lumen-ai

Convert natural language queries into SQL, visualizations, and insights.

3|1|Updated Dec 21, 2025
One-click install
npx skills add https://github.com/cdcore09/holoviz-claude --skill lumen-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: lumen-ai
Source: https://github.com/cdcore09/holoviz-claude/tree/main/plugins/holoviz-expert/skills/lumen-ai
Command: npx skills add https://github.com/cdcore09/holoviz-claude --skill lumen-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Lumen AI enables natural language interfaces to analyze data, translating questions into actionable insights, visualizations, and SQL queries without manual coding.

Core Features & Use Cases

  • Natural Language Interface: Ask questions in plain language and get instant data explorations.
  • Multi-LLM Support: Works with OpenAI, Anthropic, Google Gemini, Mistral, or local models for privacy and flexibility.
  • Agent Architecture: Specialized agents orchestrate tasks like tables discovery, charts, and analyses to deliver results.
  • Extensible & Privacy-Focused: Easily add tools and keep data locally when needed.
  • Self-Service Analytics: Empowers non-technical users to perform ad-hoc analysis and generate insights.
  • Use Cases: Ad-hoc exploration, dashboard prototyping, and domain-specific analytics across multiple data sources.

Quick Start

  1. Install Lumen with AI support pip install lumen[ai]
  2. Install an LLM provider (example: OpenAI) pip install openai
  3. Run the built-in interface export OPENAI_API_KEY="your-api-key" lumen-ai serve data/sales.csv

Frequently Asked Questions about lumen-ai

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert natural language queries into SQL for data exploration?

Natural language queries are converted into SQL and insights by translating questions into actionable data explorations and visualizations using an LLM agent architecture without manual coding.

Can I use local models via Ollama or LlamaCPP for self-service analytics?

Yes, self-service analytics can use local models via Ollama or LlamaCPP, alongside OpenAI, Anthropic, Gemini, and Mistral, ensuring privacy and flexibility by keeping data locally when needed.

Does Lumen AI work with OpenAI and Anthropic for conversational data analysis?

Lumen AI works with OpenAI and Anthropic for conversational data analysis, supporting multi-LLM integration to translate plain language questions into instant data explorations and visualizations across diverse datasets.

How to set up ad-hoc data exploration with lumen-ai?

Setting up ad-hoc data exploration requires installing lumen with AI support via pip, installing an LLM provider like openai, exporting your API key, and running the built-in interface command on your dataset.

What Python dependencies are required for natural language data visualization?

Natural language data visualization requires lumen version 0.10.0 or higher with AI support and panel version 1.3.0 or higher, plus an optional LLM provider package like openai or anthropic.

What are the limitations of conversational data exploration across diverse datasets?

Limitations of conversational data exploration include dependency on LLM accuracy for SQL generation and the need for specific lumen and panel versions, with potential privacy constraints unless using local models via Ollama or LlamaCPP.