Retrieve
Queries a knowledge base and retrieves information from it.
Request Syntax
POST /knowledgebases/knowledgeBaseId/retrieve HTTP/1.1
Content-type: application/json
{
"guardrailConfiguration": {
"guardrailId": "string",
"guardrailVersion": "string"
},
"nextToken": "string",
"retrievalConfiguration": {
"vectorSearchConfiguration": {
"filter": { ... },
"implicitFilterConfiguration": {
"metadataAttributes": [
{
"description": "string",
"key": "string",
"type": "string"
}
],
"modelArn": "string"
},
"numberOfResults": number,
"overrideSearchType": "string",
"rerankingConfiguration": {
"bedrockRerankingConfiguration": {
"metadataConfiguration": {
"selectionMode": "string",
"selectiveModeConfiguration": { ... }
},
"modelConfiguration": {
"additionalModelRequestFields": {
"string" : JSON value
},
"modelArn": "string"
},
"numberOfRerankedResults": number
},
"type": "string"
}
}
},
"retrievalQuery": {
"text": "string"
}
}
URI Request Parameters
The request uses the following URI parameters.
- knowledgeBaseId
-
The unique identifier of the knowledge base to query.
Length Constraints: Minimum length of 0. Maximum length of 10.
Pattern:
[0-9a-zA-Z]+Required: Yes
Request Body
The request accepts the following data in JSON format.
- guardrailConfiguration
-
Guardrail settings.
Type: GuardrailConfiguration object
Required: No
- nextToken
-
If there are more results than can fit in the response, the response returns a
nextToken. Use this token in thenextTokenfield of another request to retrieve the next batch of results.Type: String
Length Constraints: Minimum length of 1. Maximum length of 2048.
Pattern:
\S*Required: No
- retrievalConfiguration
-
Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.
Type: KnowledgeBaseRetrievalConfiguration object
Required: No
- retrievalQuery
-
Contains the query to send the knowledge base.
Type: KnowledgeBaseQuery object
Required: Yes
Response Syntax
HTTP/1.1 200
Content-type: application/json
{
"guardrailAction": "string",
"nextToken": "string",
"retrievalResults": [
{
"content": {
"byteContent": "string",
"row": [
{
"columnName": "string",
"columnValue": "string",
"type": "string"
}
],
"text": "string",
"type": "string"
},
"location": {
"confluenceLocation": {
"url": "string"
},
"customDocumentLocation": {
"id": "string"
},
"kendraDocumentLocation": {
"uri": "string"
},
"s3Location": {
"uri": "string"
},
"salesforceLocation": {
"url": "string"
},
"sharePointLocation": {
"url": "string"
},
"sqlLocation": {
"query": "string"
},
"type": "string",
"webLocation": {
"url": "string"
}
},
"metadata": {
"string" : JSON value
},
"score": number
}
]
}
Response Elements
If the action is successful, the service sends back an HTTP 200 response.
The following data is returned in JSON format by the service.
- guardrailAction
-
Specifies if there is a guardrail intervention in the response.
Type: String
Valid Values:
INTERVENED | NONE - nextToken
-
If there are more results than can fit in the response, the response returns a
nextToken. Use this token in thenextTokenfield of another request to retrieve the next batch of results.Type: String
Length Constraints: Minimum length of 1. Maximum length of 2048.
Pattern:
\S* - retrievalResults
-
A list of results from querying the knowledge base.
Type: Array of KnowledgeBaseRetrievalResult objects
Errors
For information about the errors that are common to all actions, see Common Errors.
- AccessDeniedException
-
The request is denied because of missing access permissions. Check your permissions and retry your request.
HTTP Status Code: 403
- BadGatewayException
-
There was an issue with a dependency due to a server issue. Retry your request.
- resourceName
-
The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or AWS STS.
HTTP Status Code: 502
- ConflictException
-
There was a conflict performing an operation. Resolve the conflict and retry your request.
HTTP Status Code: 409
- DependencyFailedException
-
There was an issue with a dependency. Check the resource configurations and retry the request.
- resourceName
-
The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or AWS STS.
HTTP Status Code: 424
- InternalServerException
-
An internal server error occurred. Retry your request.
- reason
-
The reason for the exception. If the reason is
BEDROCK_MODEL_INVOCATION_SERVICE_UNAVAILABLE, the model invocation service is unavailable. Retry your request.
HTTP Status Code: 500
- ResourceNotFoundException
-
The specified resource Amazon Resource Name (ARN) was not found. Check the Amazon Resource Name (ARN) and try your request again.
HTTP Status Code: 404
- ServiceQuotaExceededException
-
The number of requests exceeds the service quota. Resubmit your request later.
HTTP Status Code: 400
- ThrottlingException
-
The number of requests exceeds the limit. Resubmit your request later.
HTTP Status Code: 429
- ValidationException
-
Input validation failed. Check your request parameters and retry the request.
HTTP Status Code: 400
Examples
Send a basic query
The following example queries a knowledge base.
Sample Request
POST /knowledgebases/KB12345678/retrieve HTTP/1.1
Content-type: application/json
{
"retrievalQuery": {
"text": "What is AWS?"
}
}
Send a query and include filters
To include filters in a knowledge base query, at least one of the data source files must include a .metadata.json file. For example, if you had a data source of articles called articles.pdf, accompanied by a metadata file called articles.pdf.metadata.json, you could tag it for genre, year, and author. In the Retrieve request, you could apply the following filter to return all entertainment articles written after 2018, in addition to cooking or sports articles written by authors starting with C.
Sample Request
POST /knowledgebases/KB12345678/retrieve HTTP/1.1
Content-type: application/json
{
"retrievalQuery": {
"text": "What is AWS?",
},
"vectorSearchConfiguration": {
"numberOfResults": 5,
"filter": {
"orAll": [
{
"andAll": [
{
"equals": {
"key": "genre",
"value": "entertainment"
}
},
{
"greaterThan": {
"key": "year",
"value": 2018
}
}
]
},
{
"andAll": [
{
"in": {
"key": "genre",
"value": ["cooking", "sports"]
}
},
{
"startsWith": {
"key": "author",
"value": "C"
}
}
]
}
]
}
}
}
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following: