From e95e8e1a974ebee12ba42a21387fd7ecc7d8fec9 Mon Sep 17 00:00:00 2001
From: Chris Murphy <chris.murphy@klaviyo.com>
Date: Mon, 1 Dec 2025 16:16:31 -0500
Subject: [PATCH] generalized query in ContentRelevanceFilter to be a str or
 list

---
 crawl4ai/deep_crawling/filters.py | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/crawl4ai/deep_crawling/filters.py b/crawl4ai/deep_crawling/filters.py
index 981cbcd8..c075cb7d 100644
--- a/crawl4ai/deep_crawling/filters.py
+++ b/crawl4ai/deep_crawling/filters.py
@@ -509,18 +509,22 @@ class DomainFilter(URLFilter):
 class ContentRelevanceFilter(URLFilter):
     """BM25-based relevance filter using head section content"""
 
-    __slots__ = ("query_terms", "threshold", "k1", "b", "avgdl")
+    __slots__ = ("query_terms", "threshold", "k1", "b", "avgdl", "query")
 
     def __init__(
         self,
-        query: str,
+        query: Union[str, List[str]],
         threshold: float,
         k1: float = 1.2,
         b: float = 0.75,
         avgdl: int = 1000,
     ):
         super().__init__(name="BM25RelevanceFilter")
-        self.query_terms = self._tokenize(query)
+        if isinstance(query, list):
+            self.query = " ".join(query)
+        else:
+            self.query = query
+        self.query_terms = self._tokenize(self.query)
         self.threshold = threshold
         self.k1 = k1  # TF saturation parameter
         self.b = b  # Length normalization parameter