How to deploy an AI assistant: Pattern 2, the control/data split (customer cloud)

Описание и применение

<p><em>A reference architecture for running the data plane of an AI assistant in the customer's own cloud account, with the provider keeping only a control plane</em></p> <p>This document describes the second of three deployment patterns for an AI assistant platform. It is written for architects and platform engineers whose customer, or whose own organisation, has said: <strong>"our documents, our search index and our encryption key stay in our cloud account, under a key we can revoke without asking anyone."</strong></p> <p>The structure is the same as Pattern 1: a one-picture architecture, th

Задача

<p><em>A reference architecture for running the data plane of an AI assistant in the customer's own cloud account, with the provider keeping only a control plane</em></p> <p>This document describes the second of three deployment patterns for an AI assistant platform. It is written for architects and platform engineers whose customer, or whose own organisation, has said: <strong>"our documents, our search index and our encryption key stay in our cloud account, under a key we can revoke without asking anyone."</strong></p> <p>The structure is the same as Pattern 1: a one-picture architecture, th

Результат

<p><em>A reference architecture for running the data plane of an AI assistant in the customer's own cloud account, with the provider keeping only a control plane</em></p> <p>This document describes the second of three deployment patterns for an AI assistant platform. It is written for architects and platform engineers whose customer, or whose own organisation, has said: <strong>"our documents, our search index and our encryption key stay in our cloud account, under a key we can revoke without asking anyone."</strong></p> <p>The structure is the same as Pattern 1: a one-picture architecture, th

Доказательства

How to deploy an AI assistant: Pattern 2, the control/data split (customer cloud)

Источник