Skip to main content
Docision is an open-source tool for multimodal document decisions. It uses the text, tables, layout, and visual elements on a page to choose from the answers you provide. You can use it to classify documents, check information, and route records through a workflow. For an invoice review, use one request to classify the document, check for a stamp, and decide whether to archive it, request missing information, or send it for review under your rules.

GitHub repository

View the README, source code, and examples.

Docision-1.0 model

View and download the model weights on Hugging Face.

Quickstart

This example requires Python 3.10 or later and uses CUDA GPU 0. Download the model and run inference with the input included in the repository:

Read the results

examples/multiple.json asks several questions in Chinese and English about the same table image. One asks for the RR for severely malnourished patients. After running the command, find that question by id in outputs/document-decisions.json. This excerpt from the project’s recorded output shows scores rounded to eight decimal places. Sample image · Input JSON · Full recorded output
decision shows that the model chose A (3.4). Use probability to compare candidate scores for the same question. Review decisions when the scores are close.

Use your own document image

Save the following JSON to a file and point --input to it. Set image to a path relative to the input file’s directory. In questions, list the questions and their candidate answers.
For several questions about one page, use stable inference and prefix caching to reuse the page context. Package configuration guide

Use cases

You can use the same approach to ask questions with defined options about engineering drawings and scientific charts. For example, ask which experimental group each of two curves represents based on the chart legend.

Ways to use Docision

  • Local Playground. Upload a document, enter your questions and options, and view the results in the browser.
  • Python or HTTP API. Add page checks to your application. When you submit a PDF, Docision returns results by page. Package documentation
  • MCP. Connect to a running Docision service to inspect local documents in Codex or Claude Code and export decisions as JSON or CSV. MCP setup guide

Model and public benchmark

Docision-1.0 is based on Qwen3-VL-4B-Instruct. The public doc-decision-bench dataset contains 608 document images and 2,617 Chinese–English question pairs, for a total of 5,234 language records. It covers document understanding and decisions as well as classification across industries. Dataset card The project reports 96.18% accuracy for Docision, 86.78% for the base Qwen3-VL-4B model, and 95.72% for JEV-27B-VL on this benchmark. Official benchmark results The project uses the Apache License 2.0.