fix qdrant client: compatibe with open-source qdrant

Signed-off-by: min.tian <min.tian.cn@gmail.com>

vectordb_bench/backend/clients/qdrant_cloud/config.py

@@ -1,18 +1,31 @@
 from pydantic import BaseModel, SecretStr
 
 from ..api import DBConfig, DBCaseConfig, MetricType
+from pydantic import validator
 
-
+# Allowing `api_key` to be left empty, to ensure compatibility with the open-source Qdrant.
 class QdrantConfig(DBConfig):
     url: SecretStr
     api_key: SecretStr
 
     def to_dict(self) -> dict:
-        return {
-            "url": self.url.get_secret_value(),
-            "api_key": self.api_key.get_secret_value(),
-            "prefer_grpc": True,
-        }
+        api_key = self.api_key.get_secret_value()
+        if len(api_key) > 0:
+            return {
+                "url": self.url.get_secret_value(),
+                "api_key": self.api_key.get_secret_value(),
+                "prefer_grpc": True,
+            }
+        else:
+            return {"url": self.url.get_secret_value(),}
+
+    @validator("*")
+    def not_empty_field(cls, v, field):
+        if field.name in ["api_key", "db_label"]:
+            return v
+        if isinstance(v, (str, SecretStr)) and len(v) == 0:
+            raise ValueError("Empty string!")
+        return v
 
 class QdrantIndexConfig(BaseModel, DBCaseConfig):
     metric_type: MetricType | None = None

vectordb_bench/backend/clients/qdrant_cloud/qdrant_cloud.py

@@ -43,8 +43,7 @@ def __init__(
         if drop_old:
             log.info(f"QdrantCloud client drop_old collection: {self.collection_name}")
             tmp_client.delete_collection(self.collection_name)
-
-        self._create_collection(dim, tmp_client)
+            self._create_collection(dim, tmp_client)
         tmp_client = None
 
     @contextmanager
@@ -110,13 +109,18 @@ def insert_embeddings(
     ) -> (int, Exception):
         """Insert embeddings into Milvus. should call self.init() first"""
         assert self.qdrant_client is not None
+        QDRANT_BATCH_SIZE = 500
         try:
             # TODO: counts
-            _ = self.qdrant_client.upsert(
-                collection_name=self.collection_name,
-                wait=True,
-                points=Batch(ids=metadata, payloads=[{self._primary_field: v} for v in metadata], vectors=embeddings)
-            )
+            for offset in range(0, len(embeddings), QDRANT_BATCH_SIZE):
+                vectors = embeddings[offset: offset + QDRANT_BATCH_SIZE]
+                ids = metadata[offset: offset + QDRANT_BATCH_SIZE]
+                payloads=[{self._primary_field: v} for v in ids]
+                _ = self.qdrant_client.upsert(
+                    collection_name=self.collection_name,
+                    wait=True,
+                    points=Batch(ids=ids, payloads=payloads, vectors=vectors),
+                )
         except Exception as e:
             log.info(f"Failed to insert data, {e}")
             return 0, e