Lumen AI Skill

Overview

Lumen AI is an open-source, agent-based framework for conversational data exploration. Users ask questions in plain English and receive visualizations, SQL queries, and insights automatically generated by large language models.

What is Lumen AI?

Lumen AI translates natural language queries into:

• SQL queries for database exploration
• Interactive visualizations
• Statistical summaries
• Custom domain-specific analyses
• Data-driven insights

Key Features

• Natural Language Interface: Ask questions in plain English
• Multi-LLM Support: OpenAI, Anthropic, Google, Mistral, local models
• Agent Architecture: Specialized agents for SQL, charts, analyses
• Extensible: Custom agents, tools, and analyses
• Privacy-Focused: Full local deployment option
• No Vendor Lock-in: Switch LLM providers with configuration change

Lumen AI vs Lumen Dashboards

Feature	Lumen AI	Lumen Dashboards
Interface	Conversational, natural language	Declarative YAML
Use Case	Ad-hoc exploration, varying questions	Fixed dashboards, repeated views
Users	Non-technical users, self-service	Developers, dashboard builders
Cost	LLM API costs	No LLM costs
Flexibility	High - generates any query	Fixed - predefined views

Use Lumen AI when:

• Users need ad-hoc data exploration
• Questions vary and aren't predictable
• Enabling self-service analytics
• Reducing analyst backlog

Use Lumen Dashboards when:

• Dashboard structure is fixed
• Same visualizations needed repeatedly
• No LLM costs desired
• Full control over outputs needed

Quick Start

Installation

# Install Lumen with AI support
pip install lumen[ai]

# Install LLM provider (choose one or more)
pip install openai        # OpenAI
pip install anthropic     # Anthropic Claude

Launch Built-in Interface

# Set API key
export OPENAI_API_KEY="sk-..."

# Launch with dataset
lumen-ai serve data/sales.csv

# Or with database
lumen-ai serve "postgresql://user:pass@localhost/mydb"

Python API - Basic Example

import lumen.ai as lmai
import panel as pn
from lumen.sources.duckdb import DuckDBSource

pn.extension()

# Configure LLM
lmai.llm.llm_type = "anthropic"
lmai.llm.model = "claude-3-5-sonnet-20241022"

# Load data
source = DuckDBSource(
    tables=["./data/sales.csv", "./data/customers.csv"]
)

# Create UI
ui = lmai.ExplorerUI(
    source=source,
    title="Sales Analytics AI"
)

ui.servable()

Example Queries

Once running, try queries like:

• "What tables are available?"
• "Show me total sales by region"
• "Create a scatter plot of price vs quantity"
• "What were the top 10 products last month?"
• "Calculate average order value per customer"

Core Concepts

1. Agents

Specialized components that handle specific tasks:

• TableListAgent: Shows available tables and schemas
• ChatAgent: General conversation and summaries
• SQLAgent: Generates and executes SQL queries
• hvPlotAgent: Creates interactive visualizations
• VegaLiteAgent: Publication-quality charts
• AnalysisAgent: Custom domain-specific analyses

See: Built-in Agents Reference for complete agent documentation.

2. LLM Providers

Lumen AI works with multiple LLM providers:

Cloud Providers:

• OpenAI (GPT-4o, GPT-4o-mini)
• Anthropic (Claude 3.5 Sonnet, Claude 3 Opus/Haiku)
• Google (Gemini 1.5 Pro/Flash)
• Mistral (Mistral Large/Medium/Small)

Local Models:

• Ollama (Llama 3.1, Mistral, CodeLlama)
• LlamaCPP (custom models)

See: LLM Provider Configuration for setup details and provider comparison.

3. Memory and Context

Agents share a memory system:

• Query results persist across interactions
• Agents can build on previous work
• Context maintained throughout conversation

4. Tools

Extend agent capabilities:

• DocumentLookup: RAG for document context
• TableLookup: Schema and metadata access
• Custom Tools: External APIs, calculations, etc.

See: Custom Tools Guide for building tools.

