Update pipeline.py

pipeline.py

@@ -267,7 +267,7 @@ async def process_link_chunk_allOutput(link, iso, acc, saveLinkFolder, linksWith
 
     return all_output
 
-def extractSources(doi, linksWithTexts, links, all_output, iso, acc, saveLinkFolder, niche_cases=None):
+async def extractSources(doi, linksWithTexts, links, all_output, iso, acc, saveLinkFolder, niche_cases=None):
     article_text = ""
     if doi != "unknown":
         link = 'https://doi.org/' + doi
@@ -503,7 +503,7 @@ async def pipeline_with_gemini(accessions,stop_flag=None, save_df=None, niche_ca
             acc_score["file_all_output"] = str(all_filename)    
       print("acc sscore for file all output: ", acc_score["file_all_output"])  
       if len(acc_score["file_all_output"]) == 0 or doi!="unknown":  
-          linksWithTexts, links, all_output = extractSources(doi, linksWithTexts, links, all_output, iso, acc, sample_folder_id, niche_cases)
+          linksWithTexts, links, all_output = await extractSources(doi, linksWithTexts, links, all_output, iso, acc, sample_folder_id, niche_cases)
           links = unique_preserve_order(links)
           print("this is links: ",links)
           acc_score["source"] = links
@@ -539,14 +539,14 @@ async def pipeline_with_gemini(accessions,stop_flag=None, save_df=None, niche_ca
                 temp_source = True      
             if temp_source:
                 print("temp source is true so have to try again search link")
-                linksWithTexts, links, all_output = extractSources(doi, linksWithTexts, links, all_output, iso, acc, sample_folder_id, niche_cases)
+                linksWithTexts, links, all_output = await extractSources(doi, linksWithTexts, links, all_output, iso, acc, sample_folder_id, niche_cases)
                 links = unique_preserve_order(links)
                 print("links: ", links)
                 acc_score["source"] = links
         except:
             try:
                 print("in the exception and start to get link")
-                linksWithTexts, links, all_output = extractSources(doi, linksWithTexts, links, all_output, iso, acc, sample_folder_id, niche_cases)
+                linksWithTexts, links, all_output = await extractSources(doi, linksWithTexts, links, all_output, iso, acc, sample_folder_id, niche_cases)
                 links = unique_preserve_order(links)
                 print("this is links: ",links)
                 acc_score["source"] = links