Chat
Last updated
Last updated
The ‘Chat’ module is the primary interface to query your data.
Simply ask questions in plain language.
Latency depends on your connection type and query complexity.
Simple questions: ~10-15 seconds
Complex queries: up to 30-45 second
To learn more about the types of questions that can be asked, view Question Types.
Learn more about Prompting Best Practices and Limitations.
To start a chat, you must first select the knowledge base.
To rename a chat, click on the chat title, make the necessary edits, and then save.
To share a chat, click share and send.
There are multiple ways to delete chat:
Click on the 3 dots next to share OR Expand the side bar, hover over the chat, and click on the trash icon
The sidebar allows you to filter between chats you created and chats shared by others.
You can also sort chats by knowledge base or by the most recent activity. You can also filter chats through key words.
There are three tabs available within the Prompt Advisor:
Curated Prompts
Prompt Playbook [still in beta]
Table Preview
The prompt advisor button gives a starting point to begin analysis as well as sample prompt set to understand how to query using Lumi.
Lumi is designed to extract actionable insights from operational data using plain language. It is not intended as a database query tool or SQL generation platform.
Playbook is industry and business function specific curated prompts to give a starting point to uncover insights and real business value depending on desired objective. (Increasing Revenue, Reducing Costs, Improving Customer Experience etc.)
Filter by industry or business function to narrow playbook prompts to suite query objective. Playbooks are designed to drive common insights that are applicable to specific industries.
Depending on business type and knowledge base configuration, not all playbook prompts will be applicable or will have context for accurate responses.
You can also select table preview to understand and view sample data as well as what tables are available inside of the knowledge base.
Upon returning data from a given query, an interactive display is available to understand returned data. Data can be viewed in both a Table or Chart form. Data can also be downloaded for full accessibility as well as copied to clipboard.
A key feature that Lumi offers is assumptions and extended data explanations to give understanding of how the analysis is being conducted.
Explanation is a very helpful view of the steps that Lumi took to generate the returned data. This is useful to check overall logic.
Local Code defines the query that was run to generate the returned data. This is critical for technical understanding and validating the returned data.
