Rerank Search Results for Higher Relevance - AnalyticDB for PostgreSQL - Alibaba Cloud - AnalyticDB

Re-scores and reranks vector and full-text search results through semantic understanding to improve relevance and accuracy. AnalyticDB for PostgreSQL supports calling Rerank models to reorder search results but does not provide models.

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:Rerank

list

*DBInstance

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

None

Request parameters

Parameter	Type	Required	Description	Example
DBInstanceId	string	Yes	Instance ID. Note You can call the DescribeDBInstances API to view details of all AnalyticDB PostgreSQL instances in the target region, including the instance ID.	gp-xxxxxxxxx
RegionId	string	Yes	Region ID of the instance.	cn-hangzhou
Query	string	No	Query text for reranking.	ADBPGYesWhat
Documents	array	No	Documents to rerank.
	string	No	Content of a document.	ADBPGYesAlibaba CloudOLAPdatabase.
Model	string	No	Rerank model. Supported models: bge-reranker-v2-m3: (default) better performance, supports 8,192 tokens per inference. If exceeded, the text is split into chunks, which may reduce accuracy. bge-reranker-v2-minicpm-layerwise: better performance than v2-m3, supports 2,048 tokens per inference. If exceeded, the text is split into chunks, which may reduce accuracy.	bge-reranker-v2-m3
TopK	integer	No	Number of most relevant documents to return.	3
ReturnDocuments	boolean	No	If set to false, the response excludes document text and returns only the document index and rerank score.	false
MaxChunksPerDoc	integer	No	Maximum number of chunks when text exceeds the model context window: bge-reranker-v2-m3: default value is 10. bge-reranker-v2-minicpm-layerwise: default value is 5. Note Splitting example If you use the bge-reranker-v2-minicpm-layerwise model, the maximum single inference window is 2,048 tokens. If the query is 48 tokens and a document contains 9,000 tokens, the document is split as follows: tokens 1-2000 for the first chunk, 2001-4000 for the second chunk, and so on. If the number of chunks exceeds MaxChunksPerDoc, the remaining text is discarded.	10

Response elements

Element	Type	Description	Example
	object
RequestId	string	Request ID.	ABB39CC3-4488-4857-905D-2E4A051D0521
Message	string	Message returned by the API.	success
Status	string	API execution status. Valid values: success: The execution succeeded. fail: The execution failed.	success
Tokens	integer	Number of consumed tokens.	100
Results	object
Results	array<object>	Rerank results.
	object	Details of the results.
Document	string	Reranked document content.	ADBPGYesAlibaba CloudOLAPdatabase.
Index	integer	Zero-based index of this document in the input Documents array.	1
RelevanceScore	number	Relevance score assigned by the rerank model.	2.31412

Examples

Success response

JSON format

{
  "RequestId": "ABB39CC3-4488-4857-905D-2E4A051D0521",
  "Message": "success",
  "Status": "success",
  "Tokens": 100,
  "Results": {
    "Results": [
      {
        "Document": "ADBPGYesAlibaba CloudOLAPdatabase.",
        "Index": 1,
        "RelevanceScore": 2.31412
      }
    ]
  }
}

Error codes

See Error Codes for a complete list.

Release notes

See Release Notes for a complete list.