main
HuangHai 1 month ago
parent 68231fd5f8
commit 8579fcdbed

@ -85,7 +85,7 @@ def process_query(query):
"""处理用户查询并生成报告"""
print(f"正在搜索与'{query}'相关的数据...")
context = search_related_data(query)
print(f"找到{len(context.split('\n\n'))}条相关数据")
print(f"找到{len(context.split(chr(10)+chr(10)))}条相关数据")
print("正在生成报告...")
report = generate_report(query, context)

@ -1,129 +1,94 @@
D:\anaconda3\envs\rag\python.exe D:\dsWork\dsProject\dsRag\T7_Query.py
D:\anaconda3\envs\rag\python.exe D:\dsWork\dsProject\dsRag\T8_RAG.py
D:\anaconda3\envs\rag\lib\site-packages\jieba\_compat.py:18: UserWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html. The pkg_resources package is slated for removal as early as 2025-11-30. Refrain from using this package or pin to Setuptools<81.
import pkg_resources
2025-06-23 20:03:12,025 - INFO - loading projection weights from D:\Tencent_AILab_ChineseEmbedding\Tencent_AILab_ChineseEmbedding.txt
2025-06-23 20:03:13,349 - INFO - KeyedVectors lifecycle event {'msg': 'loaded (10000, 200) matrix of type float32 from D:\\Tencent_AILab_ChineseEmbedding\\Tencent_AILab_ChineseEmbedding.txt', 'binary': False, 'encoding': 'utf8', 'datetime': '2025-06-23T20:03:13.329238', 'gensim': '4.3.3', 'python': '3.10.18 | packaged by conda-forge | (main, Jun 4 2025, 14:42:04) [MSC v.1943 64 bit (AMD64)]', 'platform': 'Windows-10-10.0.19044-SP0', 'event': 'load_word2vec_format'}
2025-06-23 20:03:13,349 - INFO - 模型加载成功,词向量维度: 200
2025-06-23 20:13:47,913 - INFO - loading projection weights from D:\Tencent_AILab_ChineseEmbedding\Tencent_AILab_ChineseEmbedding.txt
2025-06-23 20:13:49,382 - INFO - KeyedVectors lifecycle event {'msg': 'loaded (10000, 200) matrix of type float32 from D:\\Tencent_AILab_ChineseEmbedding\\Tencent_AILab_ChineseEmbedding.txt', 'binary': False, 'encoding': 'utf8', 'datetime': '2025-06-23T20:13:49.361378', 'gensim': '4.3.3', 'python': '3.10.18 | packaged by conda-forge | (main, Jun 4 2025, 14:42:04) [MSC v.1943 64 bit (AMD64)]', 'platform': 'Windows-10-10.0.19044-SP0', 'event': 'load_word2vec_format'}
2025-06-23 20:13:49,382 - INFO - 模型加载成功,词向量维度: 200
D:\anaconda3\envs\rag\lib\site-packages\elasticsearch\_sync\client\__init__.py:311: SecurityWarning: Connecting to 'https://10.10.14.206:9200' using TLS with verify_certs=False is insecure
_transport = transport_class(
正在搜索与'整理云南省初中在校生情况文档'相关的数据...
Building prefix dict from the default dictionary ...
2025-06-23 20:03:13,622 - DEBUG - Building prefix dict from the default dictionary ...
2025-06-23 20:13:50,520 - DEBUG - Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\ADMINI~1\AppData\Local\Temp\jieba.cache
2025-06-23 20:03:13,622 - DEBUG - Loading model from cache C:\Users\ADMINI~1\AppData\Local\Temp\jieba.cache
测试句子: (万人) 教职工数需求
向量搜索结果:
Loading model cost 0.655 seconds.
2025-06-23 20:03:14,277 - DEBUG - Loading model cost 0.655 seconds.
2025-06-23 20:13:50,520 - DEBUG - Loading model from cache C:\Users\ADMINI~1\AppData\Local\Temp\jieba.cache
Loading model cost 0.648 seconds.
2025-06-23 20:13:51,168 - DEBUG - Loading model cost 0.648 seconds.
Prefix dict has been built successfully.
2025-06-23 20:03:14,278 - DEBUG - Prefix dict has been built successfully.
