CreateDocumentCollection - AnalyticDB - Alibaba Cloud Documentation Center

Creates a knowledge base.

Try it now

Try this API in OpenAPI Explorer, no manual signing needed. Successful calls auto-generate SDK code matching your parameters. Download it with built-in credential security for local usage.

Test

RAM authorization

The table below describes the authorization required to call this API. You can define it in a Resource Access Management (RAM) policy. The table's columns are detailed below:

Action: The actions can be used in the Action element of RAM permission policy statements to grant permissions to perform the operation.
API: The API that you can call to perform the action.
Access level: The predefined level of access granted for each API. Valid values: create, list, get, update, and delete.
Resource type: The type of the resource that supports authorization to perform the action. It indicates if the action supports resource-level permission. The specified resource must be compatible with the action. Otherwise, the policy will be ineffective.
- For APIs with resource-level permissions, required resource types are marked with an asterisk (*). Specify the corresponding Alibaba Cloud Resource Name (ARN) in the Resource element of the policy.
- For APIs without resource-level permissions, it is shown as All Resources. Use an asterisk (*) in the Resource element of the policy.
Condition key: The condition keys defined by the service. The key allows for granular control, applying to either actions alone or actions associated with specific resources. In addition to service-specific condition keys, Alibaba Cloud provides a set of common condition keys applicable across all RAM-supported services.
Dependent action: The dependent actions required to run the action. To complete the action, the RAM user or the RAM role must have the permissions to perform all dependent actions.

