Requirements
AI Assistant is delivered as a Docker container that you deploy to your own infrastructure. It then requires a PostgreSQL database and dedicated file storage, the latter of which can be either the PostgreSQL database itself, or any S3-compatible object storage.
The minimum requirements for AI Assistant are:
- PostgreSQL(opens in a new tab) 14, 15, or 16 with the pgvector(opens in a new tab) extension — Earlier versions may work, but they aren’t officially supported
- Docker(opens in a new tab) 1.10.0 or newer
The following cloud database services are also supported:
- Azure Database for PostgreSQL(opens in a new tab) — Refer to the Azure documentation(opens in a new tab) for information on how to enable pgvector
- Google Cloud SQL for PostgreSQL(opens in a new tab) — pgvector is enabled by default
- PostgreSQL on Amazon RDS(opens in a new tab) — pgvector is enabled by default
Nutrient Web SDK version requirements
When integrating AI Assistant 1.5.0 with Nutrient Web SDK, the minimum required version of Nutrient Web SDK is version 2024.6.0.
AI Assistant resource requirements
AI Assistant requires a certain amount of compute and memory resources to serve and process documents. However, the amount of resources used depends on many factors, including, but not limited to, the number of documents and the request load.
AI Assistant was built to run on both x86_64- and ARM64-based processors. We recommend using ARM-based hardware, since in many cases, this offers almost identical performance to x86_64 at a lower price.