2025-06-23 20:03:14,278 - INFO - 文本: (万人) 教职工数需求, 分词结果: ['', '万人', '', '\t', '教职工', '数', '需求']
2025-06-23 20:03:14,278 - INFO - 有效词向量数量: 5
2025-06-23 20:03:14,278 - INFO - 生成的平均向量: [-0.0246012 -0.1393744 -0.0812634 0.22129479 -0.0203214 ]...
2025-06-23 20:13:51,169 - DEBUG - Prefix dict has been built successfully.
2025-06-23 20:13:51,169 - INFO - 文本: 整理云南省初中在校生情况文档, 分词结果: ['整理', '云南省', '初中', '在校生', '情况', '文档']
2025-06-23 20:13:51,169 - INFO - 有效词向量数量: 3
2025-06-23 20:13:51,169 - INFO - 生成的平均向量: [ 0.18687634 -0.19447033 -0.04333766 -0.05068566 0.09433967]...
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
2025-06-23 20:03:14,384 - INFO - POST https://10.10.14.206:9200/knowledge_base/_search [status:200 duration:0.104s]
2025-06-23 20:13:51,222 - INFO - POST https://10.10.14.206:9200/knowledge_base/_search [status:200 duration:0.051s]
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
- (万人) 教职工数需求
- (万人) 教职工数需求
- (万人) 专任教师数需求
- (万人) 教职工数需求
- (万人) 教职工需求
2025-06-23 20:13:51,231 - INFO - POST https://10.10.14.206:9200/raw_texts/_search [status:200 duration:0.009s]
找到10条相关数据
正在生成报告...
2025-06-23 20:13:56,582 - INFO - Retrying request to /chat/completions in 0.469314 seconds
2025-06-23 20:14:02,067 - INFO - Retrying request to /chat/completions in 0.762535 seconds
Traceback (most recent call last):
File "D:\anaconda3\envs\rag\lib\site-packages\httpx\_transports\default.py", line 101, in map_httpcore_exceptions
yield
File "D:\anaconda3\envs\rag\lib\site-packages\httpx\_transports\default.py", line 250, in handle_request
resp = self._pool.handle_request(req)
File "D:\anaconda3\envs\rag\lib\site-packages\httpcore\_sync\connection_pool.py", line 256, in handle_request
raise exc from None
File "D:\anaconda3\envs\rag\lib\site-packages\httpcore\_sync\connection_pool.py", line 236, in handle_request
response = connection.handle_request(
File "D:\anaconda3\envs\rag\lib\site-packages\httpcore\_sync\connection.py", line 101, in handle_request
raise exc
File "D:\anaconda3\envs\rag\lib\site-packages\httpcore\_sync\connection.py", line 78, in handle_request
stream = self._connect(request)
File "D:\anaconda3\envs\rag\lib\site-packages\httpcore\_sync\connection.py", line 124, in _connect
stream = self._network_backend.connect_tcp(**kwargs)
File "D:\anaconda3\envs\rag\lib\site-packages\httpcore\_backends\sync.py", line 207, in connect_tcp
with map_exceptions(exc_map):
File "D:\anaconda3\envs\rag\lib\contextlib.py", line 153, in __exit__
self.gen.throw(typ, value, traceback)
File "D:\anaconda3\envs\rag\lib\site-packages\httpcore\_exceptions.py", line 14, in map_exceptions
raise to_exc(exc) from exc
httpcore.ConnectTimeout: timed out
文本精确搜索结果:
2025-06-23 20:03:14,419 - INFO - POST https://10.10.14.206:9200/raw_texts/_search [status:200 duration:0.033s]
2025-06-23 20:03:14,420 - INFO - 文本: 表 6 高等教育规模及资源配置需求预测统计表, 分词结果: ['表', ' ', '6', ' ', '高等教育', '规模', '及', '资源配置', '需求预测', '统计表']
2025-06-23 20:03:14,420 - INFO - 有效词向量数量: 4
2025-06-23 20:03:14,421 - INFO - 生成的平均向量: [ 0.18066275 -0.12073625 -0.12693274 0.219709 0.00525575]...
