1537 lines
110 KiB
Plaintext
1537 lines
110 KiB
Plaintext
2026-06-08 13:31:01 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:31:01 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:31:01 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:31:01 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:31:02 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:32:29 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 319 字符
|
|
2026-06-08 13:32:29 [INFO ] llm_extractor: LLM 发票提取成功: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:32:29 [INFO ] extractor: [高铁票] 已解析: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:32:29 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:33:55 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 271 字符
|
|
2026-06-08 13:33:55 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:33:55 [INFO ] extractor: [高铁票] 已解析: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:33:55 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:35:21 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 311 字符
|
|
2026-06-08 13:35:21 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:35:21 [INFO ] extractor: [酒店住宿] 已解析: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:35:21 [INFO ] extractor: 共处理 3 张发票
|
|
2026-06-08 13:35:21 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 13:35:21 [INFO ] pipeline: [1/3] 发票提取 完成
|
|
2026-06-08 13:38:29 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:38:29 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:38:29 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:38:29 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:38:30 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:39:15 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:39:15 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:39:15 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:39:15 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:39:16 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:39:26 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 354 字符
|
|
2026-06-08 13:39:26 [INFO ] llm_extractor: LLM 发票提取成功: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:39:26 [INFO ] extractor: [高铁票] 已解析: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:39:26 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:39:35 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 318 字符
|
|
2026-06-08 13:39:35 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:39:35 [INFO ] extractor: [高铁票] 已解析: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:39:35 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:39:46 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 309 字符
|
|
2026-06-08 13:39:46 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:39:46 [INFO ] extractor: [酒店住宿] 已解析: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:39:46 [INFO ] extractor: 共处理 3 张发票
|
|
2026-06-08 13:39:46 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 13:39:46 [INFO ] pipeline: [1/3] 发票提取 完成
|
|
2026-06-08 13:40:04 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:40:04 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:40:04 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:40:04 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:40:05 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:40:13 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 317 字符
|
|
2026-06-08 13:40:13 [INFO ] llm_extractor: LLM 发票提取成功: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:40:13 [INFO ] extractor: [高铁票] 已解析: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:40:13 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:40:23 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 318 字符
|
|
2026-06-08 13:40:23 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:40:23 [INFO ] extractor: [高铁票] 已解析: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:40:23 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:40:34 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 309 字符
|
|
2026-06-08 13:40:34 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:40:34 [INFO ] extractor: [酒店住宿] 已解析: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:40:34 [INFO ] extractor: 共处理 3 张发票
|
|
2026-06-08 13:40:34 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 13:40:34 [INFO ] pipeline: [1/3] 发票提取 完成
|
|
2026-06-08 13:45:56 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:45:56 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:45:56 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:45:56 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:45:57 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:46:05 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 317 字符
|
|
2026-06-08 13:46:05 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000154520",
|
|
"开票日期": "2026/3/23",
|
|
"项目名称": "高铁票",
|
|
"规格型号": "",
|
|
"价税合计": "258.00",
|
|
"销售方名称": "中国铁路",
|
|
"出发站": "阜阳西",
|
|
"到达站": "无锡",
|
|
"车次": "G7221",
|
|
"乘车日期": "2026/3/21",
|
|
"座位等级": "二等座",
|
|
"人员姓名": "王建锋",
|
|
"刷卡日期": "",
|
|
"公务卡号": "",
|
|
"刷卡金额": "",
|
|
"备注": "",
|
|
"工号": ""
|
|
}
|
|
2026-06-08 13:46:05 [INFO ] llm_extractor: LLM 发票提取成功: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:46:05 [INFO ] extractor: [高铁票] 已解析: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:46:05 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:46:15 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 318 字符
|
|
2026-06-08 13:46:15 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26329166851000278168",
|
|
"开票日期": "2026/3/23",
|
|
"项目名称": "高铁票",
|
|
"规格型号": "",
|
|
"价税合计": "259.00",
|
|
"销售方名称": "中国铁路",
|
|
"出发站": "无锡东",
|
|
"到达站": "阜阳西",
|
|
"车次": "G1826",
|
|
"乘车日期": "2026/3/22",
|
|
"座位等级": "二等座",
|
|
"人员姓名": "王建锋",
|
|
"刷卡日期": "",
|
|
"公务卡号": "",
|
|
"刷卡金额": "",
|
|
"备注": "",
|
|
"工号": ""
|
|
}
|
|
2026-06-08 13:46:15 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:46:15 [INFO ] extractor: [高铁票] 已解析: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:46:15 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:46:23 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 309 字符
|
|
2026-06-08 13:46:23 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26322000002199439186",
|
|
"开票日期": "2026/3/23",
|
|
"项目名称": "*住宿服务*住宿费",
|
|
"规格型号": "间 天",
|
|
"价税合计": "368.60",
|
|
"销售方名称": "滨湖区雪浪山庄花园酒店",
|
|
"出发站": "",
|
|
"到达站": "",
|
|
"车次": "",
|
|
"乘车日期": "",
|
|
"座位等级": "",
|
|
"人员姓名": "",
|
|
"刷卡日期": "",
|
|
"公务卡号": "",
|
|
"刷卡金额": "",
|
|
"备注": "",
|
|
"工号": ""
|
|
}
|
|
2026-06-08 13:46:23 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:46:23 [INFO ] extractor: [酒店住宿] 已解析: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:46:23 [INFO ] extractor: 共处理 3 张发票
|
|
2026-06-08 13:46:23 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 13:46:23 [INFO ] pipeline: [1/3] 发票提取 完成
|
|
2026-06-08 13:47:51 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:47:51 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:47:51 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:47:51 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:47:52 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:48:01 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 316 字符
|
|
2026-06-08 13:48:01 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000154520",
|
|
"开票日期": "2026/3/23",
|
|
"项目名称": "票价",
|
|
"规格型号": "",
|
|
"价税合计": "258.00",
|
|
"销售方名称": "中国铁路",
|
|
"出发站": "阜阳西",
|
|
"到达站": "无锡",
|
|
"车次": "G7221",
|
|
"乘车日期": "2026/3/21",
|
|
"座位等级": "二等座",
|
|
"人员姓名": "王建锋",
|
|
"刷卡日期": "",
|
|
"公务卡号": "",
|
|
"刷卡金额": "",
|
|
"备注": "",
|
|
"工号": ""
|
|
}
|
|
2026-06-08 13:48:01 [INFO ] llm_extractor: LLM 发票提取成功: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:48:01 [INFO ] extractor: [高铁票] 已解析: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:48:01 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:48:09 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 324 字符
|
|
2026-06-08 13:48:09 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26329166851000278168",
|
|
"开票日期": "2026/3/23",
|
|
"项目名称": "铁路旅客运输服务费",
|
|
"规格型号": "",
|
|
"价税合计": "259.00",
|
|
"销售方名称": "中国铁路",
|
|
"出发站": "无锡东",
|
|
"到达站": "阜阳西",
|
|
"车次": "G1826",
|
|
"乘车日期": "2026/3/22",
|
|
"座位等级": "二等座",
|
|
"人员姓名": "王建锋",
|
|
"刷卡日期": "",
|
|
"公务卡号": "",
|
|
"刷卡金额": "",
|
|
"备注": "",
|
|
"工号": ""
|
|
}
|
|
