OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Data Agents

Lumen

Lumen is an open-source Python framework for agents that translate natural-language requests into SQL-based data pipelines and create charts, dashboards, tables and reports.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Lumen — OpenViST project profile in Data Agents.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Lumen when a data exploration workflow should start from questions in natural language and produce inspectable, reusable transformations or visual outputs.

Who it is for

  • Data analysts who want to explore files, databases or data lakes through natural-language questions.
  • Developers building conversational analytics or domain-specific data applications.
  • Teams that want to inspect, edit, share or reuse generated data transformations and visualizations.

Documented uses

  • Generate SQL data pipelines from natural-language requests.
  • Explore data with charts, tables and dashboards.
  • Provide documents as context for retrieval-augmented generation.
  • Review and refine generated outputs, then summarize results and key insights.
  • Capture analyses for sharing, notebook work or dashboard composition.
Before you choose

Requirements & limits

The project is open source under the BSD-3-Clause license. The documented setup supports Python 3 or later on Linux, Windows and macOS, with installation through Conda or PyPI.

  • Generated outputs can be inspected, refined and manually edited rather than treated as fixed answers.
  • The declarative data model supports sharing analysis, continuing it in a notebook and composing dashboards.
  • The framework can be extended with custom agents, tools and analyses for domain-specific workflows.
  • Lumen is built on Panel, which the project describes as enabling a broad range of rendered outputs.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install Lumen and start Explorer with a CSV file

Set up Lumen and launch its Explorer server using a local data file.

Before you start

  • Python 3 or later
  • Linux, Windows or macOS
  • A data file such as data.csv
  • Conda or PyPI

Steps

  1. Install with Conda using conda install -c pyviz lumen, or use PyPI with the command below.

    Documented command
    pip install 'lumen[ai]'

  2. Run lumen-ai serve data.csv, replacing data.csv with the path to your data file.

Expected outcome

The documented command starts a Lumen Explorer server for the specified data file.

Guide limitations

  • The README does not provide further server configuration or usage steps in this getting-started sequence.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
12 October 2026
Original website title
holoviz/lumen · Official homepage title · retained in its source language
How we review sourcesSuggest a correction