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
- (万人) 教职工数需求
- (万人) 教职工数需求
- (万人) 教职工数需求
==================================================
测试句子: 表 6 高等教育规模及资源配置需求预测统计表
向量搜索结果:
- 表 6 高等教育规模及资源配置需求预测统计表
- 表 1 学前教育规模及资源配置需求预测统计表
- 表 5 中等职业教育规模及资源配置需求预测统计表
- 表 4 普通高中教育规模及资源配置需求预测统计表
- 表 3 初中教育规模及资源配置需求预测统计表
The above exception was the direct cause of the following exception:
文本精确搜索结果:
- 表 6 高等教育规模及资源配置需求预测统计表
==================================================
测试句子: 指标
向量搜索结果:
2025-06-23 20:03:14,431 - INFO - POST https://10.10.14.206:9200/knowledge_base/_search [status:200 duration:0.008s]
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
2025-06-23 20:03:14,440 - INFO - POST https://10.10.14.206:9200/raw_texts/_search [status:200 duration:0.008s]
2025-06-23 20:03:14,440 - INFO - 文本: 指标, 分词结果: ['指标']
2025-06-23 20:03:14,441 - INFO - 有效词向量数量: 1
2025-06-23 20:03:14,441 - INFO - 生成的平均向量: [-0.24731 -0.30286 -0.223835 0.217864 -0.162194]...
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
2025-06-23 20:03:14,450 - INFO - POST https://10.10.14.206:9200/knowledge_base/_search [status:200 duration:0.007s]
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
2025-06-23 20:03:14,456 - INFO - POST https://10.10.14.206:9200/raw_texts/_search [status:200 duration:0.005s]
2025-06-23 20:03:14,457 - INFO - 文本: 二是保障随迁子女受教育权利。健全以居住证为主要依据的农业转移人口随迁子女入学保障政策,以公办学校为主将随迁子女纳入流入地义务教育保障范围,保障享受基本公共教育服务。, 分词结果: ['二是', '保障', '随迁', '子女', '受', '教育', '权利', '。', '健全', '以', '居住证', '为', '主要', '依据', '的', '农业', '转移', '人口', '随迁', '子女', '入学', '保障', '政策', '', '以', '公办', '学校', '为主', '将', '随迁', '子女', '纳入', '流入地', '义务教育', '保障', '范围', '', '保障', '享受', '基本', '公共', '教育', '服务', '。']
2025-06-23 20:03:14,457 - INFO - 有效词向量数量: 32
2025-06-23 20:03:14,458 - INFO - 生成的平均向量: [ 0.18174155 -0.13902284 -0.13658895 0.17560197 0.04838478]...
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
- 指标
- 指标
- 指标
- 指标
- 指标
文本精确搜索结果:
- 指标
- 指标
- 指标
- 指标
- 指标
- 指标
- 2001-2022年云南省人口指标统计表
- 各学段数据及人口指标统计表
- 1.2001-2022年云南省人口指标统计表 33
- 2.各学段数据及人口指标统计表 34
==================================================
测试句子: 二是保障随迁子女受教育权利。健全以居住证为主要依据的农业转移人口随迁子女入学保障政策,以公办学校为主将随迁子女纳入流入地义务教育保障范围,保障享受基本公共教育服务。
向量搜索结果:
- 健全以居住证为主要依据的农业转移人口随迁子女入学保障政策,以公办学校为主将随迁子女纳入流入地义务教育保障范围,保障享受基本公共教育服务
- 在学校布局、入学政策等方面守牢底线,既适应城乡人口变化趋势,又能提供公平的受教育机会,保障不同群体受教育权利
- 健全随迁子女入学保障政策,保障各类特殊群体受教育权利
- 健全随迁子女入学保障政策,保障各类特殊群体受教育权利
- 健全随迁子女入学保障政策,保障各类特殊群体受教育权利
Traceback (most recent call last):
File "D:\anaconda3\envs\rag\lib\site-packages\openai\_base_client.py", line 972, in request
response = self._client.send(
File "D:\anaconda3\envs\rag\lib\site-packages\httpx\_client.py", line 914, in send
response = self._send_handling_auth(
File "D:\anaconda3\envs\rag\lib\site-packages\httpx\_client.py", line 942, in _send_handling_auth
response = self._send_handling_redirects(
File "D:\anaconda3\envs\rag\lib\site-packages\httpx\_client.py", line 979, in _send_handling_redirects
response = self._send_single_request(request)
File "D:\anaconda3\envs\rag\lib\site-packages\httpx\_client.py", line 1014, in _send_single_request
response = transport.handle_request(request)
