Creating an AI21 Labs (Amazon Bedrock) connection
To communicate with AI21 Labs, create a connection to the AI21 Labs (Amazon Bedrock) analytics source. Create the connection in the hub, Data load editor, or Script editor.
Data received from these connections can be used in the load script and in chart expressions to enhance your Qlik Sense analytics apps.
Configurable settings
The following table explains the settings to configure for the connection.
See the Amazon Bedrock documentation for more information about the parameters: AI21 Labs Jurassic-2 models
| Field | Description |
|---|---|
| AI21 Labs Model |
Select a model to use to generate the responses. |
| AWS Region | Choose the appropriate geographical region where the AWS resources are hosted. |
| Use FIPS Endpoint (US Regions Only) | Select whether communication between the connection and AWS uses encryption compliant with some version of the Federal Information Processing Standard (FIPS). |
| AWS Access Key |
Enter the AWS Access Key ID, which is one part of the access key pair (the other being the secret key) that you will need to provide as credentials to authenticate the AWS account. |
| AWS Secret Key | Enter the AWS Secret Key, which is one part of the access key pair (the other being the Access Key ID) that you will need to provide as credentials to authenticate the AWS account. |
| Maximum Token Count | Set the length of the response generated by the model. |
| Maximum Token Count |
Set the length of the response generated by the model. |
| Temperature |
Control the randomness of the response from the model. The lower the value, the lower the randomness. |
| Top P | Control how probable the token usage is. A lower value leads to higher exclusion of less probable tokens. |
| Presence Penalty | Control how often words, from both the input prompt and the response, are repeated in the response. The higher the value, the more variety in word usage (see external documentation for mechanism used). |
| Count Penalty | Control how often words, from both the input prompt and the response, are repeated in the response. The higher the value, the more variety in word usage (see external documentation for mechanism used). |
| Frequency Penalty | Control how often words, from both the input prompt and the response, are repeated in the response. The higher the value, the more variety in word usage (see external documentation for mechanism used). |
| Penalize Whitespaces | Turn this setting on to apply a penalty to both white spaces and new lines in the input. |
| Penalize Numbers | Turn this setting on to penalize numbers in the input. |
| Penalize Emojis | Turn this setting on to prevent emojis in the input from being penalized. |
| Penalize Punctuations | Turn this setting on to penalize punctuation in the input. |
| Penalize Stopwords | Turn this setting on to penalize stop words in the input. |
| Association Field |
Specify an Association Field, a field from the input data table containing a unique identifier. It is required to include this field in the source data when making an endpoint request for the results table returned to be associated with the source field table using a key. The designated field will be returned as a field in the response and enable the response to be associated with the source data in the data model. This can be any field with a unique ID, either from the source data or as part of the table load process. |
| Name | The name of the connection. The default name is used if you do not enter a name. |
Creating a new connection
You can create a connection to the analytic connector from the hub, from Data load editor in an existing app, or from Script editor in an existing script. Follow the steps below to create a connection.
Do the following:
-
Access the connector through Data load editor or Script editor.
Click Create new connection and select the AI21 Labs (Amazon Bedrock) connector from the list.
-
Fill out the connection dialog fields.
-
Click Create.
The data connection is saved to the space where the app is created, so it can be reused in other Qlik Sense apps and scripts. It is also listed under Data connections in Data load editor or Script editor.
Once you have created the connection, you can use it to load data with the requests and the platform's responses to them. Additionally, you can use it in chart expressions. For more information, see Select and load data from an AI21 Labs (Amazon Bedrock) connection and Using AI21 Labs (Amazon Bedrock) connections in visualization expressions.