2026-06-08 13:48:09 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:48:09 [INFO ] extractor: [高铁票] 已解析: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:48:09 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:48:17 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 309 字符
|
|
2026-06-08 13:48:17 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26322000002199439186",
|
|
"开票日期": "2026/3/23",
|
|
"项目名称": "*住宿服务*住宿费",
|
|
"规格型号": "间 天",
|
|
"价税合计": "368.60",
|
|
"销售方名称": "滨湖区雪浪山庄花园酒店",
|
|
"出发站": "",
|
|
"到达站": "",
|
|
"车次": "",
|
|
"乘车日期": "",
|
|
"座位等级": "",
|
|
"人员姓名": "",
|
|
"刷卡日期": "",
|
|
"公务卡号": "",
|
|
"刷卡金额": "",
|
|
"备注": "",
|
|
"工号": ""
|
|
}
|
|
2026-06-08 13:48:17 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:48:17 [INFO ] extractor: [酒店住宿] 已解析: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:48:17 [INFO ] extractor: 共处理 3 张发票
|
|
2026-06-08 13:48:17 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 13:48:17 [INFO ] pipeline: [1/3] 发票提取 完成
|
|
2026-06-08 13:53:40 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:53:40 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:53:40 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:53:40 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:53:41 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:53:42 [ERROR] llm_extractor: LLM 请求失败: Error code: 400 - {'error': {'message': "'reasoning_effort' must be a string", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}}
|
|
2026-06-08 13:53:42 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 王建峰-阜阳西-无锡东258.pdf (Error code: 400 - {'error': {'message': "'reasoning_effort' must be a string", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}})
|
|
2026-06-08 13:53:42 [INFO ] llm_extractor: 正则回退解析完成: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:53:42 [INFO ] extractor: [高铁票] 已解析: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:53:42 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:53:42 [ERROR] llm_extractor: LLM 请求失败: Error code: 400 - {'error': {'message': "'reasoning_effort' must be a string", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}}
|
|
2026-06-08 13:53:42 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 王建锋-无锡东-阜阳西259.pdf (Error code: 400 - {'error': {'message': "'reasoning_effort' must be a string", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}})
|
|
2026-06-08 13:53:42 [INFO ] llm_extractor: 正则回退解析完成: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:53:42 [INFO ] extractor: [高铁票] 已解析: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:53:42 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:53:42 [ERROR] llm_extractor: LLM 请求失败: Error code: 400 - {'error': {'message': "'reasoning_effort' must be a string", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}}
|
|
2026-06-08 13:53:42 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 王建锋3.21住宿368.6.pdf (Error code: 400 - {'error': {'message': "'reasoning_effort' must be a string", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}})
|
|
2026-06-08 13:53:42 [INFO ] llm_extractor: 正则回退解析完成: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:53:42 [INFO ] extractor: [酒店住宿] 已解析: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:53:42 [INFO ] extractor: 共处理 3 张发票
|
|
2026-06-08 13:53:42 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 13:53:42 [INFO ] pipeline: [1/3] 发票提取 完成
|
|
2026-06-08 13:54:26 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:54:26 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:54:26 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:54:26 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:54:28 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:54:28 [ERROR] llm_extractor: LLM 请求失败: Error code: 400 - {'error': {'message': "Invalid 'reasoning_effort' value: 'on'. Supported values: none, minimal, low, medium, high, xhigh.", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}}
|
|
2026-06-08 13:54:28 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 王建峰-阜阳西-无锡东258.pdf (Error code: 400 - {'error': {'message': "Invalid 'reasoning_effort' value: 'on'. Supported values: none, minimal, low, medium, high, xhigh.", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}})
|
|
2026-06-08 13:54:28 [INFO ] llm_extractor: 正则回退解析完成: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:54:28 [INFO ] extractor: [高铁票] 已解析: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:54:28 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:54:28 [ERROR] llm_extractor: LLM 请求失败: Error code: 400 - {'error': {'message': "Invalid 'reasoning_effort' value: 'on'. Supported values: none, minimal, low, medium, high, xhigh.", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}}
|
|
2026-06-08 13:54:28 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 王建锋-无锡东-阜阳西259.pdf (Error code: 400 - {'error': {'message': "Invalid 'reasoning_effort' value: 'on'. Supported values: none, minimal, low, medium, high, xhigh.", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}})
|
|
2026-06-08 13:54:28 [INFO ] llm_extractor: 正则回退解析完成: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:54:28 [INFO ] extractor: [高铁票] 已解析: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:54:28 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:54:29 [ERROR] llm_extractor: LLM 请求失败: Error code: 400 - {'error': {'message': "Invalid 'reasoning_effort' value: 'on'. Supported values: none, minimal, low, medium, high, xhigh.", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}}
|
|
2026-06-08 13:54:29 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 王建锋3.21住宿368.6.pdf (Error code: 400 - {'error': {'message': "Invalid 'reasoning_effort' value: 'on'. Supported values: none, minimal, low, medium, high, xhigh.", 'type': 'invalid_request_error', 'param': 'reasoning_effort', 'code': 'invalid_value'}})
|
|
2026-06-08 13:54:29 [INFO ] llm_extractor: 正则回退解析完成: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:54:29 [INFO ] extractor: [酒店住宿] 已解析: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:54:29 [INFO ] extractor: 共处理 3 张发票
|
|
2026-06-08 13:54:29 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 13:54:29 [INFO ] pipeline: [1/3] 发票提取 完成
|
|
2026-06-08 13:54:42 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:54:42 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:54:42 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:54:42 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:54:43 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:54:57 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 317 字符
|
|
2026-06-08 13:54:57 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000154520",
|
|
"开票日期": "2026/3/23",
|
|
"项目名称": "高铁票",
|
|
"规格型号": "",
|
|
"价税合计": "258.00",
|
|
"销售方名称": "中国铁路",
|
|
"出发站": "阜阳西",
|
|
"到达站": "无锡",
|
|
"车次": "G7221",
|
|
"乘车日期": "2026/3/21",
|
|
"座位等级": "二等座",
|
|
"人员姓名": "王建锋",
|
|
"刷卡日期": "",
|
|
"公务卡号": "",
|
|
"刷卡金额": "",
|
|
"备注": "",
|
|
"工号": ""
|
|
}
|
|
2026-06-08 13:54:57 [INFO ] llm_extractor: LLM 发票提取成功: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:54:57 [INFO ] extractor: [高铁票] 已解析: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 13:54:57 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:55:08 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 318 字符
|
|
2026-06-08 13:55:08 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26329166851000278168",
|
|
"开票日期": "2026/3/23",
|
|
"项目名称": "高铁票",
|
|
"规格型号": "",
|
|
"价税合计": "259.00",
|
|
"销售方名称": "中国铁路",
|
|
"出发站": "无锡东",
|
|
"到达站": "阜阳西",
|
|
"车次": "G1826",
|
|
"乘车日期": "2026/3/22",
|
|
"座位等级": "二等座",
|
|
"人员姓名": "王建锋",
|
|
"刷卡日期": "",
|
|
"公务卡号": "",
|
|
"刷卡金额": "",
|
|
"备注": "",
|
|
"工号": ""
|
|
}
|
|
2026-06-08 13:55:08 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:55:08 [INFO ] extractor: [高铁票] 已解析: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 13:55:08 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 13:55:17 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 309 字符
|
|
2026-06-08 13:55:17 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26322000002199439186",
|
|
"开票日期": "2026/3/23",
|
|
"项目名称": "*住宿服务*住宿费",
|
|
"规格型号": "间 天",
|
|
"价税合计": "368.60",
|
|
"销售方名称": "滨湖区雪浪山庄花园酒店",
|
|
"出发站": "",
|
|
"到达站": "",
|
|
"车次": "",
|
|
"乘车日期": "",
|
|
"座位等级": "",
|
|
"人员姓名": "",
|
|
"刷卡日期": "",
|
|
"公务卡号": "",
|
|
"刷卡金额": "",
|
|
"备注": "",
|
|
"工号": ""
|
|
}
|
|
2026-06-08 13:55:17 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:55:17 [INFO ] extractor: [酒店住宿] 已解析: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 13:55:17 [INFO ] extractor: 共处理 3 张发票
