> ## Documentation Index
> Fetch the complete documentation index at: https://sambanova-systems.mintlify.site/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# DataRobot integration guide

DataRobot is an enterprise AI platform that enables organizations to build, deploy, and govern predictive and generative AI models at scale. It provides an end-to-end environment for model lifecycle management, including custom LLM deployments, RAG blueprints, and agentic workflows.

## Overview

Integrate SambaNova models directly into DataRobot Workbench as custom managed LLMs. Once connected, you can:

* Use SambaNova models inside RAG and Agentic Workflows
* Interact with models via Playground chat
* Manage deployments with full governance and monitoring through DataRobot

<Note>
  For detailed implementation guidance, see the [Full SambaNova DataRobot Integration guide](https://github.com/sambanova/integrations/blob/main/datarobot/README.md).
</Note>

## Prerequisites

Before you begin, ensure you have:

* A [SambaCloud](http://cloud.sambanova.ai?utm_source=datarobot\&utm_medium=external\&utm_campaign=cloud_signup) account with an API key
* Access to DataRobot Workbench, Console, and Registry

### Required files

Download the following files from the [SambaNova integrations repository](https://github.com/sambanova/integrations/tree/main/datarobot):

* [`custom.py`](https://github.com/sambanova/integrations/blob/main/datarobot/custom.py) — defines the chat and load\_model DataRobot hooks
* [`requirements.txt`](https://github.com/sambanova/integrations/blob/main/datarobot/requirements.txt) — minimal dependencies (`sambanova`, `pandas`)
* [`model-metadata.yaml`](https://github.com/sambanova/integrations/blob/main/datarobot/model-metadata.yaml) — runtime parameters configuration

## Setup

Follow these steps to deploy a SambaNova-powered model inside DataRobot:

1. Create a Custom Model
   * Navigate to **Registry → Workshop → + Add Model**
   * Select **Proxy** type with `TextGeneration` target type
   * Upload your `custom.py`, `requirements.txt`, and `model-metadata.yaml` files
2. Build Environment
   * Select `[GenAI] Python 3.12 with Moderations` as the base environment
   * Click **Build** and wait for "Environment built successfully" confirmation
3. Configure Runtime Parameters

   Open the runtime parameter editor and configure the following:

   * `SAMBANOVA_API_KEY` → your SambaNova API token
   * `SAMBANOVA_API_BASE` → `https://api.sambanova.ai/v1`
   * `SAMBANOVA_MODEL` → `gpt-oss-120b`

     <img src="https://mintcdn.com/sambanova-systems/Al7Ln4u2kYfZDFqv/images/docs/integrations/datarobot/custom_model.png?fit=max&auto=format&n=Al7Ln4u2kYfZDFqv&q=85&s=90ba94db87bfd0057a97f8479fa2ac13" alt="DataRobot Custom model setting page" width="2346" height="1265" data-path="images/docs/integrations/datarobot/custom_model.png" />
4. Register your custom SambaNova model in the DataRobot Registry.
5. Deploy the Model
   * Go to **Registry → Models → Deploy**
   * Select your previously registered custom model
   * Wait until the deployment status shows **Active**

     <img src="https://mintcdn.com/sambanova-systems/Al7Ln4u2kYfZDFqv/images/docs/integrations/datarobot/deployment.png?fit=max&auto=format&n=Al7Ln4u2kYfZDFqv&q=85&s=e3403386520c23de1637589340884c0c" alt="DataRobot model deployment page" width="1898" height="715" data-path="images/docs/integrations/datarobot/deployment.png" />
6. Link to RAG or Agentic Workflow
   * In **Workbench**, create a new GenAI RAG use case
   * Navigate to **Playground → Create LLM blueprint → Add deployed LLM**
   * Select your deployment (e.g., `SambaNova Chat`)
   * Set **Chat model ID** to the SambaNova model name (e.g., `gpt-oss-120b`)
   * Validate and add the configuration
   * Configure your vector store, system prompt, and history management settings

Your RAG workflow is now powered by a live SambaNova model routed through DataRobot's managed deployment layer.

<img src="https://mintcdn.com/sambanova-systems/Al7Ln4u2kYfZDFqv/images/docs/integrations/datarobot/usage.png?fit=max&auto=format&n=Al7Ln4u2kYfZDFqv&q=85&s=8885e593f35e00df122df54f3a5760c2" alt="DataRobot RAG Playground with SambaNova models" width="1468" height="977" data-path="images/docs/integrations/datarobot/usage.png" />

## Additional resources

Learn more about DataRobot's capabilities:

* [DataRobot GenAI Overview](https://docs.datarobot.com/en/docs/gen-ai/index.html)
* [DataRobot Custom Models API (DRUM)](https://docs.datarobot.com/en/docs/api/reference/drum/index.html)
* [DataRobot GenAI Walkthrough](https://docs.datarobot.com/en/docs/get-started/gs-dr5/genai-walk-basic.html)