Upload Document Chunks for RAG via UpsertChunks API - AnalyticDB for PostgreSQL - Alibaba Cloud - AnalyticDB

Vectorizes document chunks and uploads them to a document collection.

Operation description

The vectorization algorithm is the one specified when you called the CreateDocumentCollection operation.

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:UpsertChunks

create

*Document

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

None

Request parameters

Parameter	Type	Required	Description	Example
DBInstanceId	string	Yes	The cluster ID. Note You can call the DescribeDBInstances operation to query information about all AnalyticDB for PostgreSQL instances in a region, including instance IDs.	gp-xxxxxxxxx
RegionId	string	Yes	The region ID of the cluster.	cn-hangzhou
NamespacePassword	string	Yes	The password of the namespace. Note This value is specified when you call the CreateNamespace operation.	testpassword
Namespace	string	No	The name of the namespace. Default value: public. Note You can call the CreateNamespace operation to create a namespace and call the ListNamespaces operation to query a list of namespaces.	mynamespace
Collection	string	Yes	The name of the document collection. Note You can call the CreateDocumentCollection operation to create a document collection and call the ListDocumentCollections operation to query a list of document collections.	document
FileName	string	No	The file name of the document. Note If a non-empty file name is specified, the system determines whether to overwrite the data associated with that file name based on the ShouldReplaceFile parameter. If you leave this parameter empty, chunk data is appended to the document collection.	mydoc.txt
ShouldReplaceFile	boolean	No	Specifies whether to overwrite the data associated with the file name specified by FileName. If set to true, the system deletes all data associated with the file name and then inserts new data. If set to false, the system keeps the existing data and inserts or updates chunk data based on the TextChunks parameter. Default value: true.	true
AllowInsertWithFilter	boolean	No	Controls whether data insertion is allowed when a Filter is provided under TextChunks. If set to true, the insert operation is performed when the filter does not match any data. If set to false, no action is performed when the filter does not match any data. Default value: true.	true
TextChunks	array<object>	No	The list of document chunks.
	array<object>	No	A document chunk object.
Filter	string	No	The filter condition for the data to update. Use the same format as a WHERE clause.	title = 'seagull'
Content	string	Yes	The text content of the chunk.	AnalyticDB for PostgreSQL is a simple, fast, and cost-effective PB-scale cloud data warehouse solution.
Metadata	object	No	The metadata of the chunk.	{"title":"test"}
Id	string	No	The unique ID of the vector data.	273e3fc7-8f56-4167-a1bb-d35d2f3b9043

Response elements

Element	Type	Description	Example
	object
RequestId	string	The request ID.	ABB39CC3-4488-4857-905D-2E4A051D0521
Message	string	The response message.	Successful
Status	string	The status of the operation. Valid values: success fail	success
EmbeddingTokens	string	The number of tokens consumed during vectorization. Note A token is the minimum unit for splitting text. A token can be a word, phrase, punctuation, or character.	100
JobId	string	The job ID. You can use `GetGraphRAGJob` to check the job status. Note Returned only when the knowledge base is enabled.	231460f8-75dc-405e-a669-0c5204887e91

Examples

Success response

JSON format

{
  "RequestId": "ABB39CC3-4488-4857-905D-2E4A051D0521",
  "Message": "Successful",
  "Status": "success",
  "EmbeddingTokens": "100",
  "JobId": "231460f8-75dc-405e-a669-0c5204887e91"
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.