feat: add NER annotation step and integrate into pipeline

2025-08-11 07:13:09 +02:00
parent 6d39c3afc1
commit d5a4aaaf4a
23 changed files with 1108 additions and 160 deletions
@@ -19,7 +19,7 @@ class PipelineMonitor:

        self.paths = paths
        self.checkpoint_dir = paths.checkpoints_dir
-        self.steps = ["data_cleaning", "feature_extraction", "llm_annotation", "data_splitting"]
+        self.steps = ["data_cleaning", "feature_extraction", "ner_annotation", "llm_annotation", "data_splitting"]

    def get_step_status(self, step_name: str) -> Dict:
        """Get status of a specific pipeline step"""