fix: avoid incompatible error for wenxing model and add middleware config for baidu vector database

Author: WayneCao

api/commands.py

@@ -325,55 +325,6 @@ def migrate_knowledge_vector_database():
 
                 elif vector_type in lower_colletion_vector_types:
                     collection_name = Dataset.gen_collection_name_by_id(dataset_id).lower()
-                elif vector_type == VectorType.MILVUS:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.MILVUS, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.RELYT:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "relyt", "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.TENCENT:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.TENCENT, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.PGVECTOR:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": VectorType.PGVECTOR, "vector_store": {"class_prefix": collection_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.OPENSEARCH:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.OPENSEARCH,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.ANALYTICDB:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.ANALYTICDB,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.ELASTICSEARCH:
-                    dataset_id = dataset.id
-                    index_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {"type": "elasticsearch", "vector_store": {"class_prefix": index_name}}
-                    dataset.index_struct = json.dumps(index_struct_dict)
-                elif vector_type == VectorType.BAIDU:
-                    dataset_id = dataset.id
-                    collection_name = Dataset.gen_collection_name_by_id(dataset_id)
-                    index_struct_dict = {
-                        "type": VectorType.BAIDU,
-                        "vector_store": {"class_prefix": collection_name},
-                    }
-                    dataset.index_struct = json.dumps(index_struct_dict)
                 else:
                     raise ValueError(f"Vector store {vector_type} is not supported.")
 

api/configs/middleware/__init__.py

@@ -16,6 +16,7 @@
 from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
 from configs.middleware.storage.volcengine_tos_storage_config import VolcengineTOSStorageConfig
 from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
+from configs.middleware.vdb.baidu_vector_config import BaiduVectorDBConfig
 from configs.middleware.vdb.chroma_config import ChromaConfig
 from configs.middleware.vdb.couchbase_config import CouchbaseConfig
 from configs.middleware.vdb.elasticsearch_config import ElasticsearchConfig
@@ -34,7 +35,6 @@
 from configs.middleware.vdb.upstash_config import UpstashConfig
 from configs.middleware.vdb.vikingdb_config import VikingDBConfig
 from configs.middleware.vdb.weaviate_config import WeaviateConfig
-from configs.middleware.vdb.baidu_vector_config import BaiduVectorDBConfig
 
 
 class StorageConfig(BaseSettings):

api/core/rag/datasource/vdb/baidu/baidu_vector.py

@@ -2,14 +2,14 @@
 import time
 import uuid
 from typing import Any
-import numpy as np
 
+import numpy as np
 from pydantic import BaseModel, model_validator
 from pymochow import MochowClient
 from pymochow.auth.bce_credentials import BceCredentials
 from pymochow.configuration import Configuration
-from pymochow.exception import ClientError, ServerError
-from pymochow.model.enum import FieldType, IndexState, IndexType, MetricType, TableState, ServerErrCode
+from pymochow.exception import ServerError
+from pymochow.model.enum import FieldType, IndexState, IndexType, MetricType, ServerErrCode, TableState
 from pymochow.model.schema import Field, HNSWParams, Schema, VectorIndex
 from pymochow.model.table import AnnSearch, HNSWSearchParams, Partition, Row
 

api/core/rag/datasource/vdb/vector_type.py

@@ -22,4 +22,4 @@ class VectorType(str, Enum):
     UPSTASH = "upstash"
     TIDB_ON_QDRANT = "tidb_on_qdrant"
     OCEANBASE = "oceanbase"
-    BAIDU = "baidu"
+