feat(qdrant):add replication_factor when create collection in qdrant (#20133)

Co-authored-by: 刘敏 <min.liu@tongdun.net>

api/.env.example

@@ -152,6 +152,7 @@ QDRANT_API_KEY=difyai123456
 QDRANT_CLIENT_TIMEOUT=20
 QDRANT_GRPC_ENABLED=false
 QDRANT_GRPC_PORT=6334
+QDRANT_REPLICATION_FACTOR=1
 
 #Couchbase configuration
 COUCHBASE_CONNECTION_STRING=127.0.0.1

api/configs/middleware/vdb/qdrant_config.py

@@ -33,3 +33,8 @@ class QdrantConfig(BaseSettings):
         description="Port number for gRPC connection to Qdrant server (default is 6334)",
         default=6334,
     )
+
+    QDRANT_REPLICATION_FACTOR: PositiveInt = Field(
+        description="Replication factor for Qdrant collections (default is 1)",
+        default=1,
+    )

api/core/rag/datasource/vdb/qdrant/qdrant_vector.py

@@ -46,6 +46,7 @@ class QdrantConfig(BaseModel):
     root_path: Optional[str] = None
     grpc_port: int = 6334
     prefer_grpc: bool = False
+    replication_factor: int = 1
 
     def to_qdrant_params(self):
         if self.endpoint and self.endpoint.startswith("path:"):
@@ -119,11 +120,13 @@ class QdrantVector(BaseVector):
                     max_indexing_threads=0,
                     on_disk=False,
                 )
+
                 self._client.create_collection(
                     collection_name=collection_name,
                     vectors_config=vectors_config,
                     hnsw_config=hnsw_config,
                     timeout=int(self._client_config.timeout),
+                    replication_factor=self._client_config.replication_factor,
                 )
 
                 # create group_id payload index
@@ -466,5 +469,6 @@ class QdrantVectorFactory(AbstractVectorFactory):
                 timeout=dify_config.QDRANT_CLIENT_TIMEOUT,
                 grpc_port=dify_config.QDRANT_GRPC_PORT,
                 prefer_grpc=dify_config.QDRANT_GRPC_ENABLED,
+                replication_factor=dify_config.QDRANT_REPLICATION_FACTOR,
             ),
         )

api/core/rag/datasource/vdb/tidb_on_qdrant/tidb_on_qdrant_vector.py

@@ -49,6 +49,7 @@ class TidbOnQdrantConfig(BaseModel):
     root_path: Optional[str] = None
     grpc_port: int = 6334
     prefer_grpc: bool = False
+    replication_factor: int = 1
 
     def to_qdrant_params(self):
         if self.endpoint and self.endpoint.startswith("path:"):
@@ -134,6 +135,7 @@ class TidbOnQdrantVector(BaseVector):
                     vectors_config=vectors_config,
                     hnsw_config=hnsw_config,
                     timeout=int(self._client_config.timeout),
+                    replication_factor=self._client_config.replication_factor,
                 )
 
                 # create group_id payload index
@@ -484,6 +486,7 @@ class TidbOnQdrantVectorFactory(AbstractVectorFactory):
                 timeout=dify_config.TIDB_ON_QDRANT_CLIENT_TIMEOUT,
                 grpc_port=dify_config.TIDB_ON_QDRANT_GRPC_PORT,
                 prefer_grpc=dify_config.TIDB_ON_QDRANT_GRPC_ENABLED,
+                replication_factor=dify_config.QDRANT_REPLICATION_FACTOR,
             ),
         )
 

docker/.env.example

@@ -412,6 +412,7 @@ QDRANT_API_KEY=difyai123456
 QDRANT_CLIENT_TIMEOUT=20
 QDRANT_GRPC_ENABLED=false
 QDRANT_GRPC_PORT=6334
+QDRANT_REPLICATION_FACTOR=1
 
 # Milvus configuration. Only available when VECTOR_STORE is `milvus`.
 # The milvus uri.

docker/docker-compose.yaml

@@ -138,6 +138,7 @@ x-shared-env: &shared-api-worker-env
   QDRANT_CLIENT_TIMEOUT: ${QDRANT_CLIENT_TIMEOUT:-20}
   QDRANT_GRPC_ENABLED: ${QDRANT_GRPC_ENABLED:-false}
   QDRANT_GRPC_PORT: ${QDRANT_GRPC_PORT:-6334}
+  QDRANT_REPLICATION_FACTOR: ${QDRANT_REPLICATION_FACTOR:-1}
   MILVUS_URI: ${MILVUS_URI:-http://host.docker.internal:19530}
   MILVUS_DATABASE: ${MILVUS_DATABASE:-}
   MILVUS_TOKEN: ${MILVUS_TOKEN:-}