The Ask Kyvos Copilot must be configured through the Kyvos Manager on the GenAI Configuration page.
You can either select a semantic model from a predefined list. After selecting the semantic model, the predefined list of questions will be displayed. You can change the semantic model at any point in time.
You can type your query or use the microphone option to generate it.
The Ask Kyvos Copilot feature provides a flexible communication platform. You can initiate a new chat session or continue with an existing one. Your chat history is preserved, enabling you to revisit previous queries.
The Ask Kyvos Copilot is a context-aware feature, so there's no need to repeat previous queries when delving deeper into a query. It automatically responds by understanding the context of the preceding query.
Once you input a query, Kyvos Ask Copilot fetches the relevant information based on the selected semantic model. You can view the data input and use different operations, such as showing info and data summary, saving the data as a workbook that would be part of your dashboard, and using different settings for data, making it easy to understand and analyze.
Your query input is displayed based on the metadata of the semantic model. The metadata, such as metadata, such as description, key, tags, drivers, and key element settings, enables you to get more targeted and relevant data inputs. If the metadata of the semantic model is not sufficient, the accuracy of the answers might be inappropriate. In this case, you can modify semantic model metadata at any time.
You can export and share analysis in formats like PDF, Image, and CSV.
You can attempt a maximum of three attempts to ask queries. After reaching the maximum number of attempts, an error message is displayed. Additionally, you can view details of the error. This helps you narrow or modify your queries.
You can remove the unwanted chats.
System semantic models are not supported. All business semantic models, ROLAP and MOLAP, are supported.
...
Tip
...
Best Practices
| Anchor | ||||
|---|---|---|---|---|
|
Here is a list of best practices you must follow to get better clarity in response:
For Semantic Model Designers
Refer to the metadata of a semantic model to better frame your questions in alignment with the model's capabilities and the type of information it can provide.
Always provide proper tags to each column, which will be used to pick columns for querying correctly. Tags should ideally contain the synonyms or business language that the customer will use to refer specific columns.
Always have complete date attributes in the semantic model irrespective of predefined hierarchy.
Hide all unnecessary Levels, Attributes, and Measures not required for conversational analytics.
Special characters must not be present in the name of the semantic model, tags, and description.
Ensure that you clearly define the Keys field for level and attributes for which you want a different sort order than the order of the display field.
For Business Users
Always provide description to clearly provide business context. Column level description should be leveraged to provide information like:
Sample 2-3 values for domain-specific attributes.
Defining special date time aspects like Holiday months, Weekdays/Weekends other than usual ones, Business season, etc.
Some special instructions you want Large Language Model (LLM) to follow, like not using specific columns for certain purposes. For example, order priority is used to identify returned orders.
The clearer the context of your question, the better the response will be. For example, rather than asking, "Show sales for 143-435-564," it's more effective to specify, "Show sales for product ID 143-435-564.
Break down complex questions into smaller, more specific follow-up questions.
Considerations
| Anchor | ||||
|---|---|---|---|---|
|
Kyvos Copilot leverages Large Language Model (LLM) to convert natural language to SQL, which might sometimes produce inaccurate generation. Always verify the answer by checking the information in the answer. In case of an error or incorrect response, try regenerating the answer by re-submitting the question.
Layout adjustments like resizing visuals or precise alignment aren't possible through Kyvos Copilot.
To generate visualizations in response to your queries, Kyvos does not send any data to LLMs. However, to create natural language summaries and sample questions, Kyvos needs to send some data to LLMs. If you have concerns about data sharing with LLMs, you can disable this feature by setting the “property name” in the GenAI configuration