feat(extraction): add deduplication limit parameter to YAKE extractor

2026-07-24 11:38:51 -04:00
parent 68c9693711
commit 31ecad881f
2 changed files with 9 additions and 3 deletions
@@ -92,6 +92,7 @@ class EbookSearchConfig(BaseSettings):
    phrase_max_tokens: int = 5
    phrase_max_entity_tokens: int = 8
    phrase_yake_top_k: int = 1000
+    phrase_yake_dedup_limit: float = 0.85
    phrase_raw_ngram_min_count: int = 2
    phrase_raw_count_score_threshold: int = 3
    phrase_raw_count_high_score_threshold: int = 10