Update app/main.py

app/main.py

@@ -4,12 +4,9 @@ from fastapi.responses import JSONResponse
 from transformers import pipeline
 from newspaper import Article
 import pdfplumber
-import io
 import requests
 from bs4 import BeautifulSoup
 
-
-
 app = FastAPI()
 
 app.add_middleware(
@@ -22,6 +19,7 @@ app.add_middleware(
 # Load summarizer from local model dir
 summarizer = pipeline("summarization", model="/app/model/t5-base")
 
+# PDF Text Extractor
 def extract_text_from_pdf(file):
     text = ""
     with pdfplumber.open(file) as pdf:
@@ -31,20 +29,15 @@ def extract_text_from_pdf(file):
                 text += page_text + "\n"
     return text.strip()
 
-
-
-
-
+# URL Text Extractor
 def extract_text_from_url(url):
     try:
         if "wikipedia.org" in url:
-            res = requests.get(url, timeout=10)  # timeout added
-            res.raise_for_status()  # check for HTTP errors
+            res = requests.get(url, timeout=10)
+            res.raise_for_status()
             soup = BeautifulSoup(res.content, "html.parser")
             paragraphs = soup.find_all("p")
             text_content = "\n".join(p.text.strip() for p in paragraphs if p.text.strip())
-            
-            # Optional: limit to first 50 paragraphs to avoid huge texts
             text_parts = text_content.split("\n")
             limited_text = "\n".join(text_parts[:50])
             return limited_text.strip()
@@ -57,8 +50,7 @@ def extract_text_from_url(url):
         print(f"URL extraction failed: {e}")
         return ""
 
-
-
+# Summarizer
 def generate_summary(text, mode="paragraph", length="medium"):
     length_map = {
         "short": 50,
@@ -76,14 +68,16 @@ def generate_summary(text, mode="paragraph", length="medium"):
     )
     return summary_result[0]['summary_text']
 
+# Health Check
 @app.get("/")
 def home():
     return {"message": "📄 AI Summarizer API Running!"}
 
+# Summarize Endpoint
 @app.post("/summarize")
 async def summarize(
     text: str = Form(None),
-    pdf_file: UploadFile | None = File(None),
+    pdf_file: UploadFile = File(None),
     url: str = Form(None),
     mode: str = Form("paragraph"),
     length: str = Form("medium")
@@ -94,10 +88,9 @@ async def summarize(
         content = text.strip()
 
     elif pdf_file is not None and pdf_file.filename:
-    content = extract_text_from_pdf(pdf_file.file)
-    if not content:
-        return JSONResponse({"error": "❌ No readable text extracted from the PDF."}, 400)
-
+        content = extract_text_from_pdf(pdf_file.file)
+        if not content:
+            return JSONResponse({"error": "❌ No readable text extracted from the PDF."}, 400)
 
     elif url:
         content = extract_text_from_url(url)
@@ -118,4 +111,3 @@ async def summarize(
         "summaryLength": len(summary),
         "mode": mode
     }
-