🔆 Release Highlights

Bulk actions in Feedback Task datasets

Our signature bulk actions are now available for Feedback datasets!

https://user-images.githubusercontent.com/126158523/297772506-97d83a54-ea3f-4700-acd6-ff9e349ade63.mp4

Switch between Focus and Bulk depending on your needs:

• In the Focus view, you can navigate and respond to records individually. This is ideal for closely examining and giving responses to each record.
• The Bulk view allows you to see multiple records on the same page. You can select all or some of them and perform actions in bulk, such as applying a label, saving responses, submitting, or discarding. You can use this feature along with filters and similarity search to process a list of records in bulk.

For now, this is only available in the Pending queue, but rest assured, bulk actions will be improved and extended to other queues in upcoming releases.

Read more about our Focus and Bulk views here.

Sorting rating values

We now support sorting records in the Argilla UI based on the values of Rating questions (both suggestions and responses):

Learn about this and other filters in our docs.

Out-of-the-box embedding support

It’s now easier than ever to add vector embeddings to your records with the new Sentence Transformers integration.

Just choose a model from the Hugging Face hub and use our SentenceTransformersExtractor to add vectors to your dataset:

import argilla as rg
from argilla.client.feedback.integrations.sentencetransformers import SentenceTransformersExtractor

# Connect to Argilla
rg.init(
    api_url="http://localhost:6900",
    api_key="owner.apikey",
    workspace="my_workspace"
)

# Initialize the SentenceTransformersExtractor
ste = SentenceTransformersExtractor(
    model = "TaylorAI/bge-micro-v2", # Use a model from https://huggingface.co/models?library=sentence-transformers
    show_progress = False,
)

# Load a dataset from your Argilla instance
ds_remote = rg.FeedbackDataset.from_argilla("my_dataset")

# Update the dataset
ste.update_dataset(
    dataset=ds_remote,
    fields=["context"], # Only update the context field
    update_records=True, # Update the records in the dataset
    overwrite=False, # Overwrite existing fields
)

Learn more about this functionality in this tutorial.

Changelog 1.22.0

Added

• Added Bulk annotation support. (#4333)
• Restore filters from feedback dataset settings. (#4461)
• Warning on feedback dataset settings when leaving page with unsaved changes. (#4461)
• Added pydantic v2 support using the python SDK. (#4459)
• Added vector_settings to the __repr__ method of the FeedbackDataset and RemoteFeedbackDataset. (#4454)
• Added integration for sentence-transformers using SentenceTransformersExtractor to configure vector_settings in FeedbackDataset and FeedbackRecord. (#4454)

Changed

• Module argilla.cli.server definitions have been moved to argilla.server.cli module. (#4472)
• [breaking] Changed vector_settings_by_name for generic property_by_name usage, which will return None instead of raising an error. (#4454)
• The constant definition ES_INDEX_REGEX_PATTERN in module argilla._constants is now private. (#4472)
• nan values in metadata properties will raise a 422 error when creating/updating records. (#4300)
• None values are now allowed in metadata properties. (#4300)

Fixed

• Paginating to a new record, automatically scrolls down to selected form area. (#4333)

Deprecated

• The missing response status for filtering records is deprecated and will be removed in the release v1.24.0. Use pending instead. (#4433)

Removed

• The deprecated python -m argilla database command has been removed. (#4472)

New Contributors

• @Piyush-Kumar-Ghosh made their first contribution in https://github.com/argilla-io/argilla/pull/4463

Full Changelog: https://github.com/argilla-io/argilla/compare/v1.21.0...v1.22.0