# November 2024 > November 2024 - Read about DataRobot's new features, released in November 2024. This Markdown file sits beside the HTML page at the same path (with a `.md` suffix). It summarizes the topic and lists links for tools and LLM context. Companion generated at `2026-05-06T18:17:10.005973+00:00` (UTC). ## Primary page - [November 2024](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html): Full documentation for this topic (HTML). ## Sections on this page - [November 2024](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#november-2024): In-page section heading. - [November features](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#november-features): In-page section heading. - [Applications](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#applications): In-page section heading. - [Provision DataRobot assets with the application template gallery](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#provision-datarobot-assets-with-the-application-template-gallery): In-page section heading. - [Modeling](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#modeling): In-page section heading. - [Violin plot distribution insight for Individual Prediction Explanations](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#violin-plot-distribution-insight-for-individual-prediction-explanations): In-page section heading. - [Composable ML now supported for predictive clustering experiments](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#composable-ml-now-supported-for-predictive-clustering-experiments): In-page section heading. - [GPU support in Workbench now GA](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#gpu-support-in-workbench-now-ga): In-page section heading. - [Predictions and MLOps](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#predictions-and-mlops): In-page section heading. - [Deploy LLMs from the Hugging Face Hub in DataRobot](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#deploy-llms-from-the-hugging-face-hub-in-datarobot): In-page section heading. - [Bolt-on Governance API integration for custom models](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#bolt-on-governance-api-integration-for-custom-models): In-page section heading. - [Admin](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#admin): In-page section heading. - [Home page changes from user feedback](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#home-page-changes-from-user-feedback): In-page section heading. - [API](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#api): In-page section heading. - [Python client v3.6](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#python-client-v36): In-page section heading. - [DataRobot REST API v2.35](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#datarobot-rest-api-v235): In-page section heading. - [Create vector databases with unstructured PDF documents](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/november2024-announce.html#create-vector-databases-with-unstructured-pdf-documents): In-page section heading. ## Related documentation - [AI Platform releases](https://docs.datarobot.com/en/docs/release/index.html): Linked from this page. - [Managed SaaS releases](https://docs.datarobot.com/en/docs/release/cloud-history/index.html): Linked from this page. - [2024 AI Platform releases](https://docs.datarobot.com/en/docs/release/cloud-history/2024-announce/index.html): Linked from this page. - [Self-Managed AI Platform release notes](https://docs.datarobot.com/en/docs/release/archive-release-notes/index.html): Linked from this page. - [Application templates](https://docs.datarobot.com/en/docs/wb-apps/app-templates/index.html): Linked from this page. - [SHAP Distributions: Per Feature](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/shap-distribution.html): Linked from this page. - [Individual Prediction Explanations](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/shap-predex.html): Linked from this page. - [Workbench](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/create-experiments/create-predictive/ml-unsupervised.html#clustering): Linked from this page. - [DataRobot Classic](https://docs.datarobot.com/en/docs/classic-ui/modeling/special-workflows/unsupervised/clustering.html): Linked from this page. - [Workbench experiments](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/create-experiments/create-predictive/ml-basic-experiment.html#train-on-gpus): Linked from this page. - [DataRobot Classic](https://docs.datarobot.com/en/docs/classic-ui/modeling/build-models/adv-opt/gpus.html): Linked from this page. - [documentation](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/structured-custom-models.html#chat): Linked from this page. - [example notebook](https://docs.datarobot.com/en/docs/agentic-ai/genai-code/genai-chat-completion-api.html): Linked from this page. - [Use Case directory](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/usecases/usecase-overview.html): Linked from this page. - [Modelstab in Registry](https://docs.datarobot.com/en/docs/workbench/nxt-registry/nxt-model-directory/nxt-view-manage-reg-models.html): Linked from this page. - [Python client changelog](https://docs.datarobot.com/en/docs/api/reference/changelogs/py-changelog/index.html): Linked from this page. - [REST API changelog](https://docs.datarobot.com/en/docs/api/reference/changelogs/rest-changelog/index.html): Linked from this page. ## Documentation content ## November 2024 November 27, 2024 This page provides announcements of newly released features available in DataRobot's SaaS multi-tenant AI Platform, with links to additional resources. From the release center, you can also access: - Current month's announcements - Self-Managed AI Platform release notes ## November features The following table lists each new feature: **Features grouped by capability** | Name | GA | Preview | | --- | --- | --- | | Applications | | | | Provision DataRobot assets with the application template gallery | ✔ | | | Modeling | | | | Violin plot distribution insight for Individual Prediction Explanations | ✔ | | | Composable ML now supported for predictive clustering experiments | ✔ | | | GPU support in Workbench now GA | ✔* | | | Predictions and MLOps | | | | Deploy LLMs from the Hugging Face Hub in DataRobot | ✔* | | | Bolt-on Governance API integration for custom models | | ✔ | | Admin | | | | Home page changes from user feedback | ✔ | | | API | | | | Python client v3.6 | ✔ | | | DataRobot REST API v2.35 | ✔ | | | Create vector databases with unstructured PDF documents | ✔ | | *Premium ### Applications #### Provision DataRobot assets with the application template gallery [Application templates](https://docs.datarobot.com/en/docs/wb-apps/app-templates/index.html) provide a code-first, end-to-end pipeline for provisioning DataRobot resources. With customizable components, templates assist you by programmatically generating DataRobot resources that support predictive and generative use cases. The templates include necessary metadata, perform auto-installation of dependencies configuration settings, and seamlessly integrate with existing DataRobot infrastructure to help you quickly deploy and configure solutions. ### Modeling #### Violin plot distribution insight for Individual Prediction Explanations The [SHAP Distributions: Per Feature](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/experiment-insights/shap-distribution.html), also called a violin plot, is a statistical graphic for comparing probability distributions of a dataset across different categories. Based on a sampling of 1,000 rows, this new SHAP insight displays cohorts of rows and visualizes them per feature, allowing you to inspect distributions of SHAP values and feature values. DataRobot now provides two SHAP tools to help analyze how feature values influence predictions: - SHAP Distributions: Per Feature shows the distribution and density of scores per feature using a violin plot for the visualization. - Individual Prediction Explanations show the effect of each feature on predictions on a row-by-row basis. #### Composable ML now supported for predictive clustering experiments With this release, Composable ML (editable blueprints) are available for unsupervised clustering experiments in both [Workbench](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/create-experiments/create-predictive/ml-unsupervised.html#clustering) and [DataRobot Classic](https://docs.datarobot.com/en/docs/classic-ui/modeling/special-workflows/unsupervised/clustering.html). With Composable ML for clustering, you can build blueprints that best suit your needs, using built-in tasks and custom Python/R code. #### GPU support in Workbench now GA The ability to use GPU workers for use cases that include text and/or images and require deep learning models is now generally available in [Workbench experiments](https://docs.datarobot.com/en/docs/workbench/nxt-workbench/experiments/create-experiments/create-predictive/ml-basic-experiment.html#train-on-gpus) and in [DataRobot Classic](https://docs.datarobot.com/en/docs/classic-ui/modeling/build-models/adv-opt/gpus.html). This is a premium feature that speeds up training time and, if enabled, can be accessed from the additional automation settings in an experiment. DataRobot detects blueprints that contain certain tasks and, when detected, includes GPU-supported blueprints in both Autopilot and the blueprint repository. Contact your DataRobot representative for information on enabling the feature. ### Predictions and MLOps #### Deploy LLMs from the Hugging Face Hub in DataRobot Use the model workshop to create and deploy popular open source LLMs from the [Hugging Face Hub](https://huggingface.co/models), securing your AI apps with enterprise-grade GenAI observability and governance in DataRobot. The new [\[GenAI\] vLLM Inference Serverexecution environment](https://github.com/datarobot/datarobot-user-models/tree/master/public_dropin_gpu_environments/vllm) and [vLLM Inference Server Text Generation Template](https://github.com/datarobot/datarobot-user-models/tree/master/model_templates/gpu_vllm_textgen) provide out-the-box integration with the GenAI monitoring capabilities and bolt-on governance API provided by DataRobot. This infrastructure uses the [vLLM library](https://github.com/vllm-project/vllm), an open source framework for LLM inference and serving, to integrate with Hugging Face libraries to seamlessly download and load popular open source LLMs from Hugging Face Hub. To get started, [customize the text generation model template](https://github.com/datarobot/datarobot-user-models/blob/master/model_templates/gpu_vllm_textgen/README.md). It uses `Llama-3.1-8b` LLM by default; however, you can change the selected model by modifying the `engine_config.json` file to specify the name of the OSS model you would like to use. Feature flag OFF by default: Enable Custom Model GPU Inference (Premium feature) #### Bolt-on Governance API integration for custom models The `chat()` hook allows custom models to implement the [OpenAI chat completion API](https://platform.openai.com/docs/api-reference/chat/create) to provide access to chat history and streaming response. For more information, see the [documentation](https://docs.datarobot.com/en/docs/api/code-first-tools/drum/structured-custom-models.html#chat) and an [example notebook](https://docs.datarobot.com/en/docs/agentic-ai/genai-code/genai-chat-completion-api.html). ### Admin #### Home page changes from user feedback The DataRobot home page, introduced in November of 2023, provides access to a wealth of information for use with the DataRobot app. Responding to user feedback, the new home page has been fine-tuned to provide quick help for new users and access to recent activity for returning users. Use the tiles at the top to quickly access: - Application templateend-to-end solutions. These code-first, reusable pipelines are available out-of-the-box, but also offer easy customization, for quick, tailored successes. - TheUse Case directoryto create or revisit your experiment-based, iterative workflows for predictive and generative AI models. - TheModelstab in Registrywhere you can manage, govern, and deploy assets to production. ### API #### Python client v3.6 v3.6 for DataRobot's Python client is now generally available. For a complete list of changes introduced in v3.6, view the [Python client changelog](https://docs.datarobot.com/en/docs/api/reference/changelogs/py-changelog/index.html). #### DataRobot REST API v2.35 DataRobot's v2.35 for the REST API is now generally available. For a complete list of changes introduced in v2.35, view the [REST API changelog](https://docs.datarobot.com/en/docs/api/reference/changelogs/rest-changelog/index.html). #### Create vector databases with unstructured PDF documents DataRobot now provides a service to run OCR on a dataset for you to easily extract and prepare unstructured data from PDFs to create vector databases, enabling you to start building RAG flows within DataRobot. The service produces an output of a dataset of PDF documents with the extracted text.