perf: use the orjson codec to parse Oracle vector metadata (#27813)

`_json_to_metadata` parses the metadata of every result row returned by search and get. It now goes through `JSONCodec`, which selects orjson when `ENABLE_ORJSON` is set.

The text it parses is produced by Oracle's own `JSON_SERIALIZE`, and the column is a native `JSON` type, so the database normalises whatever was written and the reader never depends on the writer's escaping.

The matching `_metadata_to_json` write deliberately keeps stdlib `json`: it passes `default=self._decimal_handler`, orjson accepts none of stdlib's keyword arguments, and dropping the handler would turn a currently successful insert of a `Decimal` into a hard failure. The read side has no such constraint.

With `ENABLE_ORJSON` unset, which is the default, `JSONCodec` is stdlib `json` and this call site behaves exactly as before.

backend/open_webui/retrieval/vector/dbs/oracle23ai.py

@@ -56,6 +56,7 @@ from open_webui.retrieval.vector.main import (
     VectorDBBase,
     VectorItem,
 )
+from open_webui.utils.json_codec import JSONCodec
 
 log = logging.getLogger(__name__)
 
@@ -390,7 +391,7 @@ class Oracle23aiClient(VectorDBBase):
         Returns:
             Dict: Metadata dictionary
         """
-        return json.loads(json_str) if json_str else {}
+        return JSONCodec.loads(json_str) if json_str else {}
 
     def insert(self, collection_name: str, items: List[VectorItem]) -> None:
         """