The Rerank operation can resolve the issue of inaccurate ranking of vector and full-text search results. It re-scores and reranks the retrieved data through semantic understanding to significantly improve the relevance and accuracy of the results. AnalyticDB for PostgreSQL allows you to rerank search results by using Rerank models, but does not provide models.
Debugging
Authorization information
The following table shows the authorization information corresponding to the API. The authorization information can be used in the Action policy element to grant a RAM user or RAM role the permissions to call this API operation. Description:
- Operation: the value that you can use in the Action element to specify the operation on a resource.
- Access level: the access level of each operation. The levels are read, write, and list.
- Resource type: the type of the resource on which you can authorize the RAM user or the RAM role to perform the operation. Take note of the following items:
- For mandatory resource types, indicate with a prefix of * .
- If the permissions cannot be granted at the resource level,
All Resourcesis used in the Resource type column of the operation.
- Condition Key: the condition key that is defined by the cloud service.
- Associated operation: other operations that the RAM user or the RAM role must have permissions to perform to complete the operation. To complete the operation, the RAM user or the RAM role must have the permissions to perform the associated operations.
| Operation | Access level | Resource type | Condition key | Associated operation |
|---|---|---|---|---|
| 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 where the instance is located. | cn-hangzhou |
| Query | string | Yes | Query statement for Rerank. | What is ADBPG? |
| Documents | array | Yes | List of documents to be re-ordered. | |
| string | Yes | Content of a single document. | ADBPG is the OLAP database of Alibaba Cloud. | |
| Model | string | No | Rerank model, currently supports:
| bge-reranker-v2-m3 |
| TopK | integer | No | Number of most relevant documents to return. | 3 |
| ReturnDocuments | boolean | No | If set to false, does not return the Documents text, only returns the index of the document order and the rerank score. | false |
| MaxChunksPerDoc | integer | No | Maximum number of chunks allowed when the text exceeds the model window:
Note
Example of splitting
| 10 |
Response parameters
Examples
Sample success responses
JSONformat
{
"RequestId": "ABB39CC3-4488-4857-905D-2E4A051D0521",
"Message": "success",
"Status": "success",
"Tokens": 100,
"Results": {
"Results": [
{
"Document": "ADBPG is the OLAP database of Alibaba Cloud.",
"Index": 1,
"RelevanceScore": 2.31412
}
]
}
}Error codes
For a list of error codes, visit the Service error codes.