Lumi Docs
  • About Lumi AI
  • Setting Up
    • Quick Start
    • 1. Connect
    • 2. Configure
      • Configuration Tips
      • Add Tables & Fields
      • Add Business Context
      • Advanced Configuration
    • 3. Distribute
  • Using Lumi
    • Getting Started
    • Lumi Use Cases
      • Data Exploration
      • Business Metrics
      • Anomaly Detection
      • Trend Analysis
      • Root Cause Analysis
      • Data Quality
    • Best Practices
      • Prompting Best Practices
      • Boards Best Practices
      • Versioning Best Practices
    • Chat Limitations
    • Knowledge Base Utility
      • Curated Prompts
      • Leveraging Memories
    • Network Configuration
  • Product Features
    • Chat
    • Boards
    • Knowledge Base
      • Overview
      • Connection
      • Tables
        • Custom Fields
      • Model
      • Business Context
      • Memories
      • Users
      • Restoration
    • Organization Settings
      • Organization Profile
      • Tool Integrations
      • Gateway Management
      • Members
    • User Profile
    • Notifications
    • Data Gateway
      • Deployment
      • Configuring for Boot
    • Source System Integrations
      • PostgreSQL
      • Microsoft SQL Server
      • MySQL
      • Databricks
      • BigQuery
      • Snowflake
      • SAP HANA
      • Oracle
    • Secondary Interfaces
      • Slack
      • Microsoft Teams
Powered by GitBook
On this page
  • 1. Data Availability
  • 2. Spelling of Attributes
  • 3. Follow Up Questions
  • 4. Data Returned From Query

Was this helpful?

  1. Using Lumi

Chat Limitations

PreviousVersioning Best PracticesNextKnowledge Base Utility

Last updated 28 days ago

Was this helpful?

We're continuously working to improve the quality of the responses. Here are the current limitations.

1. Data Availability

Lumi cannot answer questions requiring data it isn't connected to or aware of in the knowledge base. Questions beyond this scope may not receive accurate responses. You can check what data is available to query in the table preview.

2. Spelling of Attributes

Misspellings in attributes (e.g., product names, brands, or categories) may lead to empty responses. If unsure, users can:

  • Perform a general search: "how many items fall under the category that contains any variation of bikes in the description?"

  • Add common abbreviations or variations to the knowledge base.

❌ Misspelling Example

Scenario: User asking about metrics related to 'carbon road bike' sales

Error: There are no items that have the name 'carbon road bike'. This will return nothing. Lumi is directly filtering for items with the explicit name 'carbon road bike'.

Additionally this is an example of vague prompting. Is this a category, a brand, or an item? For more information view Prompting Best Practices.

✅ Tips to Resolve Error

Use the exact attribute name.

Example: What was the revenue of the item 'Carbon Elite Road Bike' last year?

Use language that generalizes the search criteria.

Example: What was the revenue of items containing any variation of 'carbon' last year?

  1. Perform a separate query to obtain all potential variations.

Example: Can you show me all the items that contain any variation of 'carbon' in the name?

  1. Re-contextualize the prompt with the exact name

Example: What was the revenue of the item 'Carbon Elite Road Bike' last year?

3. Follow Up Questions

Lumi includes follow-up questions in responses to encourage further user engagement. Please note that some of these follow-up questions might not always be directly relevant.

4. Data Returned From Query

To ensure that raw data is handled correctly, Lumi does not have access to the previous query data results. This means that prompts need to be structured with this in mind and should not reference data returned. Rather a rephrased prompt can be used to target whatever insight is desired.

Table Preview Feature