Best Practices
| Anchor | ||||
|---|---|---|---|---|
|
Here is a list of best practices you must follow while designing semantic model 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.
...
Always have complete date attribute in the semantic model along with predefined hierarchy.
...
Hide all unnecessary Levels, Attributes, and Measures not required for conversational analytics.
...
Special characters should not be present in the semantic model’s name or tags and descriptions of the semantic model.
...
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.
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 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.
Copilot can't make layout changes. For example, if you tell Copilot to resize the visuals or to align all the visuals perfectly, it won't work.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