> For the complete documentation index, see [llms.txt](https://dnotifier.gitbook.io/product-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://dnotifier.gitbook.io/product-docs/integrations/integrations.md).

# Integrations

Connect a language model, a vector store, and an embedding model, then name them from the SDK.

| Integration          | What you set                                       | Guide                                                                                          |
| -------------------- | -------------------------------------------------- | ---------------------------------------------------------------------------------------------- |
| **LLM providers**    | `provider` and `model` on `sendAI` or on an agent  | [LLM providers](https://dnotifier.gitbook.io/product-docs/integrations/llm-providers.md)       |
| **Vector stores**    | `vectorStore` on the client or on a knowledge call | [Vector stores](https://dnotifier.gitbook.io/product-docs/integrations/vector-stores.md)       |
| **Embedding models** | `embedding` on the client or on a knowledge call   | [Embedding models](https://dnotifier.gitbook.io/product-docs/integrations/embedding-models.md) |

LLM keys are saved in the dashboard under **Projects → AI Studio → Providers**. Vector store and embedding settings are passed from your app on the knowledge-base calls.

Leave the vector store and embedding unset to use Postgres and the embedding model on your subscription.
