feat: support AnalyticDB vector store (langgenius#5586)

Co-authored-by: xiaozeyu <xiaozeyu.xzy@alibaba-inc.com>

api/.env.example

@@ -151,6 +151,16 @@ CHROMA_DATABASE=default_database
 CHROMA_AUTH_PROVIDER=chromadb.auth.token_authn.TokenAuthenticationServerProvider
 CHROMA_AUTH_CREDENTIALS=difyai123456
 
+# AnalyticDB configuration
+ANALYTICDB_KEY_ID=your-ak
+ANALYTICDB_KEY_SECRET=your-sk
+ANALYTICDB_REGION_ID=cn-hangzhou
+ANALYTICDB_INSTANCE_ID=gp-ab123456
+ANALYTICDB_ACCOUNT=testaccount
+ANALYTICDB_PASSWORD=testpassword
+ANALYTICDB_NAMESPACE=dify
+ANALYTICDB_NAMESPACE_PASSWORD=difypassword
+
 # OpenSearch configuration
 OPENSEARCH_HOST=127.0.0.1
 OPENSEARCH_PORT=9200

api/commands.py

@@ -337,6 +337,14 @@ def migrate_knowledge_vector_database():
                         "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)
                 else:
                     raise ValueError(f"Vector store {vector_type} is not supported.")
 

api/configs/middleware/__init__.py

@@ -10,6 +10,7 @@
 from configs.middleware.storage.google_cloud_storage_config import GoogleCloudStorageConfig
 from configs.middleware.storage.oci_storage_config import OCIStorageConfig
 from configs.middleware.storage.tencent_cos_storage_config import TencentCloudCOSStorageConfig
+from configs.middleware.vdb.analyticdb_config import AnalyticdbConfig
 from configs.middleware.vdb.chroma_config import ChromaConfig
 from configs.middleware.vdb.milvus_config import MilvusConfig
 from configs.middleware.vdb.opensearch_config import OpenSearchConfig
@@ -183,6 +184,7 @@ class MiddlewareConfig(
 
     # configs of vdb and vdb providers
     VectorStoreConfig,
+    AnalyticdbConfig,
     ChromaConfig,
     MilvusConfig,
     OpenSearchConfig,

api/configs/middleware/vdb/analyticdb_config.py

@@ -0,0 +1,44 @@
+from typing import Optional
+
+from pydantic import BaseModel, Field
+
+
+class AnalyticdbConfig(BaseModel):
+    """
+    Configuration for connecting to AnalyticDB.
+    Refer to the following documentation for details on obtaining credentials:
+    https://www.alibabacloud.com/help/en/analyticdb-for-postgresql/getting-started/create-an-instance-instances-with-vector-engine-optimization-enabled
+    """
+
+    ANALYTICDB_KEY_ID : Optional[str] = Field(
+        default=None,
+        description="The Access Key ID provided by Alibaba Cloud for authentication."
+    )
+    ANALYTICDB_KEY_SECRET : Optional[str] = Field(
+        default=None,
+        description="The Secret Access Key corresponding to the Access Key ID for secure access."
+    )
+    ANALYTICDB_REGION_ID : Optional[str] = Field(
+        default=None,
+        description="The region where the AnalyticDB instance is deployed (e.g., 'cn-hangzhou')."
+    )
+    ANALYTICDB_INSTANCE_ID : Optional[str] = Field(
+        default=None,
+        description="The unique identifier of the AnalyticDB instance you want to connect to (e.g., 'gp-ab123456').."
+    )
+    ANALYTICDB_ACCOUNT : Optional[str] = Field(
+        default=None,
+        description="The account name used to log in to the AnalyticDB instance."
+    )
+    ANALYTICDB_PASSWORD : Optional[str] = Field(
+        default=None,
+        description="The password associated with the AnalyticDB account for authentication."
+    )
+    ANALYTICDB_NAMESPACE : Optional[str] = Field(
+        default=None,
+        description="The namespace within AnalyticDB for schema isolation."
+    )
+    ANALYTICDB_NAMESPACE_PASSWORD : Optional[str] = Field(
+        default=None,
+        description="The password for accessing the specified namespace within the AnalyticDB instance."
+    )

api/controllers/console/datasets/datasets.py

@@ -515,7 +515,7 @@ def get(self):
                         RetrievalMethod.SEMANTIC_SEARCH
                     ]
                 }
-            case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH:
+            case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH | VectorType.ANALYTICDB:
                 return {
                     'retrieval_method': [
                         RetrievalMethod.SEMANTIC_SEARCH,
@@ -539,7 +539,7 @@ def get(self, vector_type):
                         RetrievalMethod.SEMANTIC_SEARCH
                     ]
                 }
-            case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH:
+            case VectorType.QDRANT | VectorType.WEAVIATE | VectorType.OPENSEARCH| VectorType.ANALYTICDB:
                 return {
                     'retrieval_method': [
                         RetrievalMethod.SEMANTIC_SEARCH,