refac: use MilvusClient instead of deprecated ORM-style PyMilvus APIs (#27521)

* refac: use MilvusClient instead of deprecated ORM-style PyMilvus APIs

PyMilvus 2.6 emits a PyMilvusDeprecationWarning for every ORM-style call (`connections.connect`, `utility.*`, `Collection` and its methods) and will remove those APIs in PyMilvus 3.1. Both Milvus backends still used them, so a running instance floods its logs with deprecation warnings during indexing and retrieval, and would break outright once PyMilvus 3.1 lands.

Both vector clients now go through `MilvusClient`:
- `milvus_multitenancy.py`: collection creation, index creation, has_collection, insert, search, query iteration, delete and reset.
- `milvus.py`: the remaining ORM calls in `query()` (`connections.connect`, `Collection(...).load()`, `Collection.query_iterator`), plus the now-unused `FieldSchema` import.

Behaviour is unchanged: same schema, same index parameters and the same two-step scalar-index fallback, same filter expressions, same result shapes. Verified against embedded Milvus (milvus-lite, pymilvus 2.6.14) with a functional harness over both clients: insert, get, query by string/int/bool metadata filters, vector search, tenant isolation, oversized-text truncation, delete by id and by filter, delete_collection and reset all return identical results before and after, while the deprecation warnings drop from 57 to 0 for the multi-tenancy client and from 16 to 0 for the standard one.

One Milvus Lite nuance worth recording: `MilvusClient` sends index build parameters (`M`, `efConstruction`, `nlist`) as flat keys rather than as a nested `params` blob. A Milvus server accepts both forms, Milvus Lite only reads the nested one, so those tuning values are ignored on Lite. `MilvusClient` offers no way to send the nested form, and `milvus.py` already built its index parameters this way, so both backends are now consistent.

Fixes #26978

* refac: correct the Milvus scalar-index comment

The comment claimed that embedded Milvus Lite requires an explicit scalar index type. It does not: Milvus Lite rejects `create_index` on a VARCHAR field outright ("create_index only supports vector fields"), for every index type and with or without a metric type, so neither the parameterless call nor the explicit INVERTED fallback can succeed there. Filtered queries on `resource_id` still work on Lite, just unindexed.

Only the accurate half is kept, which is the reason the parameterless call is deliberate rather than an omission.

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

@@ -25,7 +25,7 @@ from open_webui.retrieval.vector.main import (
     VectorItem,
 )
 from open_webui.retrieval.vector.utils import process_metadata
-from pymilvus import Collection, DataType, FieldSchema, connections
+from pymilvus import DataType
 from pymilvus import MilvusClient as Client
 from pymilvus.exceptions import MilvusException
 
@@ -202,8 +202,6 @@ class MilvusClient(VectorDBBase):
         return self._result_to_search_result(result)
 
     def query(self, collection_name: str, filter: dict, limit: int = -1):
-        connections.connect(uri=MILVUS_URI, token=MILVUS_TOKEN, db_name=MILVUS_DB)
-
         collection_name = collection_name.replace('-', '_')
         if not self.has_collection(collection_name):
             log.warning(f'Query attempted on non-existent collection: {self.collection_prefix}_{collection_name}')
@@ -218,16 +216,16 @@ class MilvusClient(VectorDBBase):
 
         filter_string = ' && '.join(filter_expressions)
 
-        collection = Collection(f'{self.collection_prefix}_{collection_name}')
-        collection.load()
+        self.client.load_collection(collection_name=f'{self.collection_prefix}_{collection_name}')
 
         try:
             log.info(
                 f"Querying collection {self.collection_prefix}_{collection_name} with filter: '{filter_string}', limit: {limit}"
             )
 
-            iterator = collection.query_iterator(
-                expr=filter_string,
+            iterator = self.client.query_iterator(
+                collection_name=f'{self.collection_prefix}_{collection_name}',
+                filter=filter_string,
                 output_fields=[
                     'id',
                     'data',