Workflows `clip` block to return classes list
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 2.5k
- Forks
- 320
- Avg merge
- 1d 14h
- Merged PRs (30d)
- 133
Description
Search before asking
- I have searched the Inference issues and found no similar feature requests.
Description
Currently we return only similarity from clip block - we should make it more verbose and index by class names (compared texts)
Output now:
{'output': [], 'clip': [{'similarity': [0.1963316947221756, 0.26972252130508423, 0.20355430245399475], 'parent_id': 'image', 'prediction_type': 'embeddings-comparison', 'frame_id': None, 'time': 0.19132976199762197}], 'img': [{'width': 367, 'height': 400}]}
Use case
No response
Additional
No response
Are you willing to submit a PR?
- Yes I'd like to help by submitting a PR!
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
Locate the Workflows CLIP block implementation and any tests covering its output. Start by tracing how the current similarity list is assembled and compare it with the compared text or class-name inputs. Done means the block returns the similarity results indexed or labeled by those class names while preserving the existing output context.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100