Update backend/main.py

backend/main.py

@@ -5,7 +5,7 @@ import tempfile
 from pathlib import Path
 from typing import List
 
-import pdfplumber
+import fitz
 from groq import Groq
 from fastapi import FastAPI, File, UploadFile, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
@@ -86,14 +86,14 @@ Return ONLY valid JSON (no markdown fences, no extra text) using this schema:
 
 def extract_text_from_pdf(pdf_path: str) -> str:
     text = ""
-    with pdfplumber.open(pdf_path) as pdf:
-        for page in pdf.pages:
-            page_text = page.extract_text()
-            if page_text:
-                text += page_text + "\n"
+
+    doc = fitz.open(pdf_path)
+
+    for page in doc:
+        text += page.get_text()
 
     if not text.strip():
-       raise ValueError("PDF text extraction failed.")
+        raise ValueError("PDF text extraction failed.")
 
     if len(text.strip()) < 500:
         text = text[:2000]
@@ -109,7 +109,7 @@ def extract_text_from_pdf(pdf_path: str) -> str:
         text, re.IGNORECASE | re.DOTALL | re.MULTILINE
     )
 
-    if methods_match and len(methods_match.group(1).strip()) > 200:
+    if methods_match and len(methods_match.group(2).strip()) > 200:
         text = methods_match.group(2)
     else:
         chars = len(text)