refactor: unify rag storage with instance-specific client support (#3455)

- ignore line length errors globally
- migrate knowledge/memory and crew query_knowledge to `SearchResult`
- remove legacy chromadb utils; fix empty metadata handling
- restore openai as default embedding provider; support instance-specific clients
- update and fix tests for `SearchResult` migration and rag changes

src/crewai/knowledge/utils/knowledge_utils.py

@@ -1,12 +1,12 @@
-from typing import Any, Dict, List
+from crewai.rag.types import SearchResult
 
 
-def extract_knowledge_context(knowledge_snippets: List[Dict[str, Any]]) -> str:
+def extract_knowledge_context(knowledge_snippets: list[SearchResult]) -> str:
     """Extract knowledge from the task prompt."""
     valid_snippets = [
-        result["context"]
+        result["content"]
         for result in knowledge_snippets
-        if result and result.get("context")
+        if result and result.get("content")
     ]
     snippet = "\n".join(valid_snippets)
     return f"Additional Information: {snippet}" if valid_snippets else ""