Skip to content

Commit

Permalink
AWSKendraFrontendService Update: Amazon Kendra now returns confidence…
Browse files Browse the repository at this point in the history
… scores for 'document' query responses.
  • Loading branch information
AWS committed Sep 15, 2020
1 parent 29a4817 commit 606c527
Show file tree
Hide file tree
Showing 2 changed files with 15 additions and 5 deletions.
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
{
"type": "feature",
"category": "AWSKendraFrontendService",
"description": "Amazon Kendra now returns confidence scores for 'document' query responses."
}
Original file line number Diff line number Diff line change
Expand Up @@ -313,7 +313,7 @@
{"shape":"ServiceQuotaExceededException"},
{"shape":"InternalServerException"}
],
"documentation":"<p>Searches an active index. Use this API to search your documents using query. The <code>Query</code> operation enables to do faceted search and to filter results based on document attributes.</p> <p>It also enables you to provide user context that Amazon Kendra uses to enforce document access control in the search results. </p> <p>Amazon Kendra searches your index for text content and question and answer (FAQ) content. By default the response contains three types of results.</p> <ul> <li> <p>Relevant passages</p> </li> <li> <p>Matching FAQs</p> </li> <li> <p>Relevant documents</p> </li> </ul> <p>You can specify that the query return only one type of result using the <code>QueryResultTypeConfig</code> parameter.</p>"
"documentation":"<p>Searches an active index. Use this API to search your documents using query. The <code>Query</code> operation enables to do faceted search and to filter results based on document attributes.</p> <p>It also enables you to provide user context that Amazon Kendra uses to enforce document access control in the search results. </p> <p>Amazon Kendra searches your index for text content and question and answer (FAQ) content. By default the response contains three types of results.</p> <ul> <li> <p>Relevant passages</p> </li> <li> <p>Matching FAQs</p> </li> <li> <p>Relevant documents</p> </li> </ul> <p>You can specify that the query return only one type of result using the <code>QueryResultTypeConfig</code> parameter.</p> <p>Each query returns the 100 most relevant results. </p>"
},
"StartDataSourceSyncJob":{
"name":"StartDataSourceSyncJob",
Expand Down Expand Up @@ -916,7 +916,7 @@
},
"Edition":{
"shape":"IndexEdition",
"documentation":"<p>The Amazon Kendra edition to use for the index. Choose <code>DEVELOPER_EDITION</code> for indexes intended for development, testing, or proof of concept. Use <code>ENTERPRISE_EDITION</code> for your production databases. Once you set the edition for an index, it can't be changed. </p>"
"documentation":"<p>The Amazon Kendra edition to use for the index. Choose <code>DEVELOPER_EDITION</code> for indexes intended for development, testing, or proof of concept. Use <code>ENTERPRISE_EDITION</code> for your production databases. Once you set the edition for an index, it can't be changed. </p> <p>The <code>Edition</code> parameter is optional. If you don't supply a value, the default is <code>ENTERPRISE_EDITION</code>.</p>"
},
"RoleArn":{
"shape":"RoleArn",
Expand Down Expand Up @@ -1752,6 +1752,10 @@
"shape":"DocumentAttributeKey",
"documentation":"<p>The key for the facet values. This is the same as the <code>DocumentAttributeKey</code> provided in the query.</p>"
},
"DocumentAttributeValueType":{
"shape":"DocumentAttributeValueType",
"documentation":"<p>The data type of the facet value. This is the same as the type defined for the index field when it was created.</p>"
},
"DocumentAttributeValueCountPairs":{
"shape":"DocumentAttributeValueCountPairList",
"documentation":"<p>An array of key/value pairs, where the key is the value of the attribute and the count is the number of documents that share the key value.</p>"
Expand Down Expand Up @@ -2347,7 +2351,7 @@
},
"TotalNumberOfResults":{
"shape":"Integer",
"documentation":"<p>The number of items returned by the search. Use this to determine when you have requested the last set of results.</p>"
"documentation":"<p>The total number of items found by the search; however, you can only retrieve up to 100 items. For example, if the search found 192 items, you can only retrieve the first 100 of the items.</p>"
}
}
},
Expand Down Expand Up @@ -2388,7 +2392,7 @@
},
"ScoreAttributes":{
"shape":"ScoreAttributes",
"documentation":"<p>Indicates the confidence that Amazon Kendra has that a result matches the query that you provided. Each result is placed into a bin that indicates the confidence, <code>VERY_HIGH</code>, <code>HIGH</code>, and <code>MEDIUM</code>. You can use the score to determine if a response meets the confidence needed for your application.</p> <p>Confidence scores are only returned for results with the <code>Type</code> field set to <code>QUESTION_ANSWER</code> or <code>ANSWER</code>. This field is not returned if the <code>Type</code> field is set to <code>DOCUMENT</code>.</p>"
"documentation":"<p>Indicates the confidence that Amazon Kendra has that a result matches the query that you provided. Each result is placed into a bin that indicates the confidence, <code>VERY_HIGH</code>, <code>HIGH</code>, <code>MEDIUM</code> and <code>LOW</code>. You can use the score to determine if a response meets the confidence needed for your application.</p> <p>The field is only set to <code>LOW</code> when the <code>Type</code> field is set to <code>DOCUMENT</code> and Amazon Kendra is not confident that the result matches the query.</p>"
}
},
"documentation":"<p>A single query result.</p> <p>A query result contains information about a document returned by the query. This includes the original location of the document, a list of attributes assigned to the document, and relevant text from the document that satisfies the query.</p>"
Expand Down Expand Up @@ -2826,7 +2830,8 @@
"enum":[
"VERY_HIGH",
"HIGH",
"MEDIUM"
"MEDIUM",
"LOW"
]
},
"Search":{
Expand Down

0 comments on commit 606c527

Please sign in to comment.