OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

VLM Run Hub

VLM Run Hub is a Python library of reusable Pydantic schemas for structuring vision-language model extraction from images, videos and documents.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

VLM Run Hub — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use it when an existing or planned VLM workflow needs a reusable structured output model, such as an invoice schema for document extraction.

Who it is for

  • Python developers building document-processing or visual ETL workflows
  • Teams that need consistent typed fields from VLM-based image, video or document extraction

Documented uses

  • Select an industry- or document-specific schema for visual extraction.
  • Define validated, typed output structures for downstream processing.
  • Connect a reusable schema to a VLM integration.
Before you choose

Requirements & limits

The public GitHub repository declares an Apache-2.0 license. The README documents installation through pip.

  • The library supplies schemas; a separate VLM provider or integration performs inference.
  • The README demonstrates both the VLM Run Python SDK and Instructor with OpenAI.
  • The schema catalog includes document-processing examples, with additional visual-input use cases described for images, videos and documents.

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

Set up invoice extraction with Instructor and OpenAI

Use the hub’s Invoice Pydantic schema as the response model in an Instructor/OpenAI image-extraction request.

Before you start

  • Python and the vlmrun-hub package
  • Instructor and the OpenAI Python client
  • An OpenAI client configured for access
  • An invoice image URL

Steps

  1. Install the schema package with the command below.

    Documented command
    pip install vlmrun-hub

  2. Import Invoice from vlmrun.hub.schemas.document.invoice.

  3. Create an Instructor-wrapped OpenAI client using the documented MD_JSON mode.

  4. Submit a chat completion with the invoice image and set response_model=Invoice.

Expected outcome

The request is configured to return invoice information in the structure defined by the Invoice schema.

Guide limitations

  • The hub supplies the schema, not the model inference service.
  • The README example uses OpenAI and Instructor; it does not document setup for other providers in this recipe.
Documentation 1 ↗
Source-based practical guide

Set up invoice extraction with the VLM Run Python SDK

Configure the documented SDK example to send an invoice image for the `document.invoice` domain.

Before you start

  • Python, the vlmrun-hub package and the VLM Run Python SDK
  • A VLM Run API key and the documented API base URL
  • An invoice image

Steps

  1. Install the schema package with the command below.

    Documented command
    pip install vlmrun-hub

  2. Configure the SDK client with the VLM Run base URL and API key.

  3. Load an invoice image and call client.image.generate with the image and domain="document.invoice".

Expected outcome

The example submits the invoice image to the SDK using the invoice domain and receives a prediction response.

Guide limitations

  • This recipe uses VLM Run’s separate SDK and service; the hub itself provides schemas.
  • The README example uses a specific public sample image URL.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
14 October 2026
Original website title
vlm-run/vlmrun-hub · Official homepage title · retained in its source language
How we review sourcesSuggest a correction