app.py

app.py

@@ -0,0 +1,101 @@
+import streamlit as st
+from transformers import pipeline
+import pdfplumber
+from langchain.llms import HuggingFacePipeline
+from langchain.prompts import PromptTemplate
+
+# Function to extract text from a PDF
+def extract_text_from_pdf(pdf_file):
+    with pdfplumber.open(pdf_file) as pdf:
+        text = ''
+        for page in pdf.pages:
+            text += page.extract_text()
+    return text
+
+# Define the prompt template
+template = """
+You are a medical summarization expert. Focus on the following key aspects when summarizing:
+
+1. Patient History
+2. Diagnosis
+3. Treatment Recommendations
+4. Follow-up Plans
+
+Here’s the medical report to summarize:
+
+{text}
+"""
+
+prompt = PromptTemplate(
+    input_variables=["text"],
+    template=template
+)
+
+# Streamlit application layout
+st.title("Medical Report Summarizer")
+
+# Option to upload PDF or enter text
+option = st.selectbox("Choose Input Method", ["Upload PDF", "Enter Text"])
+
+if option == "Upload PDF":
+    uploaded_file = st.file_uploader("Upload your PDF file", type=["pdf"])
+    if uploaded_file is not None:
+        # Extract text from the uploaded PDF
+        extracted_text = extract_text_from_pdf(uploaded_file)
+        
+        # Dynamic calculation for max_length based on extracted text length
+        length = max(2, int(len(extracted_text) // 2))
+        
+        # Load the summarization pipeline with updated max_length
+        summarizer = pipeline(
+            "summarization",
+            model="fine_tuned_model",  # Ensure the path to your fine-tuned model is correct
+            temperature=0.3,
+            min_length=100,
+            max_length=int(length),
+            # top_k=80,  # Uncomment if you want to use top_k
+            # top_p=0.95  # Uncomment if you want to use top_p
+        )
+
+        llm = HuggingFacePipeline(pipeline=summarizer)
+        
+        # Create the formatted prompt
+        formatted_prompt = prompt.format(text=extracted_text)
+        
+        # Generate the summary
+        summary = llm(formatted_prompt)
+        
+        st.subheader("Summary:")
+        st.write(summary)
+
+elif option == "Enter Text":
+    input_text = st.text_area("Enter the text to summarize", height=300)
+    
+    if st.button("Summarize"):
+        if input_text:
+            # Dynamic calculation for max_length based on entered text length
+            length = max(2, int(len(input_text) // 2))
+            
+            # Load the summarization pipeline with updated max_length
+            summarizer = pipeline(
+                "summarization",
+                model="fine_tuned_model",
+                temperature=0.3,
+                min_length=100,
+                max_length=int(length),
+                top_k=80,  
+                top_p=0.95 
+            )
+
+            llm = HuggingFacePipeline(pipeline=summarizer)
+            
+            # Create the formatted prompt
+            formatted_prompt = prompt.format(text=input_text)
+            
+            # Generate the summary
+            summary = llm(formatted_prompt)
+            
+            st.subheader("Summary:")
+            st.write(summary)
+        else:
+            st.warning("Please enter some text to summarize.")