diff --git a/api/db/services/task_service.py b/api/db/services/task_service.py index c8202dd4f..3975c0ec3 100644 --- a/api/db/services/task_service.py +++ b/api/db/services/task_service.py @@ -121,13 +121,6 @@ class TaskService(CommonService): .where(cls.model.id == task_id) ) docs = list(docs.dicts()) - # Assuming docs = list(docs.dicts()) - if docs: - kb_config = docs[0]['kb_parser_config'] # Dict from Knowledgebase.parser_config - mineru_method = kb_config.get('mineru_parse_method', 'auto') - mineru_formula = kb_config.get('mineru_formula_enable', True) - mineru_table = kb_config.get('mineru_table_enable', True) - print(mineru_method, mineru_formula, mineru_table) if not docs: return None diff --git a/rag/flow/hierarchical_merger/hierarchical_merger.py b/rag/flow/hierarchical_merger/hierarchical_merger.py index 34e20ed0e..f7216183b 100644 --- a/rag/flow/hierarchical_merger/hierarchical_merger.py +++ b/rag/flow/hierarchical_merger/hierarchical_merger.py @@ -143,8 +143,6 @@ class HierarchicalMerger(ProcessBase): if depth == self._param.hierarchy: all_pathes.append(_path) - for i in range(len(lines)): - print(i, lines[i]) dfs(root, [], 0) if root["texts"]: diff --git a/web/src/locales/zh-traditional.ts b/web/src/locales/zh-traditional.ts index 8113ca549..30dcde85d 100644 --- a/web/src/locales/zh-traditional.ts +++ b/web/src/locales/zh-traditional.ts @@ -202,6 +202,9 @@ export default { theDocumentBeingParsedCannotBeDeleted: '正在解析的文檔不能被刪除', }, knowledgeConfiguration: { + settings: '設置', + autoMetadataTip: + '自動生成元數據。適用於解析新文件。現有文件需要重新解析才能更新( chunk 將保留)。請注意,配置中指定的索引模型將消耗額外的 Token。', titleDescription: '在這裡更新您的知識庫詳細信息,尤其是切片方法。', imageTableContextWindow: '影像與表格上下文視窗', imageTableContextWindowTip: @@ -370,7 +373,8 @@ export default { paddleocrOptions: 'PaddleOCR 選項', paddleocrApiUrl: 'PaddleOCR API URL', paddleocrApiUrlTip: 'PaddleOCR 服務的 API 端點 URL', - paddleocrApiUrlPlaceholder: '例如:https://paddleocr-server.com/layout-parsing', + paddleocrApiUrlPlaceholder: + '例如:https://paddleocr-server.com/layout-parsing', paddleocrAccessToken: 'AI Studio 訪問令牌', paddleocrAccessTokenTip: 'PaddleOCR API 的訪問令牌(可選)', paddleocrAccessTokenPlaceholder: '您的 AI Studio 令牌(可選)', @@ -664,7 +668,7 @@ export default { selectAlgorithm: '選擇演算法', modelNamePlaceholder: '例如:paddleocr-from-env-1', modelNameRequired: '模型名稱為必填項目', - apiUrlRequired: 'PaddleOCR API URL 為必填項目' + apiUrlRequired: 'PaddleOCR API URL 為必填項目', }, ollamaLink: '如何集成 {{name}}', FishAudioLink: '如何使用Fish Audio', diff --git a/web/src/locales/zh.ts b/web/src/locales/zh.ts index 9abca9ded..a92294361 100644 --- a/web/src/locales/zh.ts +++ b/web/src/locales/zh.ts @@ -377,6 +377,8 @@ export default { }, knowledgeConfiguration: { settings: '设置', + autoMetadataTip: + '自动生成元数据。适用于解析新文件。现有文件需要重新解析才能更新(chunk将保留)。请注意,配置中指定的索引模型将消耗额外的 Token。', imageTableContextWindow: '图像与表格上下文窗口', imageTableContextWindowTip: '抓取图像与表格上下方的 N 个 token,为该 chunk 提供更丰富的背景上下文。', @@ -393,7 +395,8 @@ export default { paddleocrOptions: 'PaddleOCR 选项', paddleocrApiUrl: 'PaddleOCR API URL', paddleocrApiUrlTip: 'PaddleOCR 服务的 API 端点 URL', - paddleocrApiUrlPlaceholder: '例如:https://paddleocr-server.com/layout-parsing', + paddleocrApiUrlPlaceholder: + '例如:https://paddleocr-server.com/layout-parsing', paddleocrAccessToken: 'AI Studio 访问令牌', paddleocrAccessTokenTip: 'PaddleOCR API 的访问令牌(可选)', paddleocrAccessTokenPlaceholder: '您的 AI Studio 令牌(可选)', @@ -1133,7 +1136,7 @@ General:实体和关系提取提示来自 GitHub - microsoft/graphrag:基于 selectAlgorithm: '选择算法', modelNamePlaceholder: '例如:paddleocr-from-env-1', modelNameRequired: '模型名称为必填项', - apiUrlRequired: 'PaddleOCR API URL 为必填项' + apiUrlRequired: 'PaddleOCR API URL 为必填项', }, }, message: {