|
|
2026-06-08 13:55:17 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 13:55:17 [INFO ] pipeline: [1/3] 发票提取 完成
|
|
2026-06-08 13:56:00 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:56:00 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 13:56:00 [INFO ] pipeline: ============================================================
|
|
2026-06-08 13:56:00 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 13:56:02 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:09:24 [INFO ] pipeline: ============================================================
|
|
2026-06-08 14:09:24 [INFO ] pipeline: [1/3] 发票提取
|
|
2026-06-08 14:09:24 [INFO ] pipeline: ============================================================
|
|
2026-06-08 14:09:24 [INFO ] extractor: 发现 3 个 PDF 文件
|
|
2026-06-08 14:09:25 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:09:31 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 200 字符
|
|
2026-06-08 14:09:31 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000154520",
|
|
"开票日期": "2026/3/23",
|
|
"乘车日期": "2026/3/21",
|
|
"出发站": "阜阳西",
|
|
"到达站": "无锡东",
|
|
"座位等级": "二等座",
|
|
"车次": "G7221",
|
|
"人员姓名": "王建锋",
|
|
"票价": "258.00"
|
|
}
|
|
2026-06-08 14:09:31 [INFO ] llm_extractor: LLM 发票提取成功: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 14:09:31 [INFO ] extractor: [高铁票] 已解析: 王建峰-阜阳西-无锡东258.pdf
|
|
2026-06-08 14:09:31 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:09:35 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 200 字符
|
|
2026-06-08 14:09:35 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26329166851000278168",
|
|
"开票日期": "2026/3/23",
|
|
"乘车日期": "2026/3/22",
|
|
"出发站": "无锡东",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1826",
|
|
"人员姓名": "王建锋",
|
|
"票价": "259.00"
|
|
}
|
|
2026-06-08 14:09:35 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 14:09:35 [INFO ] extractor: [高铁票] 已解析: 王建锋-无锡东-阜阳西259.pdf
|
|
2026-06-08 14:09:35 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:09:38 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 95 字符
|
|
2026-06-08 14:09:38 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26322000002199439186",
|
|
"开票日期": "2026/3/23",
|
|
"价税合计": 368.60
|
|
}
|
|
2026-06-08 14:09:38 [INFO ] llm_extractor: LLM 发票提取成功: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 14:09:38 [INFO ] extractor: [酒店住宿] 已解析: 王建锋3.21住宿368.6.pdf
|
|
2026-06-08 14:09:38 [INFO ] extractor: 共处理 3 张发票
|
|
2026-06-08 14:09:38 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 14:09:38 [INFO ] pipeline: [1/3] 发票提取 完成
|
|
2026-06-08 14:14:14 [INFO ] extractor: 发现 5 个 PDF 文件
|
|
2026-06-08 14:14:16 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:14:22 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 14:14:22 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331138",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "张国庆",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 14:14:22 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 14:14:22 [INFO ] extractor: [高铁票] 已解析: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 14:14:22 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:14:27 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 14:14:27 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000335414",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "王建锋",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 14:14:27 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 14:14:27 [INFO ] extractor: [高铁票] 已解析: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 14:14:27 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:14:32 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 14:14:32 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003550275",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "张国庆",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 14:14:32 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 14:14:32 [INFO ] extractor: [高铁票] 已解析: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 14:14:32 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:14:37 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 14:14:37 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003595208",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "王建锋",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 14:14:37 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 14:14:37 [INFO ] extractor: [高铁票] 已解析: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 14:14:37 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:14:40 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 94 字符
|
|
2026-06-08 14:14:40 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26342000001715702281",
|
|
"开票日期": "2026/6/3",
|
|
"价税合计": 536.00
|
|
}
|
|
2026-06-08 14:14:40 [INFO ] llm_extractor: LLM 发票提取成功: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 14:14:40 [INFO ] extractor: [酒店住宿] 已解析: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 14:14:40 [INFO ] extractor: 共处理 5 张发票
|
|
2026-06-08 14:14:40 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 14:14:40 [WARNING] llm_extractor: 未找到 PDF-图片配对文件，跳过信息提取
|
|
2026-06-08 14:14:40 [INFO ] fill_consumable_doc: 开始填写出库单: 易耗品、出库单.doc
|
|
2026-06-08 14:14:50 [INFO ] fill_consumable_doc: 出库单填写完成
|
|
2026-06-08 14:50:57 [INFO ] extractor: 发现 5 个 PDF 文件
|
|
2026-06-08 14:50:59 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:51:13 [ERROR] llm_extractor: LLM 请求失败: Error code: 502
|
|
2026-06-08 14:51:13 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 26349119343000331138-电子发票.pdf (Error code: 502)
|
|
2026-06-08 14:51:13 [INFO ] llm_extractor: 正则回退解析完成: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 14:51:13 [INFO ] extractor: [高铁票] 已解析: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 14:51:13 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:51:26 [ERROR] llm_extractor: LLM 请求失败: Error code: 502
|
|
2026-06-08 14:51:26 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 26349119343000335414-电子发票.pdf (Error code: 502)
|
|
2026-06-08 14:51:26 [INFO ] llm_extractor: 正则回退解析完成: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 14:51:26 [INFO ] extractor: [高铁票] 已解析: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 14:51:26 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:51:39 [ERROR] llm_extractor: LLM 请求失败: Error code: 502
|
|
2026-06-08 14:51:39 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 26349119423003550275-电子发票.pdf (Error code: 502)
|
|
2026-06-08 14:51:39 [INFO ] llm_extractor: 正则回退解析完成: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 14:51:39 [INFO ] extractor: [高铁票] 已解析: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 14:51:39 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:53:56 [INFO ] extractor: 发现 5 个 PDF 文件
|
|
2026-06-08 14:53:58 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:54:12 [ERROR] llm_extractor: LLM 请求失败: Error code: 502
|
|
2026-06-08 14:54:12 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 26349119343000331138-电子发票.pdf (Error code: 502)
|
|
2026-06-08 14:54:12 [INFO ] llm_extractor: 正则回退解析完成: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 14:54:12 [INFO ] extractor: [高铁票] 已解析: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 14:54:12 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:54:25 [ERROR] llm_extractor: LLM 请求失败: Error code: 502
|
|
2026-06-08 14:54:25 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 26349119343000335414-电子发票.pdf (Error code: 502)
|
|
2026-06-08 14:54:25 [INFO ] llm_extractor: 正则回退解析完成: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 14:54:25 [INFO ] extractor: [高铁票] 已解析: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 14:54:25 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:54:38 [ERROR] llm_extractor: LLM 请求失败: Error code: 502
|
|
2026-06-08 14:54:38 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 26349119423003550275-电子发票.pdf (Error code: 502)
|
|
2026-06-08 14:54:38 [INFO ] llm_extractor: 正则回退解析完成: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 14:54:38 [INFO ] extractor: [高铁票] 已解析: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 14:54:38 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:54:52 [ERROR] llm_extractor: LLM 请求失败: Error code: 502
|
|
2026-06-08 14:54:52 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: 26349119423003595208-电子发票.pdf (Error code: 502)
