My goal is to create a system with smart search capabilities, and one of the most important requirements is that it must run entirely on my local hardware. Privacy is key, but the main driver is the challenge and joy of building it myself (an obviously learn).
The key features I'm aiming for are:
Automatic identification and tagging of family members (local face recognition).
Generation of descriptive captions for each photo.
Natural language search (e.g., "Show me photos of us at the beach in Luquillo from last summer").
I've already prompted AI tools for a high-level project plan, and they provided a solid blueprint (eg, Ollama with LLaVA, a vector DB like ChromaDB, you know it). Now, I'm highly interested in the real-world human experience. I'm looking for advice, learning stories, and the little details that only come from building something similar.
What tools, models, and best practices would you recommend for a project like this in 2025? Specifically, I'm curious about combining structured metadata (EXIF), face recognition data, and semantic vector search into a single, cohesive application.
Any and all advice would be deeply appreciated. Thanks!
The dev is really reluctant of accepting external contributions, which has driven away a lot of curious folks willing to contribute.
Immich seems to be the other extreme. Moving really fast with a lot of contributors, but stuff occasionally breaks, the setup is fiddly, but the Ai features are 100x more powerful. I just don't like the ui as much as photoprism. I with there was some kind of blend of the two, on a middle ground of their dev philosophies.
As of now, I use SentenceTransformer model to chunk files, blip for captioning (“Family vacation in Banff, February 2025”)) and mtcnn with InsightFace for face detection. My index stores captions, face embeddings, and EXIF metadata (date, GPS) for queries like “show photos of us in Banff last winter.” I’m working on integrating ChromaDB for faster searches.
Eventually, I aim to store indexes as:
{
"filename": "/Vacation/Banff/Wife.jpg",
"chunk_id": 0,
"text": "Family at Banff, February 2025",
"caption_embedding": [0.1, 0.2, ...],
"face_embeddings": [{"name": "NT", "embedding": [0.3, 0.4, ...]}, ...],
"exif": {
"DateTimeOriginal": "2025:02:15",
"GPSCoordinates": "18.387, -65.992"
}
I also built an UI (like Spotlight Search) to search through these indexes.
Code (in progress): https://github.com/neberej/smart-search
I've used gemma to process pictures and get descriptions and also to respond questions about the pictures (eg. is there a bicycle in the picture?). Haven't tried it for face recognition, but if you already have identified someone in one photo, it can probably tell you if the person in that photo is also in another photo
Just one caveat, if you are processing thousands of pictures, it will take a while to process them all (depending on your hardware and picture size). You could also try creating a processing pipeline, first extracting faces or bounding boxes of the faces with something like opencv, and then passing those to gemma3
Please post repo link if you ever decide to open source
I must be wasting so much storage on the 4 photos I took in a row of the family pose, or derivatives that got shared on whatsapp and then stored back to my gallery, and so on, and I know I'm not the only one.
I'm using docker compose to include some supporting containers like go-vod (for hardware transcoding), another nextcloud instance to handle push notifications to the clients, and redis (for caching). I can share some more details, foibles and pitfalls if you'd like.
I initiated a rescan last week, which stacks background jobs in a queue that gets called by cron 2 or 3 times a day. Recognize has been cranking through 10k-20k photos per day, with good results.
I've installed a desktop client on my dad's laptop so he can dump all of the family hard drives we've accumulated over the years. The client does a good job of clearing up disk space after uploading, which is a huge advantage in my setup. My dad has used the OneDrive client before, so he was able to pick up this process very quickly.
Nextcloud also has a decent mobile client that can auto-upload photos and videos, which I recently used to help my mother-in-law upload media from her 7-year-old iPhone.
take my photo catalog stored in google photos, apple pictures, Onedrive, Amazon photos. collate into a single store, dedupe. Then build a proper timeline and geo/map view for all the photos.
I focused more on fast rendering in [photofield] (quick [explainer] if you're interested), but even the hacked up basic semantic search with CLIP works better than it has any right to. Vector DBs are cool, but what is cooler is writing float arrays to sqlite :)
[deepface]: https://github.com/serengil/deepface
[photofield]: https://github.com/SmilyOrg/photofield
[explainer]: https://lnar.dev/blog/photofield-origins/
I pay them for service/storage as it’s e2ee and it doesn’t matter to me if they or I store the encrypted blobs.
They also have a CLI tool you can run from cron on your NAS or whatever to make sure you have a complete local copy of your data, too.
https://ente.io - if you use the referral code SNEAK we both get additional free storage.
For Features. I dont know why there's isn't a tag for Screen Caps. I made lots of them and I want to group them together.
Stock NC gets you a very solid general purpose document management system and with a few addons, you basically get self hosted SharePoint and OneDrive without the baggage. The images/pictures side of things has seen quite a lot of development and with some addons you get image classification with fairly minimal effort.
The system as a whole will quite happily handle many 100,000 files with pretty rubbish hardware, if you are happy to wait for batch jobs to run or you throw more hardware at it and speed up the job schedules.
NC has a stock phone app which works very well these days, including camera folder uploads. There are several more apps that integrate with the main one to add optional functionality. For example notes and voip.
It is a very large and mature setup with loads of documentation and hence extensible by a determined hacker if something is missing.
The addition of an AI tool is a great idea.
It gives a sort of high level system overview that might provide some useful insights or inspiration for you.
I expect we will see a Qwen 3VL soon.
The stack is hacky, since it was mostly for myself...
Do you need the embeddings to be private? Or just the photos?