Project: https://github.com/docling-project/docling-serve

Template Repo: https://github.com/xxBeanSproutxx/unraid-docling-ca

What is it?

Docling is an open-source toolkit (IBM Research) that converts documents (PDF, DOCX, images, HTML, etc.) into structured Markdown or JSON. Perfect for AI workflows like RAG, all running locally on your Unraid server.

Default Endpoints:

- API: http://SERVER_IP:PORT

- Docs: http://SERVER_IP:PORT/docs

- Web UI: http://SERVER_IP:PORT/ui (set DOCLING_SERVE_ENABLE_UI=1)

Install Notes:

- First run may download models; caches are stored in appdata volumes.

- CPU works out of the box.

- For GPU, install the NVIDIA Driver plugin, reboot, choose a CUDA branch (cu128 or cu126) and add --gpus all.

Volumes:

- /mnt/user/appdata/docling/huggingface_cache → /opt/app-root/src/.cache/docling

- /mnt/user/appdata/docling/easyocr_cache → /opt/app-root/.EasyOCR

Issues?

Post here if you run into setup questions or bugs.

V100 32G was not working, i choose cu128 , and here doesn't download model in appdata volume.

Any Ieda? Seems it still working on my CPU.

Edited October 21, 2025Oct 21 by HAO.H

On 10/21/2025 at 10:35 AM, HAO.H said:

V100 32G was not working, i choose cu128 , and here doesn't download model in appdata volume.

Any Ieda? Seems it still working on my CPU.

Yo, forgot to quote you - see above!

Hello,

I was able to get this to work on my NVIDIA GPU. But both the CPU and NVIDIA version is giving me these logs:

WARNING:docling_jobkit.convert.manager:artifacts_path is set to an invalid directory. The system will download the model weights at runtime.

The container still works with anything I uploaded to it, just odd that i see this message each time. Thank you, ahead.

On 1/26/2026 at 3:43 PM, Soldius said:

Hello,

I was able to get this to work on my NVIDIA GPU. But both the CPU and NVIDIA version is giving me these logs:

WARNING:docling_jobkit.convert.manager:artifacts_path is set to an invalid directory. The system will download the model weights at runtime.

The container still works with anything I uploaded to it, just odd that i see this message each time. Thank you, ahead.

I tracked this down and pushed a template update to address it. The warning:

“artifacts_path is set to an invalid directory…”

was caused by the model path mapping not matching Docling Serve’s expected artifacts path.

What I changed:

- Corrected the persistent models mount to:

/opt/app-root/src/.cache/docling/models

- Added explicit DOCLING_SERVE_ARTIFACTS_PATH support so it matches that path

- Cleaned up template guidance around model storage/GPU behavior

This warning can appear when the mounted appdata folder is empty/new (or mapped one level too high), because it can mask the image’s built-in model directory and trigger runtime downloads.

After updating the template/container and applying settings, that warning should go away on normal runs.

Thanks again for reporting it! y

Your log snippet helped fix a real template issue.

Just did a fresh install of this template and it fails to load. Essentially it looks as though it's not downloading any of the models and, instead, is just saying that it can't find the models. I'm assuming that it is supposed to download the model at the time of first run, but's not doing that at all.

A similar thing is happening to me; I wanted to switch from using my GPU to just running on my CPU to save some VRAM. I removed the container and the /mnt/user/appdata/docling directory and installed from scratch. The only changes I made to the default template were to use my custom docker network, and to set DOCLING_DEVICE=cpu. When the container starts up I get a number of file not found errors:

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx is not found.

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile/ppocr_keys_v1.txt is not found.

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx is not found.

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx is not found.

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/resources/fonts/FZYTK.TTF is not found.

and a Python error because none of these can be found. It doesn't seem to be trying to download models.

On 1/26/2026 at 3:43 PM, Soldius said:

Hello,

I was able to get this to work on my NVIDIA GPU. But both the CPU and NVIDIA version is giving me these logs:

WARNING:docling_jobkit.convert.manager:artifacts_path is set to an invalid directory. The system will download the model weights at runtime.

The container still works with anything I uploaded to it, just odd that i see this message each time. Thank you, ahead.

I pushed a fix for our initial test. Let me know if the warning is resolved on your end.

On 4/6/2026 at 3:05 PM, tezgno said:

Just did a fresh install of this template and it fails to load. Essentially it looks as though it's not downloading any of the models and, instead, is just saying that it can't find the models. I'm assuming that it is supposed to download the model at the time of first run, but's not doing that at all.

This should be fixed now. I just pushed an update that changes `DOCLING_SERVE_ENABLE_REMOTE_SERVICES` to default to `true`, which allows first-run model downloads to work automatically. Please try reinstalling the template with the latest version. After your first successful start and the model cache is populated, you can set `DOCLING_SERVE_ENABLE_REMOTE_SERVICES` back to `false` if you prefer a fully offline setup. Let me know if it works!

On 4/15/2026 at 10:08 AM, chatsubo said:

A similar thing is happening to me; I wanted to switch from using my GPU to just running on my CPU to save some VRAM. I removed the container and the /mnt/user/appdata/docling directory and installed from scratch. The only changes I made to the default template were to use my custom docker network, and to set DOCLING_DEVICE=cpu. When the container starts up I get a number of file not found errors:

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx is not found.

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile/ppocr_keys_v1.txt is not found.

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx is not found.

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx is not found.

WARNING:docling.models.stages.ocr.rapid_ocr_model:The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/resources/fonts/FZYTK.TTF is not found.

and a Python error because none of these can be found. It doesn't seem to be trying to download models.

Same issue — the template was defaulting `DOCLING_SERVE_ENABLE_REMOTE_SERVICES` to `false`, which blocks model downloads. I just pushed a fix that changes the default to `true`. Please reinstall the template with the latest version and the models should download automatically on first boot. Since you switched from GPU to CPU, also make sure you select the `cpu` branch in the template (not just setting `DOCLING_DEVICE=cpu`). The `cpu` branch uses the `docling-serve-cpu` image which is built for CPU-only operation. Let me know how it goes!

**Update (May 2025):** I just pushed a fix that changes `DOCLING_SERVE_ENABLE_REMOTE_SERVICES` to default to `true`. Previously it defaulted to `false`, which blocked first-run model downloads for new installs. If you tried installing before and got model download errors, please try again with the updated template. If you prefer fully offline operation after your first successful start, you can toggle it back to `false`.

[Camofox browser automation test — edit successful]

Edited May 11May 11 by Bean_Sprout
Camofox automation test

hi im having the same issue on latest template

DOCLING_SERVE_ENABLE_REMOTE_SERVICE is set to true

WARNING: 17:38:52 - docling.models.stages.ocr.rapid_ocr_model - The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/det/ch_PP-OCRv4_det_mobile.onnx is not found.

WARNING: 17:38:52 - docling.models.stages.ocr.rapid_ocr_model - The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/paddle/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile/ppocr_keys_v1.txt is not found.

WARNING: 17:38:52 - docling.models.stages.ocr.rapid_ocr_model - The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/cls/ch_ppocr_mobile_v2.0_cls_mobile.onnx is not found.

WARNING: 17:38:52 - docling.models.stages.ocr.rapid_ocr_model - The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/onnx/PP-OCRv4/rec/ch_PP-OCRv4_rec_mobile.onnx is not found.

WARNING: 17:38:52 - docling.models.stages.ocr.rapid_ocr_model - The provided model path /opt/app-root/src/.cache/docling/models/RapidOcr/resources/fonts/FZYTK.TTF is not found.