|
|
2026-06-08 14:54:52 [INFO ] llm_extractor: 正则回退解析完成: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 14:54:52 [INFO ] extractor: [高铁票] 已解析: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 14:54:52 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://127.0.0.1:1234/v1)
|
|
2026-06-08 14:55:39 [INFO ] extractor: 发现 5 个 PDF 文件
|
|
2026-06-08 14:55:41 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 14:55:54 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 14:55:54 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331138",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "张国庆",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 14:55:54 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 14:55:54 [INFO ] extractor: [高铁票] 已解析: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 14:55:54 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 14:56:02 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 14:56:02 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000335414",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "王建锋",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 14:56:02 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 14:56:02 [INFO ] extractor: [高铁票] 已解析: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 14:56:02 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 14:56:11 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 14:56:11 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003550275",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "张国庆",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 14:56:11 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 14:56:11 [INFO ] extractor: [高铁票] 已解析: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 14:56:11 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 14:56:25 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 14:56:25 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003595208",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "王建锋",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 14:56:25 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 14:56:25 [INFO ] extractor: [高铁票] 已解析: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 14:56:25 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 14:56:31 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 94 字符
|
|
2026-06-08 14:56:31 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26342000001715702281",
|
|
"开票日期": "2026/6/3",
|
|
"价税合计": 536.00
|
|
}
|
|
2026-06-08 14:56:31 [INFO ] llm_extractor: LLM 发票提取成功: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 14:56:31 [INFO ] extractor: [酒店住宿] 已解析: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 14:56:31 [INFO ] extractor: 共处理 5 张发票
|
|
2026-06-08 14:56:31 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 14:56:31 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 5 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 14:56:31 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 14:56:31 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145318_279_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 14:56:49 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145319_280_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 14:56:49 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145320_281_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 14:56:49 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145321_282_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 14:56:49 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145323_283_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 14:56:49 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145318_279_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 14:56:49 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145319_280_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 14:56:49 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145320_281_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 14:56:49 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145321_282_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 14:56:49 [WARNING] llm_extractor: LLM 多模态提取失败，回退到 OCR+正则: 微信图片_20260608145323_283_42.jpg (cannot import name 'ImageDocument' from 'llama_index.core.llms' (D:\阜阳师范大学\财务报销\自动报销系统\.venv\Lib\site-packages\llama_index\core\llms\__init__.py))
|
|
2026-06-08 14:56:49 [ERROR] llm_extractor: OCR 回退提取失败: Engine 'paddle_static' is unavailable because dependency 'paddlepaddle' is not installed.
|
|
2026-06-08 14:56:49 [INFO ] llm_extractor: LLM 提取完成: 匹配 5/5 行，更新 0 个字段
|
|
2026-06-08 14:56:49 [INFO ] fill_consumable_doc: 开始填写出库单: 易耗品、出库单.doc
|
|
2026-06-08 14:56:57 [INFO ] fill_consumable_doc: 出库单填写完成
|
|
2026-06-08 15:13:59 [INFO ] extractor: 发现 5 个 PDF 文件
|
|
2026-06-08 15:14:01 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 15:14:11 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 15:14:11 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331138",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "张国庆",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 15:14:11 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 15:14:11 [INFO ] extractor: [高铁票] 已解析: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 15:14:11 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 15:14:21 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 15:14:21 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000335414",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "王建锋",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 15:14:21 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 15:14:21 [INFO ] extractor: [高铁票] 已解析: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 15:14:21 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 15:14:30 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 15:14:30 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003550275",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "张国庆",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 15:14:30 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 15:14:30 [INFO ] extractor: [高铁票] 已解析: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 15:14:30 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 15:14:39 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 15:14:39 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003595208",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "王建锋",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 15:14:39 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 15:14:39 [INFO ] extractor: [高铁票] 已解析: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 15:14:39 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 15:14:45 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 96 字符
|
|
2026-06-08 15:14:45 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26342000001715702281",
|
|
"开票日期": "2026/6/3",
|
|
"价税合计": "536.00"
|
|
}
|
|
2026-06-08 15:14:45 [INFO ] llm_extractor: LLM 发票提取成功: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 15:14:45 [INFO ] extractor: [酒店住宿] 已解析: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 15:14:45 [INFO ] extractor: 共处理 5 张发票
|
|
2026-06-08 15:14:45 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 15:14:45 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 5 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 15:14:46 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 15:16:20 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145318_279_42.jpg
|
|
2026-06-08 15:16:20 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 15:17:35 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145319_280_42.jpg
|
|
2026-06-08 15:17:35 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 15:19:04 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145320_281_42.jpg
|
|
2026-06-08 15:19:04 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 15:20:14 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145321_282_42.jpg
|
|
2026-06-08 15:20:14 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 15:21:11 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145323_283_42.jpg
|
|
2026-06-08 15:21:11 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 15:21:11 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 15:21:11 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 15:22:26 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145318_279_42.jpg
