yaellev1
Sisense Employee
Joined 3 years ago
User Profile
User Widgets
Contributions
Re: Sisense Intelligence token estimation
There is no extra charge. Note that Sisense Intelligence includes both features that require an LLM and those that do not. So features like Explanations, Forecast, Exploration paths etc have always been available and do not consume tokens. Only usage of LLM based features consumes tokens while you're actively using the feature. Nothing is processed in the background.21Views1like0CommentsRe: Sisense Intelligence token estimation
vatojavier that is correct, both the user prompt and some system instructions are passed to the llm along with the datasource semantic metadata , contributing to the overall token count. We plan to introduce in product analytics to help customers understand their average token usage this is not available at this time. This is currently on our 6 months roadmap. More information on what data is processed across different use cases can be found here: https://docs.sisense.com/main/SisenseLinux/data-flow-per-feature.htm?tocpath=Sisense%20Intelligence%7CData%20Handling%20-%20Securing%20AI%20in%20Sisense%20Intelligence%7C_____449Views1like0CommentsRe: Support for custom LLM endpoints
We have plans to support additional providers and llms beyond azure open ai. There are limitations to support any llm type due to: (a) not all llms perform well on our tasks and you may experience an unexpected or explainable drop in performance, and (b) not all expose functions that we rely on like structured output.17Views0likes1CommentRe: Sisense Intelligence - struggling with requests
Thats great! The feature is likely to reach GA in next release (2025.2) and will include additional improvements in the chat response as well as other improvements to the UX. By recommendations, are you referring to the AI generated quick start questions? if you feel that is not performing well, we would love to get your feedback2.4KViews0likes3CommentsRe: Sisense Intelligence - struggling with requests
Hi francoisvv What features are you referring to? When setting up your elasticube, (or live model, no difference), please make sure that you hide any irrelevant columns, give meaningful names to the columns and provide descriptions where the column name may be ambiguous with other columns or unclear.2.4KViews1like5Comments