Update app.py

app.py

@@ -1,35 +1,16 @@
-# app.py (Combined FastAPI + Streamlit UI)
+# app.py (Streamlit-only version for Hugging Face Spaces)
 
 import os
-import uuid
 import tempfile
 from typing import List
 
 import fitz  # PyMuPDF
 import requests
-import openai
 from transformers import pipeline
 from gtts import gTTS
-import shutil
-
 import streamlit as st
-from fastapi import FastAPI, UploadFile, File, Form
-from fastapi.responses import FileResponse
-from fastapi.middleware.wsgi import WSGIMiddleware
-from starlette.responses import Response
-from starlette.routing import Mount
-from starlette.applications import Starlette
-from starlette.middleware.cors import CORSMiddleware
-from starlette.staticfiles import StaticFiles
-from pydantic import BaseModel
-from fastapi.middleware.cors import CORSMiddleware
-from fastapi.staticfiles import StaticFiles
-from fastapi.middleware.wsgi import WSGIMiddleware
-import uvicorn
 
 # ---------- CONFIG ----------
-openai.api_key = os.getenv("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")
-
 def summarize_text(text: str) -> str:
     summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
     return summarizer(text, max_length=200, min_length=30, do_sample=False)[0]['summary_text']
@@ -50,70 +31,42 @@ def generate_audio(text: str, output_path: str):
     tts = gTTS(text)
     tts.save(output_path)
 
-# ---------- FASTAPI BACKEND ----------
-fastapi_app = FastAPI()
-
-@fastapi_app.post("/upload")
-def upload_paper(file: UploadFile = File(...), topics: str = Form(...)):
-    temp_dir = tempfile.mkdtemp()
-    file_path = os.path.join(temp_dir, file.filename)
-    with open(file_path, "wb") as f:
-        f.write(file.file.read())
-
-    text = extract_text_from_pdf(file_path)
-    topic_list = [t.strip() for t in topics.split(",")]
-    classified_topic = classify_topic(text, topic_list)
-    summary = summarize_text(text)
-
-    audio_path = os.path.join(temp_dir, "summary.mp3")
-    generate_audio(summary, audio_path)
-
-    return FileResponse(audio_path, media_type="audio/mpeg", filename="summary.mp3")
-
 # ---------- STREAMLIT UI ----------
-def streamlit_ui():
-    st.set_page_config(page_title="Research Paper Summarizer", layout="centered")
-    st.title("📄 AI Research Paper Summarizer")
-
-    st.markdown("""
-    Upload a research paper (PDF) and a list of topics. The app will:
-    1. Extract and summarize the paper
-    2. Classify it into a topic
-    3. Generate an audio summary 🎧
-    """)
-
-    with st.form("upload_form"):
-        uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
-        topic_input = st.text_input("Enter comma-separated topics")
-        submitted = st.form_submit_button("Summarize and Generate Audio")
-
-    if submitted and uploaded_file and topic_input:
-        with st.spinner("Processing paper..."):
-            files = {"file": (uploaded_file.name, uploaded_file, "application/pdf")}
-            data = {"topics": topic_input}
-
-            response = requests.post("http://localhost:8000/upload", files=files, data=data)
-
-            if response.status_code == 200:
-                audio_path = "summary.mp3"
-                with open(audio_path, "wb") as f:
-                    f.write(response.content)
-                st.audio(audio_path)
-                st.success("Audio summary generated!")
-            else:
-                st.error("Something went wrong during processing.")
-
-# ---------- ENTRY POINT ----------
-if __name__ == "__main__":
-    import threading
-    from multiprocessing import Process
-
-    def run_api():
-        uvicorn.run(fastapi_app, host="0.0.0.0", port=8000)
-
-    api_process = Process(target=run_api)
-    api_process.start()
-
-    streamlit_ui()
-
-    api_process.terminate()
+st.set_page_config(page_title="Research Paper Summarizer", layout="centered")
+st.title("📄 AI Research Paper Summarizer")
+
+st.markdown("""
+Upload a research paper (PDF) and a list of topics. The app will:
+1. Extract and summarize the paper
+2. Classify it into a topic
+3. Generate an audio summary 🎧
+""")
+
+with st.form("upload_form"):
+    uploaded_file = st.file_uploader("Upload a PDF file", type=["pdf"])
+    topic_input = st.text_input("Enter comma-separated topics")
+    submitted = st.form_submit_button("Summarize and Generate Audio")
+
+if submitted and uploaded_file and topic_input:
+    with st.spinner("Processing paper..."):
+        temp_dir = tempfile.mkdtemp()
+        file_path = os.path.join(temp_dir, uploaded_file.name)
+
+        with open(file_path, "wb") as f:
+            f.write(uploaded_file.read())
+
+        text = extract_text_from_pdf(file_path)
+        topic_list = [t.strip() for t in topic_input.split(",") if t.strip()]
+        classified_topic = classify_topic(text, topic_list)
+        summary = summarize_text(text)
+
+        st.markdown(f"### 🧠 Classified Topic: `{classified_topic}`")
+        st.markdown("### ✍️ Summary:")
+        st.write(summary)
+
+        audio_path = os.path.join(temp_dir, "summary.mp3")
+        generate_audio(summary, audio_path)
+
+        st.markdown("### 🔊 Audio Summary")
+        st.audio(audio_path)
+        st.success("Done! Audio summary is ready.")