Unstructured-IO / Unstructured-IO/unstructured
429 “Too Many Requests” error when Unstructured downloads YOLO layout model on Google Cloud Run
Nobody has claimed this yet.
- Dominant language
- HTML
- Stars
- 15.5k
- Forks
- 1.3k
- Avg merge
- 4d 2h
- Merged PRs (30d)
- 13
Description
Hi Unstructured team,
We’re running into HTTP 429 “Too Many Requests” errors when using the unstructured.partition.pdf function in a containerized service deployed on Google Cloud Run.
It happens when the model tries to download the yolo_x_layout model during text extraction. Is there a way we can pass a token and download the model? Setting the HUGGINGFACE_HUB_TOKEN environment variable doesn’t seem to be working, and I’m not sure if we can download the model in docker image and make it work.
Unstructured extraction failed: 429 Client Error: Too Many Requests for url: https://huggingface.co/api/models/unstructuredio/yolo_x_layout/xet-read-token/xxxxxxxxxxxxxx (Request ID: Root=1-6900e75a-58dd51313482b30b223cace0;d35575bd-d4a3-42f1-acce-5139123442be)
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Reproduce the unstructured.partition.pdf download in a Google Cloud Run container and trace how the yolo_x_layout model uses HUGGINGFACE_HUB_TOKEN. Check whether the model can be included in the Docker image or accessed with a token; done means the extraction completes without the Hugging Face 429 error.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- gcp, huggingface, python
- Domain
- backend, cloud, machine-learning
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100