Common Patterns

Pattern 1: Basic Analytics Interface

import lumen.ai as lmai
from lumen.sources.duckdb import DuckDBSource

# Configure LLM
lmai.llm.llm_type = "openai"
lmai.llm.model = "gpt-4o"

# Load data
source = DuckDBSource(tables=["sales.csv"])

# Create UI
ui = lmai.ExplorerUI(
    source=source,
    title="Business Analytics"
)

ui.servable()

Pattern 2: With Document Context (RAG)

source = DuckDBSource(
    tables=["sales.csv", "products.parquet"],
    documents=[
        "./docs/data_dictionary.pdf",
        "./docs/business_rules.md"
    ]
)

ui = lmai.ExplorerUI(
    source=source,
    tools=[lmai.tools.DocumentLookup]
)

Agents will automatically search documents for context when needed.

Pattern 3: Custom Agent

from lumen.ai.agents import Agent
import param

class SentimentAgent(Agent):
    """Analyze sentiment in text data."""

    requires = param.List(default=["current_source"])
    provides = param.List(default=["sentiment_analysis"])

    purpose = """
    Analyzes sentiment in text columns.
    Use when user asks about sentiment, emotions, or tone.
    Keywords: sentiment, emotion, positive, negative, tone
    """

    async def respond(self, query: str):
        # Agent implementation
        source = self.memory["current_source"]
        # ... analyze sentiment ...
        yield "Sentiment analysis results..."

# Use custom agent
ui = lmai.ExplorerUI(
    source=source,
    agents=[SentimentAgent, lmai.agents.ChatAgent]
)

See: Custom Agents Guide for detailed development guide.

Pattern 4: Custom Analysis

from lumen.ai.analyses import Analysis
from lumen.pipeline import Pipeline
import param

class CohortAnalysis(Analysis):
    """Customer cohort retention analysis."""

    columns = param.List(default=[
        'customer_id', 'signup_date', 'purchase_date'
    ])

    def __call__(self, pipeline: Pipeline):
        # Cohort analysis logic
        df = pipeline.data
        # ... calculate cohorts ...
        return results

# Register analysis
ui = lmai.ExplorerUI(
    source=source,
    agents=[
        lmai.agents.AnalysisAgent(analyses=[CohortAnalysis])
    ]
)

See: Custom Analyses Guide for examples.

Pattern 5: Multi-Source Data

from lumen.sources.duckdb import DuckDBSource

source = DuckDBSource(
    tables={
        "sales": "./data/sales.parquet",
        "customers": "./data/customers.csv",
        "products": "https://data.company.com/products.csv"
    }
)

ui = lmai.ExplorerUI(source=source)

Configuration

LLM Selection

Quick reference for choosing LLM:

Use Case	Provider	Model	Why
Production analytics	OpenAI	gpt-4o	Best balance
Complex SQL	Anthropic	claude-3-5-sonnet	Superior reasoning
High volume	OpenAI	gpt-4o-mini	Cost-effective
Sensitive data	Ollama	llama3.1	Local only
Development	OpenAI	gpt-4o-mini	Fast, cheap

See: LLM Provider Configuration for complete setup.

Agent Selection

# Use only specific agents
agents = [
    lmai.agents.TableListAgent,
    lmai.agents.SQLAgent,
    lmai.agents.hvPlotAgent,
    # Exclude VegaLiteAgent if not needed
]

ui = lmai.ExplorerUI(source=source, agents=agents)

Coordinator Types

DependencyResolver (default): Recursively resolves agent dependencies

ui = lmai.ExplorerUI(source=source, coordinator="dependency")

Planner: Creates execution plan upfront

ui = lmai.ExplorerUI(source=source, coordinator="planner")

UI Customization

ui = lmai.ExplorerUI(
    source=source,
    title="Custom Analytics AI",
    accent_color="#00aa41",
    suggestions=[
        "Show me revenue trends",
        "What are the top products?",
        "Create customer segmentation"
    ]
)

Best Practices

1. Provider Selection

• Production: Use Anthropic Claude 3.5 Sonnet or GPT-4o
• Development: Use GPT-4o-mini for cost savings
• Sensitive data: Use Ollama for local deployment

