Update app.py

app.py

@@ -1,77 +1,85 @@
-import streamlit as st
+import gradio as gr
 import pdfplumber
-import re
 from transformers import pipeline
 
-# Initialize LLMs
-@st.cache_resource
-def load_models():
-    summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
-    critic = pipeline("text2text-generation", model="google/flan-t5-large")
-    return summarizer, critic
+# Load models
+summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
+critic = pipeline("text2text-generation", model="google/flan-t5-large")
 
-summarizer, critic = load_models()
-
-# PDF Text Extraction
+# PDF text extraction
 def extract_text_from_pdf(pdf_file):
     text = ""
     with pdfplumber.open(pdf_file) as pdf:
         for page in pdf.pages:
-            page_text = page.extract_text()
-            if page_text:
-                text += page_text + "\n"
+            content = page.extract_text()
+            if content:
+                text += content + "\n"
     return text
 
-# Sectioning Logic
+# Split text into sections
 def split_into_sections(text):
     sections = {}
     headings = ["abstract", "introduction", "methodology", "methods", "results", "discussion", "conclusion", "references"]
-    current_section = "others"
-    sections[current_section] = ""
-
+    current = "others"
+    sections[current] = ""
     for line in text.splitlines():
-        line_lower = line.lower().strip()
-        if any(h in line_lower for h in headings):
-            current_section = next((h for h in headings if h in line_lower), "others")
-            sections[current_section] = ""
-        sections[current_section] += line + "\n"
-    
+        if any(h in line.lower() for h in headings):
+            current = next((h for h in headings if h in line.lower()), "others")
+            sections[current] = ""
+        sections[current] += line + "\n"
     return sections
 
-# NLP Functions
-def summarize_section(text, max_len=300):
-    return summarizer(text, max_length=max_len, min_length=100, do_sample=False)[0]['summary_text']
+# LLM-based functions
+def summarize(text): return summarizer(text[:3000])[0]['summary_text']
+def critique(text): return critic(f"Critique this section:\n{text}", max_length=512)[0]['generated_text']
+def find_gaps(text): return critic(f"What research gaps are present?\n{text}", max_length=512)[0]['generated_text']
+def custom_query(text): return critic(text, max_length=512)[0]['generated_text']
+
+# Main handler
+def analyze(file, pasted_text, custom_prompt):
+    if file is not None:
+        text = extract_text_from_pdf(file.name)
+    elif pasted_text.strip():
+        text = pasted_text
+    else:
+        return "Please upload a file or enter some text.", "", "", ""
 
-def critique_section(text):
-    prompt = f"Critically evaluate this section:\n{text}\nList strengths, weaknesses, and improvements."
-    return critic(prompt, max_length=512, do_sample=False)[0]['generated_text']
+    # Generate outputs
+    summary = summarize(text)
+    sections = split_into_sections(text)
 
-def identify_research_gaps(text):
-    prompt = f"Identify research gaps or unanswered questions in the following study:\n{text}"
-    return critic(prompt, max_length=512, do_sample=False)[0]['generated_text']
+    critique_output = ""
+    gap_output = ""
 
-# Streamlit UI
-st.set_page_config(page_title="CritiqueGen", layout="wide")
-st.title("📄 Research Paper Critique Generator")
+    for sec, content in sections.items():
+        snippet = content[:1000]
+        critique_output += f"### {sec.capitalize()}\n**Critique:**\n{critique(snippet)}\n\n"
+        gap_output += f"### {sec.capitalize()}\n**Research Gaps:**\n{find_gaps(snippet)}\n\n"
 
-uploaded_file = st.file_uploader("Upload a research paper (PDF)", type="pdf")
+    custom_response = ""
+    if custom_prompt.strip():
+        custom_response = custom_query(custom_prompt)
 
-if uploaded_file:
-    with st.spinner("Reading and analyzing the paper..."):
-        full_text = extract_text_from_pdf(uploaded_file)
-        sections = split_into_sections(full_text)
+    return summary, critique_output, gap_output, custom_response
 
-        st.header("📋 Summary")
-        summary = summarize_section(full_text[:3000])
-        st.write(summary)
+# Gradio UI
+demo = gr.Interface(
+    fn=analyze,
+    inputs=[
+        gr.File(label="Upload PDF", file_types=[".pdf"]),
+        gr.Textbox(lines=8, placeholder="Or paste your research text here...", label="Pasted Text"),
+        gr.Textbox(lines=2, placeholder="Optional: Ask a custom question", label="Custom Prompt")
+    ],
+    outputs=[
+        gr.Markdown(label="📋 Summary"),
+        gr.Markdown(label="🧠 Critique by Section"),
+        gr.Markdown(label="🔎 Research Gaps"),
+        gr.Markdown(label="💬 Custom Prompt Response")
+    ],
+    title="📄 Research Paper Critique Generator",
+    description="Upload a research paper (PDF) or paste its content. Get section-wise critiques, summaries, and gap analysis using LLMs.",
+    theme="default"
+)
 
-        st.header("🔍 Section-wise Critique and Suggestions")
-        for sec, content in sections.items():
-            if content.strip():
-                with st.expander(f"📘 {sec.capitalize()}"):
-                    st.subheader("Critique")
-                    st.write(critique_section(content[:1000]))  # Limit input size
-                    st.subheader("Research Gaps")
-                    st.write(identify_research_gaps(content[:1000]))
+demo.launch()
 
-    st.success("Analysis complete ✅")