feat: add configurable search parameters for RAG, knowledge, and memory (#3531)

- Add limit and score_threshold to BaseRagConfig, propagate to clients  
- Update default search params in RAG storage, knowledge, and memory (limit=5, threshold=0.6)  
- Fix linting (ruff, mypy, PERF203) and refactor save logic  
- Update tests for new defaults and ChromaDB behavior

src/crewai/knowledge/knowledge.py

@@ -43,7 +43,7 @@ class Knowledge(BaseModel):
         self.sources = sources
 
     def query(
-        self, query: list[str], results_limit: int = 3, score_threshold: float = 0.35
+        self, query: list[str], results_limit: int = 5, score_threshold: float = 0.6
     ) -> list[SearchResult]:
         """
         Query across all knowledge sources to find the most relevant information.

src/crewai/knowledge/knowledge_config.py

@@ -9,8 +9,8 @@ class KnowledgeConfig(BaseModel):
         score_threshold (float): The minimum score for a document to be considered relevant.
     """
 
-    results_limit: int = Field(default=3, description="The number of results to return")
+    results_limit: int = Field(default=5, description="The number of results to return")
     score_threshold: float = Field(
-        default=0.35,
+        default=0.6,
         description="The minimum score for a result to be considered relevant",
     )

src/crewai/knowledge/storage/base_knowledge_storage.py

@@ -11,9 +11,9 @@ class BaseKnowledgeStorage(ABC):
     def search(
         self,
         query: list[str],
-        limit: int = 3,
+        limit: int = 5,
         metadata_filter: dict[str, Any] | None = None,
-        score_threshold: float = 0.35,
+        score_threshold: float = 0.6,
     ) -> list[SearchResult]:
         """Search for documents in the knowledge base."""
 

src/crewai/knowledge/storage/knowledge_storage.py

@@ -1,4 +1,5 @@
 import logging
+import traceback
 import warnings
 from typing import Any, cast
 
@@ -49,9 +50,9 @@ class KnowledgeStorage(BaseKnowledgeStorage):
     def search(
         self,
         query: list[str],
-        limit: int = 3,
+        limit: int = 5,
         metadata_filter: dict[str, Any] | None = None,
-        score_threshold: float = 0.35,
+        score_threshold: float = 0.6,
     ) -> list[SearchResult]:
         try:
             if not query:
@@ -73,7 +74,9 @@ class KnowledgeStorage(BaseKnowledgeStorage):
                 score_threshold=score_threshold,
             )
         except Exception as e:
-            logging.error(f"Error during knowledge search: {e!s}")
+            logging.error(
+                f"Error during knowledge search: {e!s}\n{traceback.format_exc()}"
+            )
             return []
 
     def reset(self) -> None:
@@ -86,7 +89,9 @@ class KnowledgeStorage(BaseKnowledgeStorage):
             )
             client.delete_collection(collection_name=collection_name)
         except Exception as e:
-            logging.error(f"Error during knowledge reset: {e!s}")
+            logging.error(
+                f"Error during knowledge reset: {e!s}\n{traceback.format_exc()}"
+            )
 
     def save(self, documents: list[str]) -> None:
         try: