Unstructured-IO / Unstructured-IO/unstructured-api

How to use a local custom model for hi_res strategy

Open
#484 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
951
Forks
192
Avg merge
7d 8h
Merged PRs (30d)
2

Description

In the readme content, I found this:

We also support models to be used locally, for example, yolox. Please refer to the using-the-api-locally section for more information on how to use the local API.

Is that mean self-hosting api service(run docker or run-web-app) could use a local model for hi_res strategy?

If possible, how can I do it?

Btw, what's the model's download folder and where the onnx file is? (under web-app service, run by make run-web-app)

I have set the hiResModelName to yolox_quantized before, but after the downloading, I can't find the model file which named yolox_l0.05_quantized.onnx

Any feadback is welcome! 💖 🙏

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the README's hi-res model name and using-the-api-locally sections, then inspect the make run-web-app entry point. Determine whether self-hosted services support local hi_res models and where the downloaded model files are stored. Done means the README explains the setup and model location clearly.

Written by the indexing model from the issue text.

Assessment

Tech stack
docker, python
Domain
backend, documentation
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.