| import gradio as gr |
| import pdfplumber |
| import re |
| from transformers import pipeline |
|
|
| |
| summarizer = pipeline("summarization", model="facebook/bart-large-cnn") |
| critic = pipeline("text2text-generation", model="google/flan-t5-large") |
|
|
| |
| def extract_text(file): |
| with pdfplumber.open(file) as pdf: |
| return "\n".join([page.extract_text() or "" for page in pdf.pages]) |
|
|
| |
| def extract_sections(text): |
| pattern = r'\n(?P<header>[A-Z][A-Za-z ]{3,40})\n' |
| matches = list(re.finditer(pattern, text)) |
| sections = {} |
| for i, match in enumerate(matches): |
| start = match.end() |
| end = matches[i + 1].start() if i + 1 < len(matches) else len(text) |
| sections[match.group("header").strip().lower()] = text[start:end].strip() |
| return sections or {"full text": text} |
|
|
| |
| def truncate(text, max_tokens=1000): |
| return text[:max_tokens * 5] |
|
|
| |
| def analyze(file, pasted_text, custom_prompt): |
| raw_text = extract_text(file.name) if file else pasted_text.strip() |
| if not raw_text: |
| return "No text provided.", "", "", "" |
|
|
| summary = summarizer(truncate(raw_text), max_length=250, min_length=100, do_sample=False)[0]['summary_text'] |
| sections = extract_sections(raw_text) |
|
|
| critique_output = "" |
| gap_output = "" |
|
|
| for sec, content in sections.items(): |
| snippet = truncate(content) |
| critique_out = critic(f"Critique this section:\n{snippet}", max_length=256)[0]['generated_text'] |
| gaps_out = critic(f"Identify research gaps in this section:\n{snippet}", max_length=256)[0]['generated_text'] |
| critique_output += f"### {sec.title()}\n{critique_out}\n\n" |
| gap_output += f"### {sec.title()}\n{gaps_out}\n\n" |
|
|
| custom_out = "" |
| if custom_prompt.strip(): |
| custom_out = critic(custom_prompt.strip(), max_length=256)[0]['generated_text'] |
|
|
| return summary, critique_output.strip(), gap_output.strip(), custom_out |
|
|
| |
| demo = gr.Interface( |
| fn=analyze, |
| inputs=[ |
| gr.File(label="📄 Upload PDF", file_types=[".pdf"]), |
| gr.Textbox(lines=10, label="✍️ Or paste paper content"), |
| gr.Textbox(lines=2, label="💬 Optional: Custom prompt") |
| ], |
| outputs=[ |
| gr.Markdown(label="📋 Summary"), |
| gr.Markdown(label="🧠 Critique"), |
| gr.Markdown(label="🔎 Research Gaps"), |
| gr.Markdown(label="💡 Custom Prompt Response") |
| ], |
| title="Research Paper Critique Generator", |
| description="Upload a PDF or paste text to receive an AI-generated summary, critique, and identification of research gaps.", |
| theme="default" |
| ) |
|
|
| if __name__ == "__main__": |
| demo.launch() |
|
|
|
|
