> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.vellum.ai/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.vellum.ai/_mcp/server. # Changelog | November, 2024 ## Workflows SDK Beta Release **November 24th, 2024** We're excited to announce the beta release of the Vellum Workflows SDK! The Workflows SDK allows you to define the control flow of your AI systems using Python and push/pull the definition of your Workflows to/from Vellum's UI. The Workflows SDK is currently in closed beta. If you'd like to participate and provide feedback, please contact us. For more information, check out the [Vellum Workflows SDK docs](/developers/workflows-sdk/introduction). We'll be sharing more on the Workflows SDK in the coming weeks, so stay tuned! ## Prompt/Workflow Deployment History APIs **November 23rd, 2024** We've added two new APIs for retrieving details about a Prompt/Workflow Deployment at a specific history point. You can key off of either a `history_id` or the name of a Release Tag to retrieve the state of a Deployment at that point in time. For more info, check out our API reference: * [Prompt Deployment History](/api-reference/prompts/deployments/retrieve-history) * [Workflow Deployment History](/api-reference/workflows/deployments/retrieve-history) These APIs are available in our SDKs beginning version 0.9.15. ## Prompt Sandbox UI Improvements **November 21st, 2024** Prompt Sandboxes have received a major facelift, making it easier to reason about a Prompt's input variables and values, as well as making it possible to more easily resize panels to suit your needs. ### Prompt Editor The Prompt Editor tab now consolidates the "Input Variables" and "Scenarios" panels, so that you now define variables and provide values in the same place. All panels are resizeable. ![Prompt Editor](https://storage.googleapis.com/vellum-public/help-docs/changelogs/2024-11/prompt-editor-improvements.png) ### Comparison Mode Comparison Mode makes use of the same variable input elements, making it possible to rename input variables right next to where you'd provide their values. ![Comparison Mode](https://storage.googleapis.com/vellum-public/help-docs/changelogs/2024-11/comparison-mode-improvements.png) ### Chat Mode Lastly, Chat Mode has gotten major updates, such that you can now resize any panel and all UI elements look consistent across all modes. ![Chat Mode](https://storage.googleapis.com/vellum-public/help-docs/changelogs/2024-11/chat-mode-improvements.png) ## 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: * [Prompt Deployment Release Tags](/api-reference/prompts/deployments/list-release-tags) * [Workflow Deployment Release Tags](/api-reference/workflows/deployments/list-release-tags) 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](https://storage.googleapis.com/vellum-public/help-docs/changelogs/2024-11/evals-optional-csv-heads.png) ### 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](https://storage.googleapis.com/vellum-public/help-docs/changelogs/2024-11/subworkflow-node-full-height.png) ### 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](https://platform.openai.com/docs/guides/audio?audio-generation-quickstart-example=audio-in). To learn more about how to use audio input with Vellum, read our [documentation](/api-reference/prompts/execute-prompt#request.body.inputs.CHAT_HISTORY.value.content.AUDIO.type). ## 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](https://docs.anthropic.com/en/docs/about-claude/models) /api-reference/prompts/execute-prompt#request.body.inputs.CHAT\_HISTORY.value.content.AUDIO.type