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.

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

Multimodal model support #249

Merged
merged 14 commits into from
Sep 12, 2024
Merged

Multimodal model support #249

merged 14 commits into from
Sep 12, 2024

Conversation

RaynorChavez
Copy link
Member

@RaynorChavez RaynorChavez commented Aug 21, 2024

  • Please check if the PR fulfills these requirements
  • The commit message follows our guidelines
  • Tests for the changes have been added (for bug fixes/features)
  • Docs have been added / updated (for bug fixes / features)
  • What kind of change does this PR introduce? (Bug fix, feature, docs update, ...)
    introduces new field for create index: treat_urls_and_pointers_as_media (treat_urls_and_pointers_as_images is still supported). Introduces audioPreprocessing and videoPreprocessing for structured and unstructured indexes.

  • What is the current behavior? (You can also link to an open issue here)
    We only have treat_urls_and_pointers_as_images and no index settings for audio and video preprocessing.

  • What is the new behavior (if this is a feature change)?
    In order to get marqo to download and process video and audio files from urls, we need treat_urls_and_pointers_as_media. In fulfillment of marqo 2.12 PR Add multimodal model support marqo#931

In order to allow the user to customize preprocessing fro audio and video files.

  • Does this PR introduce a breaking change? (What changes might users need to make in their application due to this PR?)
    TBD

  • Other information:

@@ -38,10 +38,13 @@ def test_simple_index_creation(self):
expected_settings = {
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you have at least one test on the error message?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

done

tests/cloud_test_logic/cloud_test_index.py Outdated Show resolved Hide resolved
tests/marqo_test.py Outdated Show resolved Hide resolved
tests/marqo_test.py Outdated Show resolved Hide resolved
tests/marqo_test.py Show resolved Hide resolved
wanliAlex
wanliAlex previously approved these changes Sep 11, 2024
wanliAlex
wanliAlex previously approved these changes Sep 12, 2024
"type": "structured",
"model": "LanguageBind/Video_V1.5_FT_Audio_FT_Image",
"inferenceType": "marqo.GPU",
"storageClass": "marqo.performance",
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why are we using performance?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thought it would be good for test coverage. I just switched to balanced

@farshidz farshidz merged commit cd001d8 into mainline Sep 12, 2024
3 of 5 checks passed
@RaynorChavez RaynorChavez deleted the raynor/multimodal_support branch September 12, 2024 01:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants