fix(rerank): derive the doc cap from tokens (measured floor 1.92), cap the query (#24)

2026-09-10 22:00:30 -04:00
parent 0eb8ad0db6
commit 4de5aaa02f
2 changed files with 31 additions and 8 deletions
@@ -124,7 +124,7 @@ class HybridRerankRetriever:

    def __init__(self, collection, bm25, rerank_url: str,
                 pool: int = 50, rerank_pool: int = 50,
-                 rrf_k: int = 60, doc_max_chars: int = 2000,
+                 rrf_k: int = 60, doc_max_chars: int = 1523,
                 timeout: float = 30.0):
        self.col = collection
        self.bm25 = bm25