{
"event": "PreToolUse",
"tool_name": "Grep",
"tool_input": {
"pattern": "def (extract_entities|extract_relations|classify_taxonomy|classify_ontology|link_chunk_entities|analyze_document)",
"path": "\/var\/www\/scripts\/pipeline",
"output_mode": "content"
}
}
{
"tool_response": {
"mode": "content",
"numFiles": 0,
"filenames": [],
"content": "knowledge\/entity_extractor.py:21: def extract_entities(self, text: str, level: KnowledgeLevel, source_id: int) -> list[dict]:\nknowledge\/analyzer.py:47: def extract_entities(self, text: str, level: KnowledgeLevel, source_id: int) -> list[dict]:\nknowledge\/analyzer.py:101: def analyze_document(self, document_id: int, text: str) -> dict:\nanalyzers\/relation_extractor.py:19:def extract_relations(text: str, entities: list[dict], client=None) -> list[dict]:\nanalyzers\/entity_extractor.py:159:def extract_entities_ollama(text: str, model: str = \"gemma3:27b-it-qat\") -> list[dict]:\nanalyzers\/entity_extractor.py:304:def extract_entities_anthropic(text: str, client) -> list[dict]:\nanalyzers\/statement_analyzer.py:233:def analyze_document_statements(document_id: int, client=None, progress=None) -> int:\nanalyzers\/document_analyzer.py:20:def analyze_document(document_id: int, text: str, use_anthropic: bool = True, progress=None) -> dict:\nanalyzers\/document_analyzer.py:165:def link_chunk_entities(document_id: int) -> int:\nanalyzers\/taxonomy_classifier.py:19:def classify_taxonomy(text: str, client=None) -> dict:\nvision.py:131:def analyze_document(file_path, model=DEFAULT_VISION_MODEL, store_images=False, image_dir=None, progress=None):\nquality_test.py:90:def extract_entities(text, model_name, model_id, client=None):\nquality_test.py:132:def classify_taxonomy(text, model_name, model_id, client=None):",
"numLines": 13
}
}