Code walkthroughs¶
Availability information
DataRobot's GenAI capabilities are a premium feature; contact your DataRobot representative for enablement information. Try this functionality for yourself in a limited capacity in the DataRobot trial experience.
For code-first users, the following sections provide code samples that create and validate external vector databases and LLMs. Additionally, use the end-to-end notebook to walk through a comprehensive overview of GenAI features.
See the list of considerations to keep in mind when working with DataRobot GenAI.
| Topic | Description |
|---|---|
| End-to-end code-first generative AI experimentation | A comprehensive overview of the generative AI features DataRobot has to offer with the Python API client. |
| Create and deploy a vector database | How to use the Python SDK to create and deploy DataRobot vector databases using built-in embeddings. For custom embedding models (BYO embeddings), see the separate notebook below. |
| Create vector databases from BYO embeddings | How to build, validate, and register an external vector database from bring-your-own (BYO) embeddings. |
| Create external LLMs with code | How to set up and validate an external LLM using DataRobot's Python API client. |
| Use the DataRobot LLM gateway | How to use the OpenAI Python library to make chat completion requests directly to the DataRobot LLM gateway. |
| Agentic workflow with code | How to use a simple agentic workflow to serve, monitor, and govern the workflow. |
| Use the Bolt-on Governance API | How to use the OpenAI Python library to make chat completion requests to a deployed LLM blueprint. |
| Create a ChromaDB vector database | How to load in and host a ChromaDB in-memory vector store, with metadata filtering, within a custom model. |
| Build and host a Qdrant vector database | How to build, validate, and register a Qdrant vector database to the DataRobot application using DataRobot's Python API client. |