keybert / app.py
varun500's picture
Update app.py
a9605ff
raw
history blame
2.17 kB
import streamlit as st
from keybert import KeyBERT
# Create a KeyBERT instance
kw_model = KeyBERT()
# Define the Streamlit app
def main():
st.title("Keyword Extraction")
st.write("Enter your document below:")
# Get user input
doc = st.text_area("Document")
# Get user choice for stopwords removal (default checkbox)
remove_stopwords = st.checkbox("Remove Stopwords", value=True)
# Get user choice for MMR (default checkbox)
apply_mmr = st.checkbox("Apply Maximal Marginal Relevance (MMR)", value=True)
# Get user choice for number of results (slider)
num_results = st.slider("Number of Results", min_value=1, max_value=30, value=5, step=1)
# Get user choice for minimum n-gram value (default textbox)
min_ngram = st.number_input("Minimum N-gram", value=1, min_value=1, max_value=10, step=1)
# Get user choice for maximum n-gram value (default textbox)
max_ngram = st.number_input("Maximum N-gram", value=3, min_value=1, max_value=10, step=1)
# Get user choice for keyword diversity (MMR only)
diversity = st.slider("Keyword Diversity (MMR)", min_value=0.0, max_value=1.0, value=0.2, step=0.1, format="%.1f")
# Extract keywords
if st.button("Extract Keywords"):
if apply_mmr:
keywords = kw_model.extract_keywords(doc,
keyphrase_ngram_range=(min_ngram, max_ngram),
stop_words='english' if remove_stopwords else None,
use_mmr=True,
diversity=diversity)
else:
keywords = kw_model.extract_keywords(doc,
keyphrase_ngram_range=(min_ngram, max_ngram),
stop_words='english' if remove_stopwords else None)
selected_keywords = keywords[:num_results]
st.write(f"Top {num_results} Keywords:")
for keyword, score in selected_keywords:
st.write(f"- {keyword} (Score: {score})")
# Run the app
if __name__ == "__main__":
main()