Create app.py

app.py

@@ -0,0 +1,75 @@
+# app.py
+import streamlit as st
+from extractive import preprocess_text, get_sentence_embeddings, build_semantic_graph, apply_textrank, generate_summary
+from abstractive import abstractive_summary
+from utils import extract_named_entities
+from transformers import AutoTokenizer, AutoModel
+
+# Load pre-trained BERT model and tokenizer
+model_name = "dmis-lab/biobert-base-cased-v1.2"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModel.from_pretrained(model_name)
+
+# Streamlit app layout
+st.title("Hybrid Summarization App")
+st.write("Upload text files for multi-document summarization or enter text manually for single-document summarization.")
+
+# Multi-document summarization
+st.header("Multi-Document Summarization")
+uploaded_files = st.file_uploader("Upload text files", type="txt", accept_multiple_files=True)
+
+if uploaded_files:
+    texts = [file.read().decode("utf-8") for file in uploaded_files]
+    
+    # Perform extractive summarization for each document
+    extractive_summaries = []
+    for text in texts:
+        sentences = preprocess_text(text)
+        embeddings = get_sentence_embeddings(sentences, model, tokenizer)
+        graph = build_semantic_graph(embeddings)
+        ranked_sentences = apply_textrank(graph, sentences)
+        ext_summary = generate_summary(ranked_sentences, sentences, max_length_ratio=0.5)
+        extractive_summaries.append(ext_summary)
+    
+    # Combine extractive summaries for multi-document summarization
+    combined_extractive_summary = " ".join(extractive_summaries)
+    st.write("Combined Extractive Summary:", combined_extractive_summary)
+    
+    # Extract named entities from the combined summary
+    entities = extract_named_entities(combined_extractive_summary)
+    st.write("Named Entities:", entities)
+    
+    # Choose summary length ratio for abstractive summarization
+    abs_ratio_option = st.selectbox("Choose abstractive summary length ratio", ("1/2", "1/3", "1/4"))
+    abs_ratio = {"1/2": 0.5, "1/3": 0.33, "1/4": 0.25}[abs_ratio_option]
+
+    # Perform abstractive summarization
+    combined_input = combined_extractive_summary + " " + ' '.join([ent[0] for ent in entities])
+    abs_summary = abstractive_summary(combined_input, max_length_ratio=abs_ratio, min_length_ratio=abs_ratio/2)
+    st.write("Abstractive Summary:", abs_summary)
+
+# Single-document summarization
+st.header("Single-Document Summarization")
+text_input = st.text_area("Enter text here")
+
+if text_input:
+    # Extract named entities
+    entities = extract_named_entities(text_input)
+    st.write("Named Entities:", entities)
+
+    # Perform extractive summarization
+    sentences = preprocess_text(text_input)
+    embeddings = get_sentence_embeddings(sentences, model, tokenizer)
+    graph = build_semantic_graph(embeddings)
+    ranked_sentences = apply_textrank(graph, sentences)
+    ext_summary = generate_summary(ranked_sentences, sentences, max_length_ratio=0.5)
+    st.write("Extractive Summary:", ext_summary)
+
+    # Choose summary length ratio for abstractive summarization
+    abs_ratio_option = st.selectbox("Choose abstractive summary length ratio", ("1/2", "1/3", "1/4"))
+    abs_ratio = {"1/2": 0.5, "1/3": 0.33, "1/4": 0.25}[abs_ratio_option]
+
+    # Perform abstractive summarization
+    combined_input = ext_summary + " " + ' '.join([ent[0] for ent in entities])
+    abs_summary = abstractive_summary(combined_input, max_length_ratio=abs_ratio, min_length_ratio=abs_ratio/2)
+    st.write("Abstractive Summary:", abs_summary)