Fix bug in bm25

RUC-NLPIR · Jun 23, 2024 · 5009089 · 5009089
1 parent 5905168
commit 5009089
Showing 1 changed file with 1 addition and 7 deletions.
diff --git a/flashrag/retriever/index_builder.py b/flashrag/retriever/index_builder.py
@@ -97,13 +97,7 @@ def build_bm25_index(self):
         temp_dir = self.save_dir + "/temp"
         temp_file_path = temp_dir + "/temp.jsonl"
         os.makedirs(temp_dir)
-
-        if self.have_contents:
-            shutil.copyfile(self.corpus_path, temp_file_path)
-        else:
-            with open(temp_file_path, "w") as f:
-                for item in self.corpus:
-                    f.write(json.dumps(item) + "\n")
+        shutil.copyfile(self.corpus_path, temp_file_path)
 
         print("Start building bm25 index...")
         pyserini_args = ["--collection", "JsonCollection",