Action

Access level

Resource type

Condition key

Dependent action

gpdb:CreateDocumentCollection

create

*Collection

acs:gpdb:{#regionId}:{#accountId}:collection/{#DBInstanceId}

None

Request parameters

Parameter	Type	Required	Description	Example
DBInstanceId	string	Yes	The ID of the AnalyticDB for PostgreSQL instance. Note You can call the DescribeDBInstances operation to view details of all AnalyticDB for PostgreSQL instances in a region, including their instance IDs.	gp-xxxxxxxxx
ManagerAccount	string	Yes	The name of the management account that has the rds_superuser permission. Note You can create an account in the console by choosing Account Management. You can also call the CreateAccount operation to create an account.	testaccount
ManagerAccountPassword	string	Yes	The password of the management account.	testpassword
Namespace	string	No	The namespace. Default value: public. Note You can call the CreateNamespace operation to create a namespace. You can call the ListNamespaces operation to view the list of namespaces.	mynamespace
Collection	string	Yes	The name of the document collection to create. Note The name must comply with PostgreSQL object naming rules.	document
RegionId	string	Yes	The ID of the region where the instance resides.	cn-hangzhou
EmbeddingModel	string	No	The embedding algorithm. Default value: text-embedding-v3. Note Supported algorithms: text-embedding-v3 (recommended and default): 1024, 768, or 512 dimensions multimodal-embedding-v1 (recommended): 1024 dimensions, multimodal embedding algorithm text-embedding-v1: 1536 dimensions text-embedding-v2: 1536 dimensions text2vec (not recommended): 1024 dimensions m3e-base (not recommended): 768 dimensions m3e-small (not recommended): 512 dimensions clip-vit-b-32 (not recommended): CLIP ViT-B/32 model, 512 dimensions, image embedding algorithm clip-vit-b-16 (not recommended): CLIP ViT-B/16 model, 512 dimensions, image embedding algorithm clip-vit-l-14 (not recommended): CLIP ViT-L/14 model, 768 dimensions, image embedding algorithm clip-vit-l-14-336px (not recommended): CLIP ViT-L/14@336px model, 768 dimensions, image embedding algorithm clip-rn50 (not recommended): CLIP RN50 model, 1024 dimensions, image embedding algorithm clip-rn101 (not recommended): CLIP RN101 model, 512 dimensions, image embedding algorithm clip-rn50x4 (not recommended): CLIP RN50x4 model, 640 dimensions, image embedding algorithm clip-rn50x16 (not recommended): CLIP RN50x16 model, 768 dimensions, image embedding algorithm clip-rn50x64 (not recommended): CLIP RN50x64 model, 1024 dimensions, image embedding algorithm	text-embedding-v1
Dimension	integer	No	The vector dimension. Default value is the dimension supported by the embedding algorithm.	1024
FullTextRetrievalFields	string	No	The fields used for full-text search. Separate multiple fields with commas (,). Each field must be a key defined in the Metadata parameter.	title,page
Metadata	string	No	The metadata of vector data, formatted as a JSON string in MAP format. Keys represent field names. Values represent data types. Note Supported data types: For a complete list, see Data types. The money type is not supported. Warning The fields id, vector, doc_name, content, loader_metadata, source, and to_tsvector are reserved. Do not use them.	{"title":"text","page":"int"}
Parser	string	No	The tokenizer used for full-text search. Default value: zh_cn.	zh_cn
Metrics	string	No	The method used to build the vector index. Valid values: l2: Euclidean distance. ip: Inner product distance. cosine (default): Cosine similarity.	cosine
HnswM	integer	No	The maximum number of neighbors in the HNSW algorithm. The API sets this value automatically based on the vector dimension. Manual configuration is usually unnecessary. Note Valid values: AnalyticDB for PostgreSQL 6.0 instance: 1 to 1000. AnalyticDB for PostgreSQL 7.0 instance: 2 to 100. Default value: 16. Note We recommend setting this value based on the vector dimension: ≤ 384: 16 > 384 and ≤ 768: 32 > 768 and ≤ 1024: 64 > 1024: 128	64
HnswEfConstruction	string	No	The candidate set size used when building the HNSW index. Valid values: 4 to 1000. Default value: 64. Note This parameter applies only to AnalyticDB for PostgreSQL 7.0 instances. Its value must be ≥ 2 × HNSW_M.	128
PqEnable	integer	No	Whether to enable product quantization (PQ) to accelerate indexing. We recommend enabling PQ if your data volume exceeds 500,000 items. 0: Disabled. 1: Enabled (default).	1
ExternalStorage	integer	No	Whether to use memory-mapped files (mmap) to build the HNSW index. Default value: 0. Set this to 1 if you do not need to delete data and require high upload performance. Valid values: 0: Use segment-page storage to build the index. This mode uses PostgreSQL shared_buffer for caching and supports operations such as deletion and updates. 1: Use mmap to build the index. This mode does not support deletion or updates. Important Only AnalyticDB for PostgreSQL 6.0 supports the ExternalStorage parameter. AnalyticDB for PostgreSQL 7.0 does not support it.	0
MetadataIndices	string	No	The scalar index fields. Separate multiple fields with commas (,). Each field must be a key defined in the Metadata parameter.	title
EnableGraph	boolean	No	Whether to enable knowledge graph construction. Default value: false. Note Before using this parameter, upgrade your instance to a version that supports the graph engine. During public preview, submit a ticket to request an upgrade.	true
LLMModel	string	No	The large language model (LLM) name. knowledge-extract-standard: Default value. knowledge-extract-mini Note This parameter takes effect only when EnableGraph is set to true.	knowledge-extract-standard
Language	string	No	The language used for knowledge graph construction. Simplified Chinese: Simplified Chinese. Default value. English: English. Note This parameter takes effect only when EnableGraph is set to true.	Simplified Chinese
EntityTypes	array	No	The list of entity types. Note This parameter is required when EnableGraph is set to true.
	string	No	The entity type.	地点
RelationshipTypes	array	No	The list of relationship edge types. Note This parameter is required when EnableGraph is set to true.
	string	No	The relationship edge type.	发生
SupportSparse	boolean	No	Whether to support sparse vectors. Default value: false.	true
SparseVectorIndexConfig	object	No	The sparse vector index configuration. If provided, a sparse vector index is created.
HnswM	integer	No	The maximum number of neighbors in the HNSW algorithm. The API sets this value automatically based on the vector dimension. Manual configuration is usually unnecessary. Note Valid values: AnalyticDB for PostgreSQL 6.0 instance: 1 to 1000. AnalyticDB for PostgreSQL 7.0 instance: 2 to 100. Default value: 16. Note We recommend setting this value based on the vector dimension: ≤ 384: 16 > 384 and ≤ 768: 32 > 768 and ≤ 1024: 64 > 1024: 128	64
HnswEfConstruction	integer	No	The candidate set size used when building the HNSW index. Valid values: 4 to 1000. Default value: 64. Note This parameter applies only to AnalyticDB for PostgreSQL 7.0 instances. Its value must be ≥ 2 × HNSW_M.	128
SparseRetrievalFields	string	No	The metadata fields used to build sparse vectors. Separate multiple fields with commas (,). Each field must be a key defined in the Metadata parameter.	title,abstract

Response elements

Element	Type	Description	Example
	object
RequestId	string	The ID of the request.	ABB39CC3-4488-4857-905D-2E4A051D0521
Message	string	The response message.	Successful
Status	string	The status of the API execution. success: The operation succeeded. fail: The operation failed.	successs

Examples

Success response

JSON format

{
  "RequestId": "ABB39CC3-4488-4857-905D-2E4A051D0521",
  "Message": "Successful",
  "Status": "successs"
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.