---
title: "VLM Run integration for LuumenAI"
url: "https://www.luumen.ai/integrations/vlm-run/"
entity: SoftwareIntegration
category: "AI & automation"
audience: "SRE, DevOps, platform engineering, IT operations"
---

# VLM Run integration for LuumenAI

Pull structured data out of documents, images, and audio from the terminal

## What LuumenAI can do with VLM Run

LuumenAI connects to VLM Run with an API token and exposes 11 tools (7 read-only · 4 write). For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

## Key facts

- Authentication: API token
- Tools available: 11 tools (7 read-only · 4 write)
- Deployment: scoped as part of your Pilot, Platform, or Managed rollout
- Category: AI & automation

## About VLM Run with LuumenAI

Connect VLM Run and Luumen can see the files you have uploaded, the extraction domains available, the skills your team has built, and the status of every prediction or agent run. When you need new output, it starts an extraction or an agent execution and polls until the result is ready. Luumen authenticates with an API key.

## Example tools

Read-only (7 in total):

- `VLM_RUN_DISCOVER_EXTRACTION_SCHEMAS` — List supported structured-extraction domains, or return the full JSON schema for one domain when domain is provided.
- `VLM_RUN_FIND_FILES` — List uploaded files or find one by file ID or MD5 hash.
- `VLM_RUN_FIND_SKILLS` — List VLM Run skills or find one exact skill by ID, name, and optional version.
- `VLM_RUN_GET_RUN` — Get the current status and result of one structured-extraction prediction or agent execution; call repeatedly to poll asynchronous work.
- `VLM_RUN_LIST_AGENTS` — Return agents available to the connected account for selection before execution.
- `VLM_RUN_LIST_ARTIFACTS` — List artifact metadata belonging to exactly one chat session or agent execution.
- `VLM_RUN_LIST_RUNS` — List structured-extraction predictions or agent executions for the connected account.

Write and destructive (4 in total, subject to configured approval policy):

- `VLM_RUN_CREATE_SKILL` — Create a reusable skill from exactly one uploaded zip, prompt, or chat session.
- `VLM_RUN_EXECUTE_AGENT` — Start a VLM Run agent execution from an existing agent name or inline configuration over multimodal inputs.
- `VLM_RUN_EXTRACT_STRUCTURED_JSON` — Start structured JSON extraction from images, a document, a video, or audio using a domain, custom schema, or skill.
- `VLM_RUN_UPLOAD_FILE` — Upload a local file to VLM Run for extraction, agent input, or skill creation.

## Frequently asked questions

### How does LuumenAI connect to VLM Run?

Authorize once with API token. Luumen lists the scopes each action needs before you approve the connection, and credentials never appear in the chat.

### Can LuumenAI change things in VLM Run on its own?

For connected tools, admins configure which actions may run automatically and which require approval, within the access granted to the user.

### Is there an audit trail?

Every call to VLM Run — read or write, approved or declined — is recorded with the actor, the input, and the result.

Full page: https://www.luumen.ai/integrations/vlm-run/