Immich•2w ago

Machine learning request to "http://127.0.0.1:3003" failed with status 500: Internal Server Error

Good Day All, i run a home lab and tend to over complicate things. I do this as this helps me learn along the way. So my setup might seem over complicated.
I am ne w to immich and only been running UNRAID for a few months. I installed using the Community y application and following Spaceinvader guide. Immage is up and running . Any help will be greatly appreciated.
I have a separate Vlan network for all my "private" containers like immich and have assigned immich a stsic IP of 10.0.100.8. I have immich behind IGNX proxy on a separate VLAN separated by a FortiGate firewall. Postgres is running in the same "private" vlan as immich on ip 10.0.100.6. This all works fine. I have the mobile configured and successfully backed up photos. I can access the web interface and mostly immich is running well, except for the machine learning.

25 Replies

Immich•2w ago

:wave: Hey @WizzardDeep, Thanks for reaching out to us. Please carefully read this message and follow the recommended actions. This will help us be more effective in our support effort and leave more time for building Immich :immich:. References - Container Logs: docker compose logs docs - Container Status: docker ps -a docs - Reverse Proxy: https://immich.app/docs/administration/reverse-proxy - Code Formatting https://support.discord.com/hc/en-us/articles/210298617-Markdown-Text-101-Chat-Formatting-Bold-Italic-Underline#h_01GY0DAKGXDEHE263BCAYEGFJA Checklist I have... 1. :blue_square: verified I'm on the latest release(note that mobile app releases may take some time). 2. :blue_square: read applicable release notes. 3. :blue_square: reviewed the FAQs for known issues. 4. :blue_square: reviewed Github for known issues. 5. :blue_square: tried accessing Immich via local ip (without a custom reverse proxy). 6. :blue_square: uploaded the relevant information (see below). 7. :blue_square: tried an incognito window, disabled extensions, cleared mobile app cache, logged out and back in, different browsers, etc. as applicable (an item can be marked as "complete" by reacting with the appropriate number) Information In order to be able to effectively help you, we need you to provide clear information to show what the problem is. The exact details needed vary per case, but here is a list of things to consider: - Your docker-compose.yml and .env files. - Logs from all the containers and their status (see above). - All the troubleshooting steps you've tried so far. - Any recent changes you've made to Immich or your system. - Details about your system (both software/OS and hardware). - Details about your storage (filesystems, type of disks, output of commands like fdisk -l and df -h). - The version of the Immich server, mobile app, and other relevant pieces. - Any other information that you think might be relevant. Please paste files and logs with proper code formatting, and especially avoid blurry screenshots. Without the right information we can't work out what the problem is. Help us help you ;) If this ticket can be closed you can use the /close command, and re-open it later if needed.

WizzardDeepOP•2w ago

[Nest] 755 - 04/22/2025, 1:41:14 PM WARN [Microservices:MachineLearningRepository] Machine learning request to "http://127.0.0.1:3003" failed with status 500: Internal Server Error [Nest] 755 - 04/22/2025, 1:41:14 PM ERROR [Microservices:{"id":"8aa3eed4-0d8f-40f1-9560-8ed63df9b1ef"}] Unable to run job handler (smartSearch/smart-search): Error: Machine learning request '{"clip":{"visual":{"modelName":"ViT-B-32openai"}}}' failed for all URLs Error: Machine learning request '{"clip":{"visual":{"modelName":"ViT-B-32openai"}}}' failed for all URLs at MachineLearningRepository.predict (/app/immich/server/dist/repositories/machine-learning.repository.js:98:15) at process.processTicksAndRejections (node:internal/process/task_queues:95:5) at async MachineLearningRepository.encodeImage (/app/immich/server/dist/repositories/machine-learning.repository.js:116:26) at async SmartInfoService.handleEncodeClip (/app/immich/server/dist/services/smart-info.service.js:103:27) at async JobService.onJobStart (/app/immich/server/dist/services/job.service.js:156:28) at async EventRepository.onEvent (/app/immich/server/dist/repositories/event.repository.js:126:13) at async Worker.processJob (/app/immich/server/node_modules/bullmq/dist/cjs/classes/worker.js:394:28) at async Worker.retryIfFailed (/app/immich/server/node_modules/bullmq/dist/cjs/classes/worker.js:581:24)

Zeus•2w ago

Whats the intended IP of the ML server ? Youll have to add that in the immich settings i assume

WizzardDeepOP•2w ago

The IP for the ML server 127.0.0.1:3003 I have run curl to this and get a response.

Zeus•2w ago

Thats a loopback IP?

WizzardDeepOP•2w ago

Yes

Zeus•2w ago

You can curl that from within the immich container?

WizzardDeepOP•2w ago

yes

Zeus•2w ago

Please show a screenshot Also the ML container logs

WizzardDeepOP•2w ago

WizzardDeepOP•2w ago

How do i get the ML container logs on Unraid ?

Zeus•2w ago

What deployment is this? It should be its own container

WizzardDeepOP•2w ago

it is running in UNRAID with Comunity Application

Zeus•2w ago

I guess post the immich server logs

WizzardDeepOP•2w ago

Zeus•2w ago

Can you curl google.com from the immich container?

WizzardDeepOP•2w ago

yes can curl google

Zeus•2w ago

And the logs?

