Update pipeline.py

pipeline.py

@@ -208,8 +208,16 @@ def pipeline_with_gemini(accessions):
       # Define local temp paths for reading/writing
       import tempfile
       tmp_dir = tempfile.mkdtemp()
-      file_chunk_path = os.path.join(tmp_dir, chunk_filename)
-      file_all_path = os.path.join(tmp_dir, all_filename)
+      #file_chunk_path = os.path.join(tmp_dir, chunk_filename)
+      #file_all_path = os.path.join(tmp_dir, all_filename)
+      file_chunk_path = os.path.join(tempfile.gettempdir(), chunk_filename)
+      file_all_path = os.path.join(tempfile.gettempdir(), all_filename)  
+    
+      # 🔥 Remove the local file first if it exists
+      if os.path.exists(file_chunk_path):
+        os.remove(file_chunk_path)
+      if os.path.exists(file_all_path):
+        os.remove(file_all_path)    
     
       # Try to download if already exists on Drive
       chunk_exists = download_file_from_drive(chunk_filename, sample_folder_id, file_chunk_path)
@@ -393,7 +401,13 @@ def pipeline_with_gemini(accessions):
       document_chunks_path = os.path.join(tmp_dir, chunks_filename)
       structured_lookup_path = os.path.join(tmp_dir, lookup_filename)
       print("name if faiss path: ", faiss_index_path)  
-      
+      # 🔥 Remove the local file first if it exists
+      if os.path.exists(faiss_index_path):
+        os.remove(faiss_index_path)
+      if os.path.exists(document_chunks_path):
+        os.remove(document_chunks_path)
+      if os.path.exists(structured_lookup_path):
+        os.remove(structured_lookup_path)    
       download_file_from_drive(faiss_filename, sample_folder_id, faiss_index_path)
       download_file_from_drive(chunks_filename, sample_folder_id, document_chunks_path)
       download_file_from_drive(lookup_filename, sample_folder_id, structured_lookup_path)