# Vector databases

> Vector databases - Create a vector databases, work with versions and related assets, and interact in
> the playground.

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 `2026-05-06T18:17:09.561375+00:00` (UTC).

## Primary page

- [Vector databases](https://docs.datarobot.com/en/docs/agentic-ai/vector-database/index.html): Full documentation for this topic (HTML).

## Related documentation

- [Agentic AI](https://docs.datarobot.com/en/docs/agentic-ai/index.html): Linked from this page.
- [RAG](https://docs.datarobot.com/en/docs/reference/glossary/index.html#retrieval-augmented-generation-rag): Linked from this page.
- [Create a vector database](https://docs.datarobot.com/en/docs/agentic-ai/vector-database/vector-dbs.html#add-a-vector-database): Linked from this page.
- [appropriate](https://docs.datarobot.com/en/docs/reference/gen-ai-ref/genai-consider.html#supported-dataset-types): Linked from this page.
- [Data Registry](https://docs.datarobot.com/en/docs/agentic-ai/vector-database/vector-dbs-data.html): Linked from this page.
- [in the playground](https://docs.datarobot.com/en/docs/agentic-ai/playground-tools/build-llm-blueprints.html#add-a-vector-database): Linked from this page.
- [Versioning internal vector databases](https://docs.datarobot.com/en/docs/agentic-ai/vector-database/vector-versions.html): Linked from this page.
- [Versioning connected vector databases](https://docs.datarobot.com/en/docs/agentic-ai/vector-database/update-connected-vdbs.html): Linked from this page.
- [Register and deploy vector databases](https://docs.datarobot.com/en/docs/agentic-ai/vector-database/vector-dbs-register-deploy.html): Linked from this page.
- [Use an embedding NVIDIA NIM to create a vector database](https://docs.datarobot.com/en/docs/agentic-ai/vector-database/vector-dbs-nvidia-nim-embed.html): Linked from this page.
- [ACL hydration](https://docs.datarobot.com/en/docs/agentic-ai/vector-database/acl-hydration.html): Linked from this page.

## Documentation content

> [!NOTE] Premium
> 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.

A vector database is a collection of unstructured text that is broken into chunks, with embeddings generated for each chunk. Both the chunks and embeddings are stored in a database and are available for retrieval. Vector databases can optionally be used to ground the LLM responses to specific information and can be assigned to an LLM blueprint to leverage during a [RAG](https://docs.datarobot.com/en/docs/reference/glossary/index.html#retrieval-augmented-generation-rag) operation. The role of the vector database is to enrich the prompt with relevant context before it is sent to the LLM.

The simplified workflow for working with vector databases is as follows:

1. Create a vector databaseobject.
2. Add anappropriatedata source from theData Registry.
3. Set the configuration,embeddings, andchunking.
4. Create the vector database and add it to an LLM blueprintin the playground.

See the [considerations related to vector databases](https://docs.datarobot.com/en/docs/reference/gen-ai-ref/genai-consider.html#vector-database-considerations) for guidance when working with DataRobot GenAI capabilities.

Working with vector databases includes the following:

| Topic | Description |
| --- | --- |
| Add data sources | Add internal and external data sources; actions from the Vector databases tab in the Use Case directory. |
| Create a vector database | Create and configure a vector database. |
| Versioning internal vector databases | Use versioning to modify DataRobot-hosted internal (FAISS-based) vector databases for tracking and fine-tuning. |
| Versioning connected vector databases | Add data to an existing Pinecone-, Elasticsearch-, Milvus-, or PostgreSQL-based vector database connection. |
| Register and deploy vector databases | Send vector databases from the playground to the workshop for modification and deployment, or deploy the current vector database version directly to Console. |
| Use an embedding NVIDIA NIM to create a vector database | Premium feature. Add a registered or deployed embedding NVIDIA NIM to a Use Case with a vector database to enrich prompts in the playground with relevant context before they are sent to the LLM. |
| ACL hydration | Premium feature. ACL (Access Control List) hydration enforces fine-grained authorization for vector database results based on original document permissions from external sources such as Google Drive and SharePoint. |