diff --git a/README.md b/README.md index e97f84ea..47d10183 100644 --- a/README.md +++ b/README.md @@ -28,6 +28,7 @@ Ask DeepWiki Trust Score ClawHub Skill + MCP Toplist

@@ -96,7 +97,7 @@ Need a **production-grade data quality platform**? Try [Dingo SaaS](https://ding ### 📝 How to Get Free SaaS Code -👉 **[Apply for Dingo SaaS Repository Access](https://aicarrier.feishu.cn/share/base/form/shrcnr19E0upfiA92Wm5i2eic7g)** +👉 **[Apply for Dingo SaaS Repository Access](https://aicarrier.feishu.cn/share/base/form/shrcn9RqYttByQ5H1np6Yrnmhuf)** Review time: 1-5 business days | Suitable for enterprise data governance, team collaboration diff --git a/README_ja.md b/README_ja.md index 948a16f6..4d7b3f33 100644 --- a/README_ja.md +++ b/README_ja.md @@ -95,7 +95,7 @@ ### 📝 無料 SaaS コードの入手方法 -👉 **[Dingo SaaS リポジトリアクセスを申請する](https://aicarrier.feishu.cn/share/base/form/shrcnr19E0upfiA92Wm5i2eic7g)** +👉 **[Dingo SaaS リポジトリアクセスを申請する](https://aicarrier.feishu.cn/share/base/form/shrcn9RqYttByQ5H1np6Yrnmhuf)** 審査時間：1-5営業日 | エンタープライズデータガバナンス、チームコラボレーションに最適 diff --git a/dingo/model/rule/rule_common.py b/dingo/model/rule/rule_common.py index 75d3d0db..4ece8495 100644 --- a/dingo/model/rule/rule_common.py +++ b/dingo/model/rule/rule_common.py @@ -171,20 +171,19 @@ class RuleAudioDataFormat(BaseRule): "category": "Rule-Based TEXT Quality Metrics", "quality_dimension": "EFFECTIVENESS", "metric_name": "RuleAudioDataFormat", - "description": "Check whether the audio data format is right", + "description": "Check whether the audio data format is right, include id, audio, text fields", "evaluation_results": "" } - _required_fields = [RequiredField.CONTENT] dynamic_config = EvaluatorRuleArgs() @classmethod def eval(cls, input_data: Data) -> EvalDetail: res = EvalDetail(metric=cls.__name__) - raw_data = input_data.raw_data + record = input_data.to_dict() key_list = ["id", "audio", "text"] - if all(key in raw_data for key in key_list): + if all(key in record for key in key_list): res.label = [QualityLabel.QUALITY_GOOD] else: res.status = True @@ -1305,20 +1304,19 @@ class RuleImageDataFormat(BaseRule): "category": "Rule-Based TEXT Quality Metrics", "quality_dimension": "EFFECTIVENESS", "metric_name": "RuleImageDataFormat", - "description": "Check whether the image data format is right", + "description": "Check whether the image data format is right, include img_id, image fields", "evaluation_results": "" } - _required_fields = [RequiredField.CONTENT] dynamic_config = EvaluatorRuleArgs() @classmethod def eval(cls, input_data: Data) -> EvalDetail: res = EvalDetail(metric=cls.__name__) - raw_data = input_data.raw_data + record = input_data.to_dict() key_list = ["img_id", "image"] - if all(key in raw_data for key in key_list): + if all(key in record for key in key_list): res.label = [QualityLabel.QUALITY_GOOD] else: res.status = True @@ -1655,20 +1653,19 @@ class RuleNlpDataFormat(BaseRule): "category": "Rule-Based TEXT Quality Metrics", "quality_dimension": "EFFECTIVENESS", "metric_name": "RuleNlpDataFormat", - "description": "Check whether the nlp data format is right", + "description": "Check whether the nlp data format is right, include track_id, content fields", "evaluation_results": "" } - _required_fields = [RequiredField.CONTENT] dynamic_config = EvaluatorRuleArgs() @classmethod def eval(cls, input_data: Data) -> EvalDetail: res = EvalDetail(metric=cls.__name__) - raw_data = input_data.raw_data + record = input_data.to_dict() key_list = ["track_id", "content"] - if all(key in raw_data for key in key_list): + if all(key in record for key in key_list): res.label = [QualityLabel.QUALITY_GOOD] else: res.status = True @@ -1826,20 +1823,19 @@ class RuleSftDataFormat(BaseRule): "category": "Rule-Based TEXT Quality Metrics", "quality_dimension": "EFFECTIVENESS", "metric_name": "RuleSftDataFormat", - "description": "Check whether the sft data format is right", + "description": "Check whether the sft data format is right, include track_id, type, prompt, completion fields", "evaluation_results": "" } - _required_fields = [RequiredField.CONTENT] dynamic_config = EvaluatorRuleArgs() @classmethod def eval(cls, input_data: Data) -> EvalDetail: res = EvalDetail(metric=cls.__name__) - raw_data = input_data.raw_data + record = input_data.to_dict() key_list = ["track_id", "type", "prompt", "completion"] - if all(key in raw_data for key in key_list): + if all(key in record for key in key_list): res.label = [QualityLabel.QUALITY_GOOD] else: res.status = True @@ -2204,19 +2200,17 @@ class RuleVedioDataFormat(BaseRule): "category": "Rule-Based TEXT Quality Metrics", "quality_dimension": "EFFECTIVENESS", "metric_name": "RuleVedioDataFormat", - "description": "Check whether the vedio data format is right", + "description": "Check whether the vedio data format is right, include id, video, text fields", "evaluation_results": "" } dynamic_config = EvaluatorRuleArgs() - _required_fields = [RequiredField.CONTENT] - @classmethod def eval(cls, input_data: Data) -> EvalDetail: res = EvalDetail(metric=cls.__name__) - raw_data = input_data.raw_data + record = input_data.to_dict() key_list = ["id", "video", "text"] - if all(key in raw_data for key in key_list): + if all(key in record for key in key_list): res.label = [QualityLabel.QUALITY_GOOD] else: res.status = True diff --git a/docs/assets/wechat.jpg b/docs/assets/wechat.jpg index ff95c6c6..07a463ca 100644 Binary files a/docs/assets/wechat.jpg and b/docs/assets/wechat.jpg differ