Create app.py

web app for report summerization

app.py

@@ -0,0 +1,61 @@
+import streamlit as st
+import torch
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForSeq2SeqLM,AutoTokenizer,AutoTokenizer
+
+
+# Process text fun
+def process_text(text):
+    # Remove extra white space from the text
+    text = " ".join(text.split())
+
+    # Remove special characters
+    text = re.sub(r"[^a-zA-Z0-9.]+", " ", text)
+    
+    # Remove multiple full stops
+    text = re.sub(r"\.{2,}", ".", text)
+    
+    return text
+
+# Load model
+def load_model():
+    config = PeftConfig.from_pretrained("sami606713/medical_report_summarizer")
+    base_model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn")
+    model = PeftModel.from_pretrained(base_model, "sami606713/medical_report_summarizer")
+    return model
+
+# Load tokenizer
+def load_tokenizer():
+    tokenizer=AutoTokenizer.from_pretrained("sami606713/medical_report_summarizer")
+    return tokenizer
+
+# Summerize text
+def summerize_text(text):
+    # process the text
+    text=process_text(text)
+    # tokenize the text
+    tokenizer=load_tokenizer()
+    inputs = tokenizer(test_report, max_length=1000, truncation=True, padding='max_length', return_tensors='pt')
+
+    # Generate the output idx
+    model=load_model()
+    summary_ids = model.generate(**inputs, max_length=300)
+    predicted_summary = tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+    return predicted_summary
+
+# set the page layout
+st.set_page_config(page_title="Medical Report Summerization", 
+                   page_icon="🩺", layout="wide")
+
+# Set the title of the app
+st.title('Medical Report Summerization')
+
+# Add a pdf file uploader
+# uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
+# if uploaded_file is not None:
+#     st.write(uploaded_file)
+
+text=st.text_area("Enter report here:\n",height=250)
+if st.button("Summarize"):
+    result=summerize_text(text)
+    st.write(f"*{result}*")