|
import streamlit as st |
|
from functions import * |
|
|
|
st.set_page_config(page_title="Earnings Question/Answering", page_icon="🔎") |
|
st.sidebar.header("Semantic Search") |
|
st.markdown("## Earnings Semantic Search with LangChain, OpenAI & SBert") |
|
|
|
def gen_sentiment(text): |
|
'''Generate sentiment of given text''' |
|
return sent_pipe(text)[0]['label'] |
|
|
|
def gen_annotated_text(df): |
|
'''Generate annotated text''' |
|
|
|
tag_list=[] |
|
for row in df.itertuples(): |
|
label = row[2] |
|
text = row[1] |
|
if label == 'Positive': |
|
tag_list.append((text,label,'#8fce00')) |
|
elif label == 'Negative': |
|
tag_list.append((text,label,'#f44336')) |
|
else: |
|
tag_list.append((text,label,'#000000')) |
|
|
|
return tag_list |
|
|
|
bi_enc_dict = {'mpnet-base-v2':"all-mpnet-base-v2", |
|
'instructor-base': 'hkunlp/instructor-base', |
|
'setfit-finance': 'nickmuchi/setfit-finetuned-financial-text-classification'} |
|
|
|
search_input = st.text_input( |
|
label='Enter Your Search Query',value= "What key challenges did the business face?", key='search') |
|
|
|
sbert_model_name = st.sidebar.selectbox("Embedding Model", options=list(bi_enc_dict.keys()), key='sbox') |
|
|
|
chunk_size = st.sidebar.slider("Number of Chars per Chunk of Text",min_value=500,max_value=2000,value=1000) |
|
overlap_size = st.sidebar.slider("Number of Overlap Chars in Search Response",min_value=50,max_value=300,value=50) |
|
|
|
try: |
|
|
|
if search_input: |
|
|
|
if "sen_df" in st.session_state and "earnings_passages" in st.session_state: |
|
|
|
|
|
sen_df = st.session_state['sen_df'] |
|
|
|
title = st.session_state['title'] |
|
|
|
embedding_model = bi_enc_dict[sbert_model_name] |
|
|
|
with st.spinner( |
|
text=f"Loading {embedding_model} embedding model and Generating Response..." |
|
): |
|
|
|
docsearch = process_corpus(st.session_state['earnings_passages'],title, embedding_model) |
|
|
|
result = embed_text(search_input,title,embedding_model,docsearch) |
|
|
|
|
|
references = [doc.page_content for doc in result['input_documents']] |
|
|
|
answer = result['output_text'] |
|
|
|
sentiment_label = gen_sentiment(answer) |
|
|
|
|
|
|
|
df = pd.DataFrame.from_dict({'Text':[answer],'Sentiment':[sentiment_label]}) |
|
|
|
|
|
text_annotations = gen_annotated_text(df)[0] |
|
|
|
with st.expander(label='Query Result', expanded=True): |
|
annotated_text(text_annotations) |
|
|
|
with st.expander(label='References from Corpus used to Generate Result'): |
|
for ref in references: |
|
st.write(ref) |
|
|
|
else: |
|
|
|
st.write('Please ensure you have entered the YouTube URL or uploaded the Earnings Call file') |
|
|
|
else: |
|
|
|
st.write('Please ensure you have entered the YouTube URL or uploaded the Earnings Call file') |
|
|
|
except RuntimeError: |
|
|
|
st.write('Please ensure you have entered the YouTube URL or uploaded the Earnings Call file') |
|
|
|
|
|
|
