AI Knowledge Base Reader: Functionality and Operation

The AI Knowledge Base Reader searches for data within a data set with predefined accuracy.

Properties

Operation

Defines the operation executed by the adapter.

Possible values:

AI-Semantic-Search searches for data within a data set with predefined accuracy.

Parameters

`Adapter`	Main adapter class (do not change!) Possible values: de.softproject.integration.nativeadapter.NativeAdapter: Main class (Default)
`Repository`	The virtual repository of the adapter project. Possible values: `12c0441f-fa3618e7-9b53-4926-baf9 (Default)`
`protocol`	Used protocol (HTTP oder HTTPS) Possible values: `http`: Use HTTP (no encryption) (Default) `https`: Use HTTPS (SSL-encrypted)
`host`	Name of AI gateway host Possible values: Any valid character string without protocol specification (e.g. `localhost`)
`port`	Number of AI gateway port Possible values: Any integer (e.g. `9999`)
`accessToken`	Is required to establish a Keycloak connection. Possible values: unique access token The access token needs to be generated in Keycloak.
`datasets`	List of data records used for the response, comma-separated. Possible values: Any character string for existing data records in the system, comma-separated. Example: `x4.documentation.ver7-3-1,x4.documentation.ver7-2-3`
`chunkLimit`	(optional) Specifies the maximum number of matching data chunks to be included in the output. If chunkLimit is set to e.g. 5, the output can contain up to 5 matching chunks. Possible values: Integer `4` (Default)
`scoreThreshold`	(optional) A numerical value between 0 and 1 (with the exception of 0 and 1) that specifies the maximum score threshold for the selection of matching chunks. Lower values correspond to higher accuracy. Possible values: Decimal number between 0 and 1 `0.5` (Default)

Status values

`1 (successful)`	The operation was executed successfully.
`0`	The operation was executed successfully, but without result.
`-1 (failed)`	The operation failed due to a technical error.

Input

The adapter expects an XML document with the following structure as input:

CODE

<?xml version="1.0" encoding="UTF-8"?>
<x4ai_adapter>
	<query>Tell me something about Don Quixote</query>
</x4ai_adapter>

The following elements are included in the input:

Element	Description
`x4ai_adapter`	Enclosing element for the `AI-Semantic-Search` operation.
`query`	Searched sentence for which metadata is displayed in the output.

Output

The adapter generates a XML document as output:

CODE

<output>
  <documents>
    <document>
      <content>matching document chunk</content>
      <metadata>
        <id>uuid</id>
        <source>document name</source>
        <page>page</page>
        <source_url>url</source_url>
        <version>document version</version>
        <similarity_score>number between (0; 1)</similarity_score>
      </metadata>
    </document>
    <document>
      <content></content>
      <metadata>
        <id></id>
        <source></source>
        <page></page>
        <source_url></source_url>
        <version></version>
        <similarity_score></similarity_score>
       </metadata>
     </document>
   </documents>
</output>

The following elements are included in the output:

Element	Description
`Output`	Enclosing element for the `AI-Semantic-Search` operation.
`documents`	Enclosing element for the element `document`.
`documents`	Contains information on the document accessed, the content and the metadata.
`content`	Document contents
`metadata`	Meta data of document with the elements: `id`: Document ID `source`: unique name (`sourceKey`) of the document `page`: Document page `source_url`: Document URL `version`: Document version `similarity_score`: Similarity score of answer to the question asked. The lower the value, the better the match with the question.