Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Load CLIP Models into a Retriever for image retrieval #2857

Closed
ZanSara opened this issue Jul 20, 2022 · 0 comments · Fixed by #2891
Closed

Load CLIP Models into a Retriever for image retrieval #2857

ZanSara opened this issue Jul 20, 2022 · 0 comments · Fixed by #2891
Assignees
@ZanSara
Labels
topic:retriever type:feature New feature or request

Comments

@ZanSara
Copy link
Contributor

ZanSara commented Jul 20, 2022 •
edited
Loading

Once the simplification of haystack/modeling/model/language_modeling.py are merged, we can proceed attempting to load a Data2VecVision into a Retriever, be it EmbeddingRetriever or a custom retriever class.

This issue implies also the addition (and potentially a revision) of relevant test.

Related issues: #2445

Update: as we realized that Data2VecVision models are unsuited for the task, we shifted into rather adding support for CLIP.
@ZanSara ZanSara added type:feature New feature or request topic:retriever labels Jul 20, 2022
@ZanSara ZanSara self-assigned this Jul 20, 2022
@ZanSara ZanSara mentioned this issue Aug 3, 2022
Merged
3 tasks
@ZanSara ZanSara changed the title Load Data2VecVision into a Retriever Load CLIP Models into a Retriever for image retrieval Aug 30, 2022
This was referenced Aug 30, 2022
Closed
Closed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@ZanSara ZanSara

Labels
topic:retriever type:feature New feature or request
Projects
None yet
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

feat: MultiModalRetriever deepset-ai/haystack
1 participant
@ZanSara