nextcloud / nextcloud/context_chat
Feature Reuqest: Natural language image search using CLIP Embeddings
Nobody has claimed this yet.
- Dominant language
- PHP
- Stars
- 29
- Forks
- 12
- Avg merge
- 4d 4h
- Merged PRs (30d)
- 5
Description
Describe the feature you'd like to request
I would love to see natural language image search. You might know it from google photos or iCloud - searches like "A dog and a girl in snow" or "girl on beach with sunset".
Describe the solution you'd like
The industry standard seems to be CLIP embeddings, as e.g. implemented in immich:
https://docs.immich.app/features/searching/
Describe alternatives you've considered
The existing tag-based search is inherently limited and cannot cover the same use cases. It is also less accurate.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Review the existing tag-based search and the linked Immich documentation for the proposed CLIP-based approach. Define how natural-language queries such as the examples should be represented and searched, and verify that the resulting search supports the requested image-discovery use cases.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- machine-learning, php
- Domain
- machine-learning, search
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100