Just getting errors when processing images

[scottcru]

Hi, installation instructions followed to the letter, but when scanning I get the following error in the logs :

ERROR backend.pipeline: AI processing failed for /photos/IMG_2171.HEIC: Server error '500 Internal Server Error' for url 'http://192.168.1.214:11434/api/generate'

Can you point me in the right direction to resolve please.

[vonhex]

try giving my fork a try I think I fixed this issue, he has yet to pull my changes. https://github.com/vonhex/a-eye its also on Unraid in the community apps.

[scottcru]

Many thanks for your help. I installed your fork but continuing to receive the same problem i.e. all images error when processing. I have attached my A-Eye docker log and highlighted the errors there. Any help would be much appreciated.

A-Eye Docker Log Unraid.pdf

[lhjadmin]

Fantastic! Let me take a look.

[vonhex]

oops wrong account, ill check on it this morning, appreciate the log!

[vonhex]

The error is a 500 from Ollama's /api/generate. The actual reason (model not found, OOM, etc.) is in the response body, but
raise_for_status() discards it — users just see the generic HTTP error with no actionable info.

With changes, Now the error logged will say something like Ollama error: model 'llava:13b' not found or Ollama error: CUDA out of memory
instead of the useless HTTP status message.

Root cause in this report: The Ollama server at 192.168.1.214:11434 returned a 500. The most common causes on Unraid are:

1. Model not found — the vision model configured in A-EYE isn't pulled on that Ollama instance (ollama pull )
2. OOM — GPU/RAM ran out when loading a large model; try a smaller quantization (e.g. q4_K_M instead of q8)
3. Model timeout — Ollama unloaded the model between the /api/tags check and the generate call (unlikely but possible under
   memory pressure)

The user's next step should be to check the Ollama container logs on their Unraid (docker logs ) — with this
fix, A-EYE will also now log the specific Ollama error message so they won't have to dig into Ollama's logs at all.

[scottcru]

Thank-you for taking the trouble to look into this for me. It does seem my error related to my GPU not having sufficient VRAM (card only has 6GB) for the tasks being performed by the AI. I’ve tried some less GPU heavy visual models and it has started working. Time for another GPU purchase if I want to dive into this exciting world of local unraid AI further!

[vonhex]

Awesome! Are you able to close the issue or does it need to be SIO?