Changelog | November, 2024

Support for GPT-4o (2024-11-20)

November 20th, 2024

We’ve added support for the latest snapshot of GPT-4o (2024-11-20) to Vellum.

New API for Listing Release Tags

November 16th, 2024

We now have new API endpoints for listing all Release Tags associated with a Prompt/Workflow Deployment.

For details, check out our API Reference:

These APIs are available in our SDKs beginning version 0.9.5.

Quality of Life Improvements

November 15th, 2024

We’ve made a number of small quality of life improvements throughout Vellum.

Persisted Sort Order for Index Pages

We now remember the sort order you set on index pages. If you sort by a column, leave the page, and come back, the sort order will be preserved.

Optional Heads for Test Case CSV Upload

We used to require that all CSV files uploaded for Test Cases have a header row with all expected columns. Now, you can choose to upload a CSV with a header row containing only a subset of columns and Vellum will set the values of unspecified columns to null.

Optional Headers for Test Case CSV Upload

Semicolon Support in CSV Uploads

We now support semicolons as delimiters in CSV files uploaded for use as Test Cases.

Increased Max Concurrency for Evaluations

We used to limit the max number of concurrent Test Case runs to 12. You can now crank up the concurrency to 36.

Use Full Height for Displaying Subworkflows

We now use the full height of the screen when displaying subworkflows in the workflow editor.

Full-Height Display of Subworkflows

Remove “Copy of” When Cloning Nodes

When copy/pasting Nodes in a Workflow, we used to prefix the label of each cloned Node with “Copy of.” This is no longer the case.

Live Updates for Workflow Execution Views

When on the detail page of a Workflow Execution, the information displayed was static. If the Workflow was still running, you had to refresh the page to see changes. Now, the page will update as the Workflow progresses.

Audio Input Support via API for GPT 4o Audio Models

November 5th, 2024

We’ve added audio input capabilities via our API for the following models:

  • gpt-4o-audio-preview
  • gpt-4o-audio-preview-2024-10-01

You can now pass audio input to these models using a base64 encoded data URL.

You can read more about audio input capabilities for these models in OpenAI’s documentation.

To learn more about how to use audio input with Vellum, read our documentation.

Support for Anthropic’s Updated Haiku 3.5 Model

November 5th, 2024

We’ve added support for Anthropic’s Haiku 3.5 10-22-2024 model.

Anthropic’s Claude Haiku 3.5 /api-reference/prompts/execute-prompt#request.body.inputs.CHAT_HISTORY.value.content.AUDIO.type