Update pipeline.py

pipeline.py

@@ -296,7 +296,7 @@ def pipeline_with_gemini(accessions):
               if iso != "unknown": query_kw = iso
               else: query_kw = acc
               #text_link, tables_link, final_input_link = data_preprocess.preprocess_document(link,saveLinkFolder, isolate=query_kw)
-              success_process, output_process = run_with_timeout(data_preprocess.preprocess_document,args=(link,sample_folder_id),kwargs={"isolate":query_kw},timeout=300)
+              success_process, output_process = run_with_timeout(data_preprocess.preprocess_document,args=(link,sample_folder_id),kwargs={"isolate":query_kw},timeout=100)
               if success_process:
                 text_link, tables_link, final_input_link = output_process[0], output_process[1], output_process[2]
                 print("yes succeed for process document")
@@ -377,16 +377,18 @@ def pipeline_with_gemini(accessions):
       faiss_filename = "faiss_index.bin"
       chunks_filename = "document_chunks.json"
       lookup_filename = "structured_lookup.json"
-    
+      print("name of faiss: ", faiss_filename)  
+      
       # Save in temporary local directory
       faiss_index_path = os.path.join(tmp_dir, faiss_filename)
       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)  
+      
       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)
-
+      print("move to load rag")
       master_structured_lookup, faiss_index, document_chunks = model.load_rag_assets(
           faiss_index_path, document_chunks_path, structured_lookup_path
       )