if the api key is added and if a data file is available for upload | |
| 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, chunk_overlap=chunk_overlap) | |
| 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.....") | |
| # this is the main input widget that allows you to input your query of the uploaded document | |
| q = st.text_input('Ask a question about the content of your file:') | |
| if q: # run the query if the user entered a question and hit enter | |
| if 'vs' in st.session_state: # for seesion 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() | |
| # initialize a chat history if there's no chat history | |
| if 'history' not in st.session_state: | |
| st.session_state.history = '' | |
| # your 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 | |
| # chat history text area widget | |
| st.text_area(label='Chat History', value=h, key='history', height=400) | |