From 89f10d841df4c0bd99becf9421a929f2af16c762 Mon Sep 17 00:00:00 2001 From: suojiayi Date: Tue, 13 May 2025 06:39:28 +0000 Subject: [PATCH] =?UTF-8?q?feat:=20=E5=AF=B9=E8=AF=9D=E8=A1=A5=E5=85=A8?= =?UTF-8?q?=E8=AE=AD=E7=BB=83=E6=95=B0=E6=8D=AE=E7=94=9F=E6=88=90?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- data_generate/query_completion/merge.py | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/data_generate/query_completion/merge.py b/data_generate/query_completion/merge.py index 27290df..d7981f7 100644 --- a/data_generate/query_completion/merge.py +++ b/data_generate/query_completion/merge.py @@ -152,12 +152,12 @@ def merge_jsonl_files(file1, file2, output_file): record = json.loads(line.strip()) index = record.get('data_idx') cluster_center = record.get('cluster_center') - #embedding = record.get('embedding') + embedding = record.get('embedding') # 如果'index'存在于第一个文件的'uid'中，则合并数据 if index in data_dict: data_dict[index]['cluster_center'] = cluster_center - #data_dict[index]['embedding'] = embedding + data_dict[index]['embedding'] = embedding # 将合并后的数据写入输出文件 with open(output_file, 'w', encoding='utf-8') as out_f: @@ -195,12 +195,9 @@ def merge_jsonl_files(file1, file2, output_file): record = json.loads(line.strip()) index = record.get('uid') score = record.get('answer') - embedding = record.get('embedding') - # 如果'index'存在于第一个文件的'uid'中，则合并数据 if index in data_dict: data_dict[index]['score'] = score - data_dict[index]['embedding'] = embedding # 将合并后的数据写入输出文件 with open(output_file, 'w', encoding='utf-8') as out_f: