Visual document searchSearch and RAG

DSE (Document Screenshot Embedding)

Searches page screenshots: the page is not OCRed but turned into a single vector, so the index is more compact than with late-interaction models. The card lists English and French.

Developer
University of Waterloo, Tevatron project, Canada
First release
Sep 2024
Latest release
Sep 2024
Sizes
2B (based on Qwen2-VL)
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Legal, Finance, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Search across scans and PDFs without OCR
  • Search across presentations and reports with complex layouts
  • Picking pages for an AI assistant answer

Where it is used

Document managementLegal and complianceFinance and reporting

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. dse-qwen2-2b-mrl-v1

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can DSE (Document Screenshot Embedding) be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does DSE (Document Screenshot Embedding) need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does DSE (Document Screenshot Embedding) support Russian?

No. The developer documentation lists the supported languages and Russian is not among them.

Where can I download DSE (Document Screenshot Embedding) and what does it cost?

The DSE (Document Screenshot Embedding) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Visual document searchColPali / ColQwenIlluin Technology (ViDoRe team) · FranceCommercial use with conditions

Searches PDFs and scans as images: pages do not need to be OCR'd first, the model finds the right one for a question directly, including tables and charts. Trained on English.

DetailsVisual document searchGME (General Multimodal Embedding)Alibaba (Tongyi Lab) · ChinaCommercial use allowed

One vector for text, for an image and for a text-image pair: a single model can find a product by photo, a document page by question and an image by description. The card lists English and Chinese.

DetailsVisual document searchModernVBERT / ColModernVBERTIlluin Technology, EPFL, CentraleSupélec · FranceCommercial use allowed

A compact (250M) model for searching document pages as images. According to the authors, it matches models 10 times larger and runs without a GPU.

Details

Source: huggingface.co/MrLight/dse-qwen2-2b-mrl-v1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.