Update app.py

app.py

@@ -330,6 +330,18 @@ def get_model_files(model_type="causal_lm"):
 def get_gallery_files(file_types=["png"]):
     return sorted([f for ext in file_types for f in glob.glob(f"*.{ext}")])
 
+def download_pdf(url, output_path):
+    try:
+        response = requests.get(url, stream=True, timeout=10)
+        if response.status_code == 200:
+            with open(output_path, "wb") as f:
+                for chunk in response.iter_content(chunk_size=8192):
+                    f.write(chunk)
+            return True
+    except requests.RequestException as e:
+        logger.error(f"Failed to download {url}: {e}")
+    return False
+
 # Mock Search Tool for RAG
 def mock_search(query: str) -> str:
     if "superhero" in query.lower():
@@ -651,7 +663,7 @@ with tab4:
                 csv_path = f"sft_dataset_{int(time.time())}.csv"
                 with open(csv_path, "w", newline="") as f:
                     writer = csv.writer(f)
-                    writer.writerow(["image", "text()])
+                    writer.writerow(["image", "text"])
                     for _, row in edited_data.iterrows():
                         writer.writerow([row["image"], row["text"]])
                 st.markdown(get_download_link(csv_path, "text/csv", "Download SFT Dataset CSV"), unsafe_allow_html=True)