WizzardDeepOP•2w ago

trying to get logs, only know how to get logs from console, seeing if i can download logs

WizzardDeepOP•2w ago

c4b3732365b00636f611...

WizzardDeepOP•2w ago

Ok found them

Zeus•2w ago

these are very hard to read but:

{"log":"\u001b[2;36m[04/22/25 13:39:35]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Application startup complete.                      \n","stream":"stdout","time":"2025-04-22T01:39:35.424968922Z"}
{"log":"\u001b[2;36m[04/22/25 13:41:01]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Downloading visual model \u001b[32m'ViT-B-32__openai'\u001b[0m. This  \n","stream":"stdout","time":"2025-04-22T01:41:01.908410429Z"}
{"log":"\u001b[2;36m                    \u001b[0m         may take a while.                                  \n","stream":"stdout","time":"2025-04-22T01:41:01.908445129Z"}
{"log":"\u001b[2;36m[04/22/25 13:41:01]\u001b[0m\u001b[2;36m \u001b[0m\u001b[33mWARNING \u001b[0m Failed to load visual model \u001b[32m'ViT-B-32__openai'\u001b[0m.    \n","stream":"stdout","time":"2025-04-22T01:41:01.914092388Z"}
{"log":"\u001b[2;36m                    \u001b[0m         Clearing cache.                                    \n","stream":"stdout","time":"2025-04-22T01:41:01.914138528Z"}
{"log":"\u001b[2;36m[04/22/25 13:41:01]\u001b[0m\u001b[2;36m \u001b[0m\u001b[33mWARNING \u001b[0m Attempted to clear cache for model                 \n","stream":"stdout","time":"2025-04-22T01:41:01.914769812Z"}
{"log":"\u001b[2;36m                    \u001b[0m         \u001b[32m'ViT-B-32__openai'\u001b[0m, but cache directory does not   \n","stream":"stdout","time":"2025-04-22T01:41:01.914788132Z"}
{"log":"\u001b[2;36m                    \u001b[0m         exist                                              \n","stream":"stdout","time":"2025-04-22T01:41:01.914798112Z"}
{"log":"\u001b[2;36m[04/22/25 13:41:01]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Downloading visual model \u001b[32m'ViT-B-32__openai'\u001b[0m. This  \n","stream":"stdout","time":"2025-04-22T01:41:01.915454116Z"}

{"log":"\u001b[2;36m[04/22/25 13:39:35]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Application startup complete.                      \n","stream":"stdout","time":"2025-04-22T01:39:35.424968922Z"}
{"log":"\u001b[2;36m[04/22/25 13:41:01]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Downloading visual model \u001b[32m'ViT-B-32__openai'\u001b[0m. This  \n","stream":"stdout","time":"2025-04-22T01:41:01.908410429Z"}
{"log":"\u001b[2;36m                    \u001b[0m         may take a while.                                  \n","stream":"stdout","time":"2025-04-22T01:41:01.908445129Z"}
{"log":"\u001b[2;36m[04/22/25 13:41:01]\u001b[0m\u001b[2;36m \u001b[0m\u001b[33mWARNING \u001b[0m Failed to load visual model \u001b[32m'ViT-B-32__openai'\u001b[0m.    \n","stream":"stdout","time":"2025-04-22T01:41:01.914092388Z"}
{"log":"\u001b[2;36m                    \u001b[0m         Clearing cache.                                    \n","stream":"stdout","time":"2025-04-22T01:41:01.914138528Z"}
{"log":"\u001b[2;36m[04/22/25 13:41:01]\u001b[0m\u001b[2;36m \u001b[0m\u001b[33mWARNING \u001b[0m Attempted to clear cache for model                 \n","stream":"stdout","time":"2025-04-22T01:41:01.914769812Z"}
{"log":"\u001b[2;36m                    \u001b[0m         \u001b[32m'ViT-B-32__openai'\u001b[0m, but cache directory does not   \n","stream":"stdout","time":"2025-04-22T01:41:01.914788132Z"}
{"log":"\u001b[2;36m                    \u001b[0m         exist                                              \n","stream":"stdout","time":"2025-04-22T01:41:01.914798112Z"}
{"log":"\u001b[2;36m[04/22/25 13:41:01]\u001b[0m\u001b[2;36m \u001b[0m\u001b[34mINFO    \u001b[0m Downloading visual model \u001b[32m'ViT-B-32__openai'\u001b[0m. This  \n","stream":"stdout","time":"2025-04-22T01:41:01.915454116Z"}

I see "cache directory does not exist" and "failed to load model" this seems like something I guess you need to reach out to the people who make this app template. Something about the deployment is broken either that or your firewall/vlans/something is being blocked

WizzardDeepOP•2w ago

Thank you will reach out to UNRAIN community ok just took a stab in the dark I have pi-hole running and disabled blocking. now ML is working, not sure why my DNS is using Pi-hole as i do not set it for my "private" dockers . . . . At least i figured out why ML was broken . .

Zeus•2w ago

that makes sense. sounds like pihole is blocking the ML requests

WizzardDeepOP•2w ago

Yea, but i will need figure ou why my private dockers are using pi-hole for dns LOL

Gaming

Programming

Machine learning request to "http://127.0.0.1:3003" failed with status 500: Internal Server Error

Did you find this page helpful?