main
HuangHai 4 weeks ago
parent 9e0e39a6fc
commit 9e82dc00ce

@ -16,11 +16,12 @@ es = Elasticsearch(
def select_all_data(index_name):
try:
# 构建查询条件 - 匹配所有文档
# 修改查询条件为获取前10条数据
query = {
"query": {
"match_all": {}
},
"size": 1000 # 限制返回结果数量
"size": 10 # 仅获取10条数据
}
# 执行查询
@ -36,6 +37,12 @@ def select_all_data(index_name):
print(f" 内容: {hit['_source'].get('user_input', '')}")
print(f" 标签: {hit['_source'].get('tags', '')}")
print(f" 时间戳: {hit['_source'].get('timestamp', '')}")
# 在循环中添加打印完整数据结构的代码
if i == 1: # 只打印第一条数据的完整结构
print("完整数据结构:")
import pprint
pp = pprint.PrettyPrinter(indent=4)
pp.pprint(hit['_source'])
print("-" * 50)
except Exception as e:
print(f"查询出错: {e}")

@ -21,13 +21,19 @@ query_tag = ["MATH_DATA_1", "小学数学"] # 可以修改为其他需要的标
query = {
"query": {
"bool": {
"must": [
"should": [
{
"terms": {
"tags.tags": query_tag
"match": {
"tags": "MATH_DATA_1"
}
},
{
"match": {
"tags": "小学数学"
}
}
]
],
"minimum_should_match": 1
}
},
"size": 1000
@ -45,9 +51,15 @@ try:
for i, hit in enumerate(hits, 1):
print(f"{i}. ID: {hit['_id']}")
print(f" 内容: {hit['_source'].get('user_input', '')}")
print(f" 标签: {hit['_source'].get('tags', '')}")
print(f" 标签: {hit['_source']['tags']['tags']}")
print("-" * 50)
except Exception as e:
print(f"查询执行失败,错误详情: {str(e)}")
print(f"查询条件: {query}")
if hasattr(e, 'info') and isinstance(e.info, dict):
print(f"Elasticsearch错误详情: {e.info}")
if hasattr(e, 'status_code'):
print(f"HTTP状态码: {e.status_code}")
print(f"查询出错: {str(e)}")
# 4. 执行查询

File diff suppressed because one or more lines are too long

File diff suppressed because one or more lines are too long
Loading…
Cancel
Save