|
|
2026-06-08 15:22:26 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 15:23:46 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145319_280_42.jpg
|
|
2026-06-08 15:23:46 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 15:24:24 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145320_281_42.jpg
|
|
2026-06-08 15:24:24 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 16:01:24 [INFO ] extractor: 发现 7 个 PDF 文件
|
|
2026-06-08 16:01:26 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:01:37 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:01:37 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331138",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "张国庆",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 16:01:37 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 16:01:37 [INFO ] extractor: [高铁票] 已解析: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 16:01:37 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:01:45 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:01:45 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331314",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "一等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "陈曙光",
|
|
"票价": "167.00"
|
|
}
|
|
2026-06-08 16:01:45 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331314-电子发票.pdf
|
|
2026-06-08 16:01:45 [INFO ] extractor: [高铁票] 已解析: 26349119343000331314-电子发票.pdf
|
|
2026-06-08 16:01:45 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:01:54 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:01:54 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000335414",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "王建锋",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 16:01:54 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 16:01:54 [INFO ] extractor: [高铁票] 已解析: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 16:01:54 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:02:02 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:02:02 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003550275",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "张国庆",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 16:02:02 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 16:02:02 [INFO ] extractor: [高铁票] 已解析: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 16:02:03 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:02:10 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:02:10 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003552366",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "一等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "陈曙光",
|
|
"票价": "189.50"
|
|
}
|
|
2026-06-08 16:02:10 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003552366-电子发票.pdf
|
|
2026-06-08 16:02:10 [INFO ] extractor: [高铁票] 已解析: 26349119423003552366-电子发票.pdf
|
|
2026-06-08 16:02:11 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:02:19 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:02:19 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003595208",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "王建锋",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 16:02:19 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 16:02:19 [INFO ] extractor: [高铁票] 已解析: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 16:02:19 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:02:23 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 94 字符
|
|
2026-06-08 16:02:23 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26342000001715702281",
|
|
"开票日期": "2026/6/3",
|
|
"价税合计": 536.00
|
|
}
|
|
2026-06-08 16:02:23 [INFO ] llm_extractor: LLM 发票提取成功: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 16:02:23 [INFO ] extractor: [酒店住宿] 已解析: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 16:02:23 [INFO ] extractor: 共处理 7 张发票
|
|
2026-06-08 16:02:23 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 16:02:23 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 7 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 16:02:24 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 16:02:26 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145318_279_42.jpg
|
|
2026-06-08 16:02:26 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 16:02:28 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145319_280_42.jpg
|
|
2026-06-08 16:02:28 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 16:02:29 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145320_281_42.jpg
|
|
2026-06-08 16:02:29 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 16:02:31 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145321_282_42.jpg
|
|
2026-06-08 16:02:31 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 16:02:33 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145323_283_42.jpg
|
|
2026-06-08 16:02:33 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 16:02:33 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 16:02:34 [INFO ] llm_extractor: LLM 提取完成: 匹配 5/7 行，更新 0 个字段
|
|
2026-06-08 16:02:34 [INFO ] fill_consumable_doc: 开始填写出库单: 易耗品、出库单.doc
|
|
2026-06-08 16:02:43 [INFO ] fill_consumable_doc: 出库单填写完成
|
|
2026-06-08 16:22:03 [INFO ] extractor: 发现 7 个 PDF 文件
|
|
2026-06-08 16:22:05 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:22:13 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:22:13 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331138",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "张国庆",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 16:22:13 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 16:22:13 [INFO ] extractor: [高铁票] 已解析: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 16:22:13 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:22:19 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:22:19 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331314",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "一等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "陈曙光",
|
|
"票价": "167.00"
|
|
}
|
|
2026-06-08 16:22:19 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331314-电子发票.pdf
|
|
2026-06-08 16:22:19 [INFO ] extractor: [高铁票] 已解析: 26349119343000331314-电子发票.pdf
|
|
2026-06-08 16:22:20 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:22:27 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:22:27 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000335414",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "王建锋",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 16:22:27 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 16:22:27 [INFO ] extractor: [高铁票] 已解析: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 16:22:27 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:22:34 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:22:34 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003550275",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "张国庆",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 16:22:34 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 16:22:34 [INFO ] extractor: [高铁票] 已解析: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 16:22:34 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:22:41 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:22:41 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003552366",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "一等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "陈曙光",
|
|
"票价": "189.50"
|
|
}
|
|
2026-06-08 16:22:41 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003552366-电子发票.pdf
|
|
2026-06-08 16:22:41 [INFO ] extractor: [高铁票] 已解析: 26349119423003552366-电子发票.pdf
|
|
2026-06-08 16:22:42 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:22:49 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:22:49 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003595208",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "王建锋",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 16:22:49 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 16:22:49 [INFO ] extractor: [高铁票] 已解析: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 16:22:49 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:22:53 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 94 字符
|
|
2026-06-08 16:22:53 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26342000001715702281",
|
|
"开票日期": "2026/6/3",
|
|
"价税合计": 536.00
|
|
}
|
|
