...
On the navigation pane, click Kyvos and Ecosystem > GenAI Configuration. The page displays information about the GenAI Configuration connection details.
In the Connections pane, click the plus icon to add a new GenAI connection. The connection that you create will be listed in the Connection pane. You can edit the information when needed.
Select this Enable checkbox to enable GenAI connection. This will enable the following:
The Ask Kyvos CopilotDialogues option for creating expressions for calculated measures and members.
The Ask Kyvos CopilotDialogues option for MDX queriesoption that will appear in the Query Playground page.
The Ask Kyvos Copilot Dialogues option for Conversation AI. This AI-powered feature helps you query your data using natural language (semantic queries).
Enter details as:
| Aura tab collection |
|---|
| params | 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 |
|---|
|
| Aura tab |
|---|
| summary | MDX Queries and MDX CalculationsGenerations |
|---|
| params | JTdCJTIydGl0bGUlMjIlM0ElMjJNRFglMjBRdWVyaWVzJTIwYW5kJTIwTURYJTIwQ2FsY3VsYXRpb25zJTIyJTdEJTdCJTIydGl0bGUlMjIlM0ElMjJNRFglMjBHZW5lcmF0aW9ucyUyMiU3RA== |
|---|
|
Parameter/Field | Description |
|---|
Connection Name | A unique name that identifies your GenAI connections. | Provider | The name of the GenAI provider the system will use to generate output. | URL | The LLM Service URL of the provider-specific endpoint for generating output. For Azure | API EndPoint | Specify which endpoint to be used to generate AI-powered conversational responses. | Authentication Key | A unique key for authenticating and authorizing requests to the provider's endpoint. | Model | The name of the GenAI LLM model used to generate the output. | Is Model Fine Tuned | Select one of the following:
Yes: Select this option to fine-tune the model.
No: Select this option if you do not want to fine-tune the model. | Embedding Connection | Specify the name of the GenAI embedding provider that the system will use to generate embeddings. | Usage | Select one of the following: |
Calculations MDX QueriesYou can specify whether you want to use the feature for MDX calculations or MDX queries. If you want to create expressions for calculated measures or members, select MDX calculations. If you want to query on the semantic model, choose the MDX queries option. However: If you select the MDX calculations option, the Kyvos Dialogues option will appear in the Calculated Measures dialog box for creating expressions for calculated measures and members. If you select the MDX queries option, the Kyvos Dialogues option will appear in the Query Playground page.
You can also set a default connection to be used for MDX calculations, MDX queries. To configure this, select the appropriate checkboxes as needed: |
Calculations MDX Queries: Select this checkbox to set the default connection for MDX queries.Temperature | Configures temperature, controlling randomness. Lowering it results in less random completions. As the temperature approaches zero, the model becomes deterministic and repetitive. It is recommended to alter either this or top p, but not both. Default Value: 1 Minimum Value: 0 Maximum Value: 2
| Maximum length | Specifies | Allow Sending Data for LLM | Select Yes or No to specify whether the generated questions should include values or not. | Generate Content | Select Title, Summary, or Key Insight to determine the content to be generated, such as the title, summary, and key insights. NOTE: For summary and key insights, the value for 'Allow Sending Data for NLG', should be set to 'Yes'. | Max Rows Summary | Enter the value to configure maximum values for row summary. NOTE: The default value is 100. | Input Prompt Token Limit | Specify the maximum tokens allowed for a prompt in a single request for the current provider. NOTE: The default value is 8000. The minimum value is 0. | Output Prompt Token Limit | Specify the maximum number of tokens shared between the prompt and output, which varies by model. One token is |
roughly approximately four characters for English text. |
Default Value: 1 Minimum Value: 0 Maximum Value: 10000NOTE: The default value is 8000. The minimum value is 0. | Max Retry Count | Specify maximum retry count attempted so that we get correct query. NOTE: The default value is 0. | Summary Records Threshold | Specify similarity threshold for query autocorrection. NOTE: The default value is 0.2 The minimum value is 2. | LLM Temperature | Specify the LLM temperature, which controls the level of randomness in the output. Lowering the temperature results in less random completions. The responses of the model become increasingly deterministic and repetitive as it approaches zero. It is recommended to adjust either the temperature or top-p, but not both simultaneously. | Top P | Controls diversity via nucleus sampling. If set to 0.5, half of all likelihood-weighted options are considered. It is recommended to adjust either this or the temperature parameter, but not both. Default Value: 1 Minimum Value: 0 Maximum Value: 1
| Frequency penalty | Specifies a number between -2.0 and 2.0. Positive values penalize new tokens based on their frequency in the existing text. This reduces the likelihood of the model repeating the same line verbatim. Default Value: 1 Minimum Value: -2 Maximum Value: 2
| Presence penalty | Specifies a number between -2.0 and 2.0. Positive values penalize new tokens based on their appearance in the text so far, thereby increasing the model's likelihood of discussing new topics. Default Value: 1 Minimum Value: -2 Maximum Value: 2
|
| Aura tab |
|---|
| summary | Conversational AI |
|---|
| params | JTdCJTIydGl0bGUlMjIlM0ElMjJDb252ZXJzYXRpb25hbCUyMEFJJTIwJTIyJTdE |
|---|
|
Parameter/Field | Description |
|---|
Connection Name | A unique name that identifies your GenAI connections. | Provider | The name of the GenAI provider the system will use to generate output. | URL | The LLM Service URL of the provider-specific endpoint for generating output. | API EndPoint | Specify which endpoint to be used to generate AI-powered conversational responses. For Azure OpenAI, provide the API Endpoint in the following format:
/YOUR_DEPLOYMENT_NAME/chat/completions?api-version=2024-08-01-preview
For example, /gpt-4o/chat/completions?api-version=2024-08-01-preview
| Authentication Key | A unique key for authenticating and authorizing requests to the provider's endpoint |
.Usage | Select the Conversational AI option. You can also set a default connection to be used for Conversational AI. To configure this, select the Default Connection for Conversational AI to set the default connection for Conversational AI purposes. | Model | The name of the GenAI LLM model used to generate the output. | Is Model Fine Tuned | Select one of the following:
Yes: Select this option to fine-tune the model.
