Problem with machine Learning and search the situation or object from photo
Hi, I'm using version 1.142.1.
immich installed on Synology DSM in Container Manager.
ML Logs
I don't see any tasks in the ML logs, but I can see resource usage in this container.
If I try to search for "walking on the beach" or "children at the playground," the results first show photos of children or people walking, then photos with sand, and finally all other photos unrelated to the query.
I tried querying GPT about this issue, and it told me that the ML container wasn't receiving queries from the server or Redis container.
my docker compose yaml in attach.
Anyaone have this same problem and know solving?
7 Replies
:wave: Hey @toxic,
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.I tried querying GPT about this issue, and it told me that the ML container wasn't receiving queries from the server or Redis container.You're getting results so that's clearly nonsense. LLMs don't know what they're talking about when it comes to Immich, so don't listen to them all too much
and finally all other photos unrelated to the query.There isn't a cutoff. When you search you just get all photos ordered by relevance to the query. So it sounds like everything is working as it should.
Is it possible to exclude another result?
How does this index the name of this object? Where in the database? I want to translate all object names for real-time searches?
There isn't anything stored, it's all machine learning magic that turns the images (and your search text) into a bunch of numbers and then compares those numbers for similarity
It is possible to searching in another language?
I see in demo version and in github, container to auto taged photos. But It is possible to connect ML to tagged all pictures? If yes, I found conteiner to translate in table tag value to tag_mylang.
There are no tags, you can't translate them
For multilanguage results you should use a multilanguage model
https://immich.app/docs/features/searching/#clip-models
Changing models requires re-running "Machine Learning" on ALL assets
Super 🙂 realy thanks, i will testing this.:) regards