Create app.py

app.py

@@ -0,0 +1,77 @@
+import streamlit as st
+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
+
+summarizer, critic = load_models()
+
+# 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"
+    return text
+
+# Sectioning Logic
+def split_into_sections(text):
+    sections = {}
+    headings = ["abstract", "introduction", "methodology", "methods", "results", "discussion", "conclusion", "references"]
+    current_section = "others"
+    sections[current_section] = ""
+
+    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"
+    
+    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']
+
+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']
+
+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']
+
+# Streamlit UI
+st.set_page_config(page_title="CritiqueGen", layout="wide")
+st.title("📄 Research Paper Critique Generator")
+
+uploaded_file = st.file_uploader("Upload a research paper (PDF)", type="pdf")
+
+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)
+
+        st.header("📋 Summary")
+        summary = summarize_section(full_text[:3000])
+        st.write(summary)
+
+        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]))
+
+    st.success("Analysis complete ✅")