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

Academy/ts multimodal #2825

Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Academy/ts multimodal #2825

wants to merge 7 commits into from

Conversation

malgamves
Copy link
Contributor

What's being changed:

I'm adding a new academy course on working with multimodal data with Weaviate and the typescript client.

Type of change:

  • Documentation updates (non-breaking change to fix/update documentation)

How Has This Been Tested?

  • GitHub action – automated build completed without errors

note, you can run yarn verify-links to test site links locally

orca-security-eu[bot]
orca-security-eu bot reviewed Dec 3, 2024
View reviewed changes
Copy link

@orca-security-eu orca-security-eu bot left a comment •
edited
Loading

Choose a reason for hiding this comment

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

Orca Security Scan Summary

Status Check Issues by priority
Passed Passed Infrastructure as Code high 0   medium 0   low 0   info 0 View in Orca
Passed Passed Secrets high 0   medium 0   low 0   info 0 View in Orca
Passed Passed Vulnerabilities high 0   medium 0   low 0   info 0 View in Orca

@weaviate-git-bot
Copy link

Great to see you again! Thanks for the contribution.

beep boop - the Weaviate bot 👋🤖

PS:
Are you already a member of the Weaviate Slack channel?

databyjp
databyjp reviewed Dec 12, 2024
View reviewed changes
developers/academy/js/starter_multimodal_data/102_mm_collections/20_create_collection.mdx Outdated

If you do not specify the vector yourself, Weaviate will use a specified vectorizer to generate vector embeddings from your data.

In this code example, we specify the `multi2vec-cohere` module. This module uses the Cohere Multimodal Embed 3 model to generate vector embeddings from the text and image data.
Copy link
Contributor

Choose a reason for hiding this comment

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

This is true now - but may not be in the future.

I would highlight that this is the current default model. Tbh I think it would be best to explicitly specify the model in the vectorizer.

(In the equivalent Python one, the model is specified in the Docker file due to the nature of the CLIP integration.)

Copy link
Contributor Author

Choose a reason for hiding this comment

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

Ah makes sense, will do!

databyjp
databyjp reviewed Dec 12, 2024
View reviewed changes
developers/academy/js/starter_multimodal_data/102_mm_collections/30_import_data.mdx

### <i class="fa-solid fa-chalkboard"></i> Error handling

If you have any errors in your bulk insertion, you want to know something went wrong. That way you can decide how to handle them, such as by raising an exception. In this example, we simply print out that there was an error with the import.
Copy link
Contributor

Choose a reason for hiding this comment

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

Is this what we want to do? It may be worth talking to someone like Tommy about this.

It looks like if we insert 1000 objects and 1 fails this will throw an error. I'm not sure whether this is the kind of pattern we want users to use.

Copy link
Contributor Author

Choose a reason for hiding this comment

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

yes, i've changed this to 20 objects but yes, we're working on getting an actual batcher to work around this.

@malgamves
Copy link
Contributor Author

I'll add the model name, however, it will error out as the type is currently missing.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@orca-security-eu orca-security-eu[bot] orca-security-eu[bot] left review comments

@databyjp databyjp databyjp left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@malgamves @weaviate-git-bot @databyjp