2026-06-08 16:22:53 [INFO ] llm_extractor: LLM 发票提取成功: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 16:22:53 [INFO ] extractor: [酒店住宿] 已解析: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 16:22:53 [INFO ] extractor: 共处理 7 张发票
|
|
2026-06-08 16:22:53 [INFO ] extractor: 差旅发票: 7 张, 普通发票: 0 张
|
|
2026-06-08 16:22:53 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 16:22:53 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 7 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 16:22:54 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 16:22:56 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145318_279_42.jpg
|
|
2026-06-08 16:22:56 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 16:22:58 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145319_280_42.jpg
|
|
2026-06-08 16:22:58 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 16:22:59 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145320_281_42.jpg
|
|
2026-06-08 16:22:59 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 16:23:01 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145321_282_42.jpg
|
|
2026-06-08 16:23:01 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 16:23:03 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145323_283_42.jpg
|
|
2026-06-08 16:23:03 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 16:23:03 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 16:23:03 [INFO ] llm_extractor: LLM 提取完成: 匹配 5/7 行，更新 0 个字段
|
|
2026-06-08 16:23:03 [INFO ] fill_consumable_doc: 纯差旅发票，跳过易耗品出库单生成
|
|
2026-06-08 16:37:34 [INFO ] extractor: 发现 7 个 PDF 文件
|
|
2026-06-08 16:37:36 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:37:45 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:37:45 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331138",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "张国庆",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 16:37:45 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 16:37:45 [INFO ] extractor: [高铁票] 已解析: 26349119343000331138-电子发票.pdf
|
|
2026-06-08 16:37:45 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:37:51 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:37:51 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331314",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "一等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "陈曙光",
|
|
"票价": "167.00"
|
|
}
|
|
2026-06-08 16:37:51 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331314-电子发票.pdf
|
|
2026-06-08 16:37:51 [INFO ] extractor: [高铁票] 已解析: 26349119343000331314-电子发票.pdf
|
|
2026-06-08 16:37:51 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:37:58 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:37:58 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000335414",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "王建锋",
|
|
"票价": "115.50"
|
|
}
|
|
2026-06-08 16:37:58 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 16:37:58 [INFO ] extractor: [高铁票] 已解析: 26349119343000335414-电子发票.pdf
|
|
2026-06-08 16:37:58 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:38:04 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:38:04 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003550275",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "张国庆",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 16:38:04 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 16:38:04 [INFO ] extractor: [高铁票] 已解析: 26349119423003550275-电子发票.pdf
|
|
2026-06-08 16:38:04 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:38:11 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:38:11 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003552366",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "一等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "陈曙光",
|
|
"票价": "189.50"
|
|
}
|
|
2026-06-08 16:38:11 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003552366-电子发票.pdf
|
|
2026-06-08 16:38:11 [INFO ] extractor: [高铁票] 已解析: 26349119423003552366-电子发票.pdf
|
|
2026-06-08 16:38:11 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:38:19 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 198 字符
|
|
2026-06-08 16:38:19 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003595208",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "王建锋",
|
|
"票价": "117.50"
|
|
}
|
|
2026-06-08 16:38:19 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 16:38:19 [INFO ] extractor: [高铁票] 已解析: 26349119423003595208-电子发票.pdf
|
|
2026-06-08 16:38:19 [INFO ] llm_extractor: 开始请求 LLM (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1)
|
|
2026-06-08 16:38:23 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 96 字符
|
|
2026-06-08 16:38:23 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "酒店住宿",
|
|
"发票号码": "26342000001715702281",
|
|
"开票日期": "2026/6/3",
|
|
"价税合计": "536.00"
|
|
}
|
|
2026-06-08 16:38:23 [INFO ] llm_extractor: LLM 发票提取成功: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 16:38:23 [INFO ] extractor: [酒店住宿] 已解析: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-08 16:38:23 [INFO ] extractor: 共处理 7 张发票
|
|
2026-06-08 16:38:23 [INFO ] extractor: 差旅发票: 7 张, 普通发票: 0 张
|
|
2026-06-08 16:38:23 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-08 16:38:23 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 7 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 16:38:24 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 16:38:25 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145318_279_42.jpg
|
|
2026-06-08 16:38:25 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 16:38:27 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145319_280_42.jpg
|
|
2026-06-08 16:38:27 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 16:38:30 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145320_281_42.jpg
|
|
2026-06-08 16:38:30 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 16:38:38 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145321_282_42.jpg
|
|
2026-06-08 16:38:38 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 16:38:39 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145323_283_42.jpg
|
|
2026-06-08 16:38:39 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 16:38:39 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 16:38:39 [INFO ] llm_extractor: PDF=26349119343000331138-电子发票.pdf, 发票号=26349119343000331138, 刷卡信息={'人员姓名': '', '刷卡日期': '', '公务卡号': '', '刷卡金额': ''}
|
|
2026-06-08 16:38:39 [INFO ] llm_extractor: PDF=26349119343000331314-电子发票.pdf, 发票号=26349119343000331314, 刷卡信息={'人员姓名': '', '刷卡日期': '', '公务卡号': '', '刷卡金额': ''}
|
|
2026-06-08 16:38:40 [INFO ] llm_extractor: PDF=26349119343000335414-电子发票.pdf, 发票号=26349119343000335414, 刷卡信息={'人员姓名': '', '刷卡日期': '', '公务卡号': '', '刷卡金额': ''}
|
|
2026-06-08 16:38:40 [INFO ] llm_extractor: PDF=26349119423003550275-电子发票.pdf, 发票号=26349119423003550275, 刷卡信息={'人员姓名': '', '刷卡日期': '', '公务卡号': '', '刷卡金额': ''}
|
|
2026-06-08 16:38:40 [INFO ] llm_extractor: PDF=26349119423003552366-电子发票.pdf, 发票号=26349119423003552366, 刷卡信息={'人员姓名': '', '刷卡日期': '', '公务卡号': '', '刷卡金额': ''}
|
|
2026-06-08 16:38:40 [INFO ] llm_extractor: LLM 提取完成: 匹配 5/7 行，更新 0 个字段
|
|
2026-06-08 16:38:40 [INFO ] fill_consumable_doc: 纯差旅发票，跳过易耗品出库单生成
|
|
2026-06-08 16:45:50 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:45:50 [INFO ] pipeline: [2/3] LLM 信息提取
|
|
2026-06-08 16:45:50 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:45:50 [WARNING] llm_extractor: 未找到 PDF-图片配对文件，跳过信息提取
|
|
2026-06-08 16:45:50 [INFO ] pipeline: [2/3] LLM 信息提取 完成
|
|
2026-06-08 16:48:56 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:48:56 [INFO ] pipeline: [2/3] LLM 信息提取
|
|
2026-06-08 16:48:56 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:48:56 [WARNING] llm_extractor: 未找到 PDF-图片配对文件，跳过信息提取
|
|
2026-06-08 16:48:56 [INFO ] pipeline: [2/3] LLM 信息提取 完成
|
|
2026-06-08 16:54:29 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:54:29 [INFO ] pipeline: [2/3] LLM 信息提取
|
|
2026-06-08 16:54:29 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:54:29 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 7 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 16:54:30 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 16:54:31 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:54:31 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 16:54:31 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145319_280_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:54:31 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 16:54:31 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145320_281_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:54:31 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 16:54:31 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145321_282_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...//Z', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:54:31 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 16:54:31 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145323_283_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:54:31 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 16:54:31 [INFO ] llm_extractor: 在 uploads 会话目录找到配对: 179d55ea2a95
|
|
2026-06-08 16:54:31 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 16:54:31 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 16:54:31 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:55:39 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:55:39 [INFO ] pipeline: [2/3] LLM 信息提取
|
|
2026-06-08 16:55:39 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:55:39 [INFO ] pipeline: 使用 uploads 目录: 71dc1d795be5
|
|
2026-06-08 16:55:39 [WARNING] llm_extractor: 未找到 PDF-图片配对文件，跳过信息提取
|
|
2026-06-08 16:55:39 [INFO ] pipeline: [2/3] LLM 信息提取 完成
|
|
2026-06-08 16:56:22 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:56:22 [INFO ] pipeline: [2/3] LLM 信息提取
|
|
2026-06-08 16:56:22 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:56:22 [INFO ] pipeline: 使用 uploads 目录: 179d55ea2a95
|
|
2026-06-08 16:56:22 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 7 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 16:56:23 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 16:56:24 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:56:24 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 16:56:24 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145319_280_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:56:24 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 16:56:24 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145320_281_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:56:24 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 16:56:24 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145321_282_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...//Z', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:56:24 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 16:56:24 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145323_283_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:56:24 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 16:56:24 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 16:56:24 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 16:56:24 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:59:20 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:59:20 [INFO ] pipeline: [2/3] LLM 信息提取
|
|
2026-06-08 16:59:20 [INFO ] pipeline: ============================================================
|
|
2026-06-08 16:59:20 [INFO ] pipeline: 使用 uploads 目录: 179d55ea2a95
|
|
2026-06-08 16:59:20 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 7 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 16:59:21 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 16:59:21 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:59:21 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 16:59:21 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145319_280_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:59:21 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 16:59:21 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145320_281_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:59:21 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 16:59:21 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145321_282_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...//Z', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:59:21 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 16:59:21 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145323_283_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 16:59:21 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 16:59:21 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 16:59:21 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 16:59:21 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 17:00:34 [INFO ] pipeline: ============================================================
|
|
2026-06-08 17:00:34 [INFO ] pipeline: [2/3] LLM 信息提取
|
|
2026-06-08 17:00:34 [INFO ] pipeline: ============================================================
|
|
2026-06-08 17:00:34 [INFO ] pipeline: 使用 uploads 目录: 179d55ea2a95
|
|
2026-06-08 17:00:34 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 7 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 17:00:35 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 17:00:35 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 17:00:35 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 17:00:35 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145319_280_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 17:00:35 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 17:00:35 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145320_281_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 17:00:35 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 17:00:35 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145321_282_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...//Z', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 17:00:35 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 17:00:35 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145323_283_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 17:00:35 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 17:00:35 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 17:00:35 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 17:00:35 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (2 validation errors for ChatMessage
|
|
blocks.0
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'text', 'text': ...提取刷卡信息。'}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found
|
|
blocks.1
|
|
Unable to extract tag using discriminator 'block_type' [type=union_tag_not_found, input_value={'type': 'image_url', 'im...9k=', 'detail': 'high'}}, input_type=dict]
|
|
For further information visit https://errors.pydantic.dev/2.13/v/union_tag_not_found)
|
|
2026-06-08 17:03:44 [INFO ] pipeline: ============================================================
|
|
2026-06-08 17:03:44 [INFO ] pipeline: [2/3] LLM 信息提取
|
|
2026-06-08 17:03:44 [INFO ] pipeline: ============================================================
|
|
2026-06-08 17:03:44 [INFO ] pipeline: 使用 uploads 目录: 179d55ea2a95
|
|
2026-06-08 17:03:44 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 7 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-08 17:03:45 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-08 17:03:54 [INFO ] llm_extractor: LLM 多模态原始响应: {
|
|
"人员姓名": "",
|
|
"刷卡日期": "2026/6/1",
|
|
"公务卡号": "6282****1682",
|
|
"刷卡金额": "231.00"
|
|
}
|
|
2026-06-08 17:03:54 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145318_279_42.jpg, 结果: {'人员姓名': '', '刷卡日期': '2026/6/1', '公务卡号': '6282****1682', '刷卡金额': '231.00'}
|
|
2026-06-08 17:03:54 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-08 17:04:02 [INFO ] llm_extractor: LLM 多模态原始响应: {
|
|
"人员姓名": "",
|
|
"刷卡日期": "2026/6/1",
|
|
"公务卡号": "6282****1682",
|
|
"刷卡金额": "167.00"
|
|
}
|
|
2026-06-08 17:04:02 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145319_280_42.jpg, 结果: {'人员姓名': '', '刷卡日期': '2026/6/1', '公务卡号': '6282****1682', '刷卡金额': '167.00'}
|
|
2026-06-08 17:04:02 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-08 17:04:09 [INFO ] llm_extractor: LLM 多模态原始响应: {
|
|
"人员姓名": "",
|
|
"刷卡日期": "2026/6/2",
|
|
"公务卡号": "6282****1682",
|
|
"刷卡金额": "535.86"
|
|
}
|
|
2026-06-08 17:04:09 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145320_281_42.jpg, 结果: {'人员姓名': '', '刷卡日期': '2026/6/2', '公务卡号': '6282****1682', '刷卡金额': '535.86'}
|
|
2026-06-08 17:04:09 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-08 17:04:16 [INFO ] llm_extractor: LLM 多模态原始响应: {
|
|
"人员姓名": "",
|
|
"刷卡日期": "2026/6/3",
|
|
"公务卡号": "6282****1682",
|
|
"刷卡金额": "189.50"
|
|
}
|
|
