app.py

app.py

@@ -0,0 +1,60 @@
+import streamlit as st
+import tensorflow as tf
+from tensorflow import keras
+import keras_nlp
+import PyPDF2
+import docx2txt
+
+# Load your Keras model
+@st.cache_resource 
+def load_model_and_preprocessor():
+    bart_billsum = keras_nlp.models.BartSeq2SeqLM.from_preset('Grey01/bart_billsum')
+    
+    # Load the default BART preprocessor (assuming you saved its configuration)
+    preprocessor = keras_nlp.models.BartSeq2SeqLMPreprocessor.from_preset('bart_base_en', encoder_sequence_length=512,
+    decoder_sequence_length=128,)
+    
+    return model, preprocessor
+
+model, preprocessor = load_model_and_preprocessor()
+
+st.title("SummarizeIt")
+
+# File uploader
+uploaded_file = st.file_uploader("Choose a file", type=["pdf", "txt", "docx"])
+
+# Text extraction
+text = ""
+if uploaded_file is not None:
+    if uploaded_file.type == "application/pdf":
+        pdf_reader = PyPDF2.PdfReader(uploaded_file)
+        for page in pdf_reader.pages:
+            text += page.extract_text()
+    elif uploaded_file.type == "text/plain":
+        text = uploaded_file.read().decode("utf-8")
+    elif uploaded_file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
+        text = docx2txt.process(uploaded_file)
+# Text input for direct text entry
+user_input = st.text_area("Or paste your text here:")
+text = user_input if user_input else text  # Prioritize user input over file
+
+def generate_text(model, input_texts, max_length=200, print_time_taken=False):
+    # Convert input_texts to a list if it's a Dataset
+    if isinstance(input_texts, datasets.Dataset):
+        input_texts = input_texts.to_list()
+    chunks = [input_texts[i:i+512] for i in range(0, len(input_texts), 512)]
+    #initialize an empty list to store summaries
+    summaries = []
+    # generate summaries for each chunk
+    for chunk in chunks:
+        # Assuming your model's generate method can handle a batch of inputs
+        summary = model.generate(input_texts, max_length=max_length)
+        summaries.append(summary)
+    return summary
+
+generated_summaries = generate_text(
+    model,
+    text,  # Pass the list of documents directly
+)
+st.subheader("Generated Summary:")
+st.write(summary)