2. Security

import os

# ✅ Good: Environment variables
lmai.llm.api_key = os.getenv("OPENAI_API_KEY")

# ❌ Bad: Hardcoded secrets
lmai.llm.api_key = "sk-..."

3. Performance

# Limit table sizes for exploration
source = DuckDBSource(
    tables=["large_table.parquet"],
    table_kwargs={"large_table": {"nrows": 100000}}
)

4. User Experience

# Provide example queries
ui = lmai.ExplorerUI(
    source=source,
    suggestions=[
        "Show me revenue trends",
        "Top 10 products by sales",
        "Customer segmentation analysis"
    ]
)

Deployment

Development

lumen-ai serve app.py --autoreload --show

Production

panel serve app.py \
  --port 80 \
  --num-procs 4 \
  --allow-websocket-origin=analytics.company.com

Docker

FROM python:3.11-slim
WORKDIR /app
COPY requirements.txt .
RUN pip install -r requirements.txt
COPY app.py data/ ./
CMD ["panel", "serve", "app.py", "--port", "5006", "--address", "0.0.0.0"]

See: Deployment Guide for production deployment, Docker, Kubernetes, and security.

Troubleshooting

LLM Not Responding

# Check API key
import os
print(os.getenv("OPENAI_API_KEY"))

# Test connection
curl https://api.openai.com/v1/models \
  -H "Authorization: Bearer $OPENAI_API_KEY"

Agent Not Selected

# Debug which agent was selected
print(ui.agent_manager.last_selected_agent)

# View agent purposes
for agent in ui.agents:
    print(f"{agent.__class__.__name__}: {agent.purpose}")

SQL Generation Errors

• Add data dictionary as document for context
• Provide example queries in agent prompts
• Check table schemas match query expectations

See: Troubleshooting Guide for complete troubleshooting reference.

Progressive Learning Path

Level 1: Getting Started

1. Install and launch built-in interface
2. Try example queries
3. Configure LLM provider

Resources:

• LLM Provider Configuration

Level 2: Python API

1. Create basic ExplorerUI
2. Configure agents and tools
3. Add document context (RAG)

Resources:

• Built-in Agents Reference

Level 3: Customization

1. Build custom agents
2. Create custom analyses
3. Add custom tools

Resources:

• Custom Agents Guide
• Custom Analyses Guide
• Custom Tools Guide

Level 4: Production

1. Deploy with authentication
2. Implement monitoring
3. Scale horizontally

Resources:

• Deployment Guide

Additional Resources

Documentation

• LLM Provider Configuration - Setup for OpenAI, Anthropic, local models
• Built-in Agents Reference - Complete agent documentation
• Custom Agents Guide - Build specialized agents
• Custom Analyses Guide - Domain-specific analyses
• Custom Tools Guide - Extend agent capabilities
• Deployment Guide - Production deployment
• Troubleshooting Guide - Common issues and solutions

External Links

• Lumen AI Documentation
• Lumen AI Getting Started
• GitHub Repository
• Community Discourse

Use Cases

Business Analytics

• Ad-hoc revenue analysis
• Customer behavior exploration
• Sales performance tracking
• Market segmentation

Data Science

• Exploratory data analysis
• Quick statistical summaries
• Hypothesis testing
• Pattern discovery

Operations

• Real-time monitoring queries
• Anomaly investigation
• Performance metrics
• Incident analysis

Self-Service Analytics

• Enabling business users
• Reducing analyst backlog
• Democratizing data access
• Maintaining governance

Summary

Lumen AI transforms data exploration through natural language interfaces powered by LLMs.

Strengths:

• No SQL or coding required for users
• Flexible LLM support (cloud and local)
• Extensible architecture
• Privacy-focused options
• Reduces analyst workload

Ideal for:

• Ad-hoc data exploration
• Non-technical users
• Rapid insights
• Self-service analytics

Consider alternatives when:

• Fixed dashboards needed → Lumen Dashboards
• No LLM budget → Traditional BI tools
• Highly custom logic → Panel Dashboards

Related Skills

• Lumen Dashboards - Declarative YAML dashboards
• Panel Dashboards - Interactive dashboard development
• Plotting Fundamentals - Quick plotting with hvPlot