File "D:\anaconda3\envs\rag\lib\site-packages\httpx\_transports\default.py", line 249, in handle_request
with map_httpcore_exceptions():
File "D:\anaconda3\envs\rag\lib\contextlib.py", line 153, in __exit__
self.gen.throw(typ, value, traceback)
File "D:\anaconda3\envs\rag\lib\site-packages\httpx\_transports\default.py", line 118, in map_httpcore_exceptions
raise mapped_exc(message) from exc
httpx.ConnectTimeout: timed out
文本精确搜索结果:
2025-06-23 20:03:14,464 - INFO - POST https://10.10.14.206:9200/knowledge_base/_search [status:200 duration:0.005s]
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
2025-06-23 20:03:14,475 - INFO - POST https://10.10.14.206:9200/raw_texts/_search [status:200 duration:0.010s]
2025-06-23 20:03:14,475 - INFO - 文本: 2012—2022年全省人口总体呈现“长增突降”态势, 分词结果: ['', '一', '', '2012', '—', '2022', '年', '全省', '人口', '总体', '呈现', '“', '长增', '', '突降', '”', '态势']
2025-06-23 20:03:14,476 - INFO - 有效词向量数量: 14
2025-06-23 20:03:14,476 - INFO - 生成的平均向量: [ 0.06827115 -0.212308 -0.07557671 0.21362822 0.12347364]...
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
2025-06-23 20:03:14,482 - INFO - POST https://10.10.14.206:9200/knowledge_base/_search [status:200 duration:0.005s]
D:\anaconda3\envs\rag\lib\site-packages\urllib3\connectionpool.py:1097: InsecureRequestWarning: Unverified HTTPS request is being made to host '10.10.14.206'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings
warnings.warn(
==================================================
测试句子: 2012—2022年全省人口总体呈现“长增突降”态势
向量搜索结果:
- 2012—2022年全省人口总体呈现“长增突降”态势
- 2012—2022年全省人口总体呈现“长增突降”态势 2
- 总的看2012—2022年全省人口变化呈现先增、突降的态势图1
- 结合全国趋势看预计我省2023—2035年新生人口数持续保持在较低水平图2从2024年起全省人口总数呈缓慢下降趋势与全国范围人口下降趋势基本同步图1
- 按照全省普通高中师生比标准112.5测算2023—2035年全省普通高中教师需求量逐年增大2033年达到峰值10.31万人与2022年实际专任教师数7.64万人比存在2.67万人的缺口图20
The above exception was the direct cause of the following exception:
文本精确搜索结果:
- 2012—2022年全省人口总体呈现“长增突降”态势
- 2012—2022年全省人口总体呈现“长增突降”态势 2
==================================================
2025-06-23 20:03:14,488 - INFO - POST https://10.10.14.206:9200/raw_texts/_search [status:200 duration:0.005s]
Traceback (most recent call last):
File "D:\dsWork\dsProject\dsRag\T8_RAG.py", line 98, in <module>
report = process_query(user_query)
File "D:\dsWork\dsProject\dsRag\T8_RAG.py", line 91, in process_query
report = generate_report(query, context)
File "D:\dsWork\dsProject\dsRag\T8_RAG.py", line 73, in generate_report
response = client.chat.completions.create(
File "D:\anaconda3\envs\rag\lib\site-packages\openai\_utils\_utils.py", line 287, in wrapper
return func(*args, **kwargs)
File "D:\anaconda3\envs\rag\lib\site-packages\openai\resources\chat\completions\completions.py", line 925, in create
return self._post(
File "D:\anaconda3\envs\rag\lib\site-packages\openai\_base_client.py", line 1249, in post
return cast(ResponseT, self.request(cast_to, opts, stream=stream, stream_cls=stream_cls))
File "D:\anaconda3\envs\rag\lib\site-packages\openai\_base_client.py", line 990, in request
raise APITimeoutError(request=request) from err
openai.APITimeoutError: Request timed out.
进程已结束,退出代码为 0
进程已结束,退出代码为 1

Loading…
Cancel
Save