2026-06-08 17:04:16 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145321_282_42.jpg, 结果: {'人员姓名': '', '刷卡日期': '2026/6/3', '公务卡号': '6282****1682', '刷卡金额': '189.50'}
|
|
2026-06-08 17:04:16 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen/qwen3.6-27b, base=http://100.123.83.113:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: LLM 多模态原始响应: {
|
|
"人员姓名": "",
|
|
"刷卡日期": "2026/6/3",
|
|
"公务卡号": "6282****1682",
|
|
"刷卡金额": "235.00"
|
|
}
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: LLM 刷卡信息提取成功: 微信图片_20260608145323_283_42.jpg, 结果: {'人员姓名': '', '刷卡日期': '2026/6/3', '公务卡号': '6282****1682', '刷卡金额': '235.00'}
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: PDF=dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf, 发票号=26342000001715702281, 刷卡信息={'人员姓名': '', '刷卡日期': '2026/6/2', '公务卡号': '6282****1682', '刷卡金额': '535.86'}
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: PDF=26349119343000331138-电子发票.pdf, 发票号=26349119343000331138, 刷卡信息={'人员姓名': '', '刷卡日期': '2026/6/1', '公务卡号': '6282****1682', '刷卡金额': '231.00'}
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: PDF=26349119343000331314-电子发票.pdf, 发票号=26349119343000331314, 刷卡信息={'人员姓名': '', '刷卡日期': '2026/6/1', '公务卡号': '6282****1682', '刷卡金额': '167.00'}
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: PDF=26349119343000335414-电子发票.pdf, 发票号=26349119343000335414, 刷卡信息={'人员姓名': '', '刷卡日期': '2026/6/3', '公务卡号': '6282****1682', '刷卡金额': '189.50'}
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: PDF=26349119423003550275-电子发票.pdf, 发票号=26349119423003550275, 刷卡信息={'人员姓名': '', '刷卡日期': '2026/6/3', '公务卡号': '6282****1682', '刷卡金额': '235.00'}
|
|
2026-06-08 17:04:26 [INFO ] llm_extractor: LLM 提取完成: 匹配 5/7 行，更新 15 个字段
|
|
2026-06-08 17:04:26 [INFO ] pipeline: [2/3] LLM 信息提取 完成
|
|
2026-06-09 11:20:44 [INFO ] extractor: 发现 7 个 PDF 文件
|
|
2026-06-09 11:20:52 [INFO ] llm_extractor: 开始请求 LLM (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1)
|
|
2026-06-09 11:21:28 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 200 字符
|
|
2026-06-09 11:21:28 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331138",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "张国庆",
|
|
"票价": "115.50"
|
|
}
|
|
|
|
|
|
2026-06-09 11:21:28 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331138-电子发票.pdf
|
|
2026-06-09 11:21:28 [INFO ] extractor: [高铁票] 已解析: 26349119343000331138-电子发票.pdf
|
|
2026-06-09 11:21:28 [INFO ] llm_extractor: 开始请求 LLM (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1)
|
|
2026-06-09 11:22:02 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 200 字符
|
|
2026-06-09 11:22:02 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000331314",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "一等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "陈曙光",
|
|
"票价": "167.00"
|
|
}
|
|
|
|
|
|
2026-06-09 11:22:02 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000331314-电子发票.pdf
|
|
2026-06-09 11:22:02 [INFO ] extractor: [高铁票] 已解析: 26349119343000331314-电子发票.pdf
|
|
2026-06-09 11:22:02 [INFO ] llm_extractor: 开始请求 LLM (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1)
|
|
2026-06-09 11:22:36 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 200 字符
|
|
2026-06-09 11:22:36 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119343000335414",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/2",
|
|
"出发站": "阜阳西",
|
|
"到达站": "合肥南",
|
|
"座位等级": "二等座",
|
|
"车次": "G1967",
|
|
"人员姓名": "王建锋",
|
|
"票价": "115.50"
|
|
}
|
|
|
|
|
|
2026-06-09 11:22:36 [INFO ] llm_extractor: LLM 发票提取成功: 26349119343000335414-电子发票.pdf
|
|
2026-06-09 11:22:36 [INFO ] extractor: [高铁票] 已解析: 26349119343000335414-电子发票.pdf
|
|
2026-06-09 11:22:36 [INFO ] llm_extractor: 开始请求 LLM (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1)
|
|
2026-06-09 11:23:09 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 200 字符
|
|
2026-06-09 11:23:09 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003550275",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "张国庆",
|
|
"票价": "117.50"
|
|
}
|
|
|
|
|
|
2026-06-09 11:23:09 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003550275-电子发票.pdf
|
|
2026-06-09 11:23:09 [INFO ] extractor: [高铁票] 已解析: 26349119423003550275-电子发票.pdf
|
|
2026-06-09 11:23:09 [INFO ] llm_extractor: 开始请求 LLM (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1)
|
|
2026-06-09 11:23:42 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 200 字符
|
|
2026-06-09 11:23:42 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003552366",
|
|
"开票日期": "2026/6/3",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "一等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "陈曙光",
|
|
"票价": "189.50"
|
|
}
|
|
|
|
|
|
2026-06-09 11:23:42 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003552366-电子发票.pdf
|
|
2026-06-09 11:23:42 [INFO ] extractor: [高铁票] 已解析: 26349119423003552366-电子发票.pdf
|
|
2026-06-09 11:23:42 [INFO ] llm_extractor: 开始请求 LLM (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1)
|
|
2026-06-09 11:24:15 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 200 字符
|
|
2026-06-09 11:24:15 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "高铁票",
|
|
"发票号码": "26349119423003595208",
|
|
"开票日期": "2026/6/5",
|
|
"乘车日期": "2026/6/3",
|
|
"出发站": "合肥南",
|
|
"到达站": "阜阳西",
|
|
"座位等级": "二等座",
|
|
"车次": "G1318",
|
|
"人员姓名": "王建锋",
|
|
"票价": "117.50"
|
|
}
|
|
|
|
|
|
2026-06-09 11:24:15 [INFO ] llm_extractor: LLM 发票提取成功: 26349119423003595208-电子发票.pdf
|
|
2026-06-09 11:24:15 [INFO ] extractor: [高铁票] 已解析: 26349119423003595208-电子发票.pdf
|
|
2026-06-09 11:24:15 [INFO ] llm_extractor: 开始请求 LLM (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1)
|
|
2026-06-09 11:24:45 [INFO ] llm_extractor: LLM 请求完成，响应总长度: 154 字符
|
|
2026-06-09 11:24:45 [INFO ] llm_extractor: LLM 响应: {
|
|
"发票类型": "普通发票",
|
|
"发票号码": "26342000001715702281",
|
|
"开票日期": "2026/6/3",
|
|
"项目名称": "*生产生活服务*住宿服务",
|
|
"规格型号": "",
|
|
"价税合计": "536.00",
|
|
"销售方名称": "安徽栢景酒店
|
|
2026-06-09 11:24:45 [WARNING] llm_extractor: LLM 发票提取失败，回退到正则解析: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf (Unterminated string starting at: line 8 column 12 (char 147))
|
|
2026-06-09 11:24:45 [INFO ] llm_extractor: 正则回退解析完成: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-09 11:24:45 [INFO ] extractor: [普通发票] 已解析: dzfp_26342000001715702281_阜阳师范大学_20260603111046.pdf
|
|
2026-06-09 11:24:45 [INFO ] extractor: 共处理 7 张发票
|
|
2026-06-09 11:24:45 [INFO ] extractor: 差旅发票: 6 张, 普通发票: 1 张
|
|
2026-06-09 11:24:45 [INFO ] extractor: CSV 已保存: invoice_summary.csv
|
|
2026-06-09 11:24:45 [INFO ] llm_extractor: 文件名匹配 0 组，剩余 7 个 PDF、5 张图片，尝试金额匹配...
|
|
2026-06-09 11:24:45 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-09 11:24:47 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (request (2067 tokens) exceeds the available context size (768 tokens), try increasing it)
|
|
2026-06-09 11:24:47 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1, image=微信图片_20260608145319_280_42.jpg)
|
|
2026-06-09 11:24:48 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145319_280_42.jpg (request (2067 tokens) exceeds the available context size (768 tokens), try increasing it)
|
|
2026-06-09 11:24:48 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1, image=微信图片_20260608145320_281_42.jpg)
|
|
2026-06-09 11:24:50 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145320_281_42.jpg (request (2067 tokens) exceeds the available context size (768 tokens), try increasing it)
|
|
2026-06-09 11:24:50 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1, image=微信图片_20260608145321_282_42.jpg)
|
|
2026-06-09 11:24:51 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145321_282_42.jpg (request (2067 tokens) exceeds the available context size (768 tokens), try increasing it)
|
|
2026-06-09 11:24:51 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1, image=微信图片_20260608145323_283_42.jpg)
|
|
2026-06-09 11:24:52 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145323_283_42.jpg (request (2067 tokens) exceeds the available context size (768 tokens), try increasing it)
|
|
2026-06-09 11:24:52 [INFO ] llm_extractor: 金额匹配完成，共 5 组配对
|
|
2026-06-09 11:24:52 [INFO ] llm_extractor: 找到 5 组 PDF-图片配对
|
|
2026-06-09 11:24:52 [INFO ] llm_extractor: 开始多模态 LLM 请求 (model=qwen3.5-9b, base=http://100.123.83.115:1234/v1, image=微信图片_20260608145318_279_42.jpg)
|
|
2026-06-09 11:24:54 [ERROR] llm_extractor: LLM 多模态提取失败: 微信图片_20260608145318_279_42.jpg (request (2067 tokens) exceeds the available context size (768 tokens), try increasing it)
|