No: Select this option if you do not want to fine-tune the model. |
Prompt Token LimitEmbedding Connection | Specify the |
maximum tokens allowed for a prompt in a single request for the current provider.NOTE: The default value is 8000. The minimum value is 0. Embedding Endpoint | Specify a unique identifier for end-user, which can help OpenAI monitor and detect abuse. | Allow Sending Data for NLGSpecify similarity threshold for query autocorrectionname of the GenAI embedding provider that the system will use to generate embeddings. | Usage | Select one of the following: MDX Generations Conversational Analytics
You can specify whether you want to use the feature for MDX calculations or MDX queries. If you want to create expressions for calculated measures or members, select MDX calculations. If you want to query on the semantic model, choose the MDX queries option. However: If you select the MDX calculations option, the Kyvos Dialogues option will appear in the Calculated Measures dialog box for creating expressions for calculated measures and members. If you select the MDX queries option, the Kyvos Dialogues option will appear in the Query Playground page.
You can also set a default connection to be used for MDX calculations, MDX queries. To configure this, select the appropriate checkboxes as needed: | Allow Sending Data for LLM | Select Yes or No to specify whether the generated questions should include values or not. |
Template Folder Path | Specify a folder path for templates. | Open AI Invoke Endpoint | Specify which model to be used to generate embedding. | Embedding Model Name | Specify model name to be used to generate embedding. | Similarity Threshold (Auto Correction) | Generate Content | Select Title, Summary, or Key Insight to determine the content to be generated, such as the title, summary, and key insights. NOTE: For summary and key insights, the value for 'Allow Sending Data for NLG', should be set to 'Yes'. | Max Rows Summary | Enter the value to configure maximum values for row summary. NOTE: The default value is 100. | Input Prompt Token Limit | Specify the maximum tokens allowed for a prompt in a single request for the current provider. NOTE: The default value is 8000. The minimum value is 0. | Output Prompt Token Limit | Specify the maximum number of tokens shared between the prompt and output, which varies by model. One token is approximately four characters for English text. NOTE: The default value is |
02 2 for SQL ExecutionEnter the value to control RAG record selection | Specify maximum retry count attempted so that we get correct query. NOTE: The default value is 0. |
Upper Threshold | Summary Records Threshold | Specify similarity threshold for query autocorrection. NOTE: The default value is 0. |
7. Lower Threshold | Enter the value to control RAG record selection. NOTE: The default value is 0.4. | Maximum Records Requested | Enter the value to configure maximum records (RAG) required in a user prompt. NOTE: The default value is 10. | Max Rows Summary | Enter the value to configure maximum values for row summary. NOTE: The default value is 100. | Generate Content | Select Title, Summary, or Key Insight to determine the content to be generated, such as the title, summary, and key insights. NOTE: For summary and key insights, the value for 'Allow Sending Data for NLG', should be set to 'Yes'2 The minimum value is 2. | LLM Temperature | Specify the LLM temperature, which controls the level of randomness in the output. Lowering the temperature results in less random completions. The responses of the model become increasingly deterministic and repetitive as it approaches zero. It is recommended to adjust either the temperature or top-p, but not both simultaneously. |
|
Click Save. The GenAI connection details are saved.
Configuring an embedding connection
You can now specify the type of connection while uploading the custom provider.
After specifying the connection type, users can upload the required JAR and configuration files in a ZIP format corresponding to the selected type
...
To configure the GenAI embedding connection, perform the following steps:
...
Parameter/Field | Description |
|---|
Connection Name | A unique name that identifies your GenAI connections. |
Provider | The name of the GenAI provider the system will use to generate output. Select the required provider from the list. |
Embedding Model | Select the name of the model for generating embeddings. |
Authentication Key EndPoint | A Specify a unique key for authenticating and authorizing requests to the provider's endpoint. |
LLM Service URL | Provide the URL of the provider-specific endpoint for generating output. |
Embeddings identifier for the end user, which helps OpenAI monitor and detect abuse. |
Prompt Token Limit | Specify maximum tokens allowed for prompt in single request for current model. |
Similarity Upper Threshold | Specify upper threshold to control the selection of records for Retrieval Augmented Generation (RAG). |
Similarity Lower Threshold | Specify lower threshold to control Retrieval Augmented Generation (RAG) record selection. |
Template Folder Path | Provide the folder path for templates. |
RAG Max Records | Specify the maximum number of records (RAG) required in a user prompt. |
Configuring GenAI Custom provider
On the Custom Provider page, while configuring a custom provider
...
, you must define the ‘applicable For’ field to indicate the type whether the details apply to an LLM Connection, an Embedding Connection, or Both.
...
Parameter/Field | Description |
|---|
Provider Name | The name of the GenAI provider the system will use to generate output. |
GenAI Provider Zip | Upload the GenAI provider zip file. |
GenAI Provider ZIP | The zip file should include two folders: |
Callback Class Name Enter the callback class namefor LLM Service | Provide fully qualified class name, including package name of the class which implements the GenAICallbackService interface for LLM Service. |
Callback Class Name for Embedding Service | Provide fully qualified class name, including package name of the class which implements the GenAIEmbeddingCallbackService interface for Embedding generation. |
