From 0c57bc57c01f2787cde91d9b845eb1f697d03612 Mon Sep 17 00:00:00 2001 From: Ian Saultz <52051793+atierian@users.noreply.github.com> Date: Wed, 19 Feb 2025 09:05:09 -0500 Subject: [PATCH] add supported models callout w link to setup, conversation, and generation pages --- src/pages/[platform]/ai/conversation/index.mdx | 4 ++++ src/pages/[platform]/ai/generation/index.mdx | 4 ++++ src/pages/[platform]/ai/set-up-ai/index.mdx | 8 ++++++-- 3 files changed, 14 insertions(+), 2 deletions(-) diff --git a/src/pages/[platform]/ai/conversation/index.mdx b/src/pages/[platform]/ai/conversation/index.mdx index b9ed364ff48..6af2667f970 100644 --- a/src/pages/[platform]/ai/conversation/index.mdx +++ b/src/pages/[platform]/ai/conversation/index.mdx @@ -34,6 +34,10 @@ export function getStaticProps(context) { The conversation route simplifies the creation of AI-powered conversation interfaces in your application. It automatically sets up the necessary AppSync API components and Lambda functions to handle streaming multi-turn interactions with Amazon Bedrock foundation models. + +See [Supported Providers and Models](/[platform]/ai/concepts/models/#supported-providers-and-models) for a list of supported AI models. + + ## Key Components 1. **AppSync API**: Gateway to the conversation route. diff --git a/src/pages/[platform]/ai/generation/index.mdx b/src/pages/[platform]/ai/generation/index.mdx index 674e6bf4e43..c3e4d6b5eeb 100644 --- a/src/pages/[platform]/ai/generation/index.mdx +++ b/src/pages/[platform]/ai/generation/index.mdx @@ -34,6 +34,10 @@ AI generation routes are a request-response API used to generate structured outp - generated structured data from unstructured input - summarization + +See [Supported Providers and Models](/[platform]/ai/concepts/models/#supported-providers-and-models) for a list of supported AI models. + + Under the hood, a generation route is an AWS AppSync query that ensures the AI model responds with the response type defined for the route. ## Generate Typed Objects diff --git a/src/pages/[platform]/ai/set-up-ai/index.mdx b/src/pages/[platform]/ai/set-up-ai/index.mdx index 7526472567a..a021cadf1c6 100644 --- a/src/pages/[platform]/ai/set-up-ai/index.mdx +++ b/src/pages/[platform]/ai/set-up-ai/index.mdx @@ -67,7 +67,7 @@ Then run the [Amplify sandbox](/[platform]/deploy-and-host/sandbox-environments/ npx ampx sandbox ``` -This will provision the cloud resources you define in your amplify folder and watch for updates and redeploy them. +This will provision the cloud resources you define in your amplify folder and watch for updates and redeploy them. ## Build your AI backend @@ -77,6 +77,10 @@ To build an AI backend, you define AI 'routes' in your Amplify Data schema. An A * **Conversation:** A conversation route is a streaming, multi-turn API. Conversations and messages are automatically stored in DynamoDB so users can resume conversations. Examples of this are any chat-based AI experience or conversational UI. * **Generation:** A single synchronous request-response API. A generation route is just an AppSync Query. Examples of this are: generating alt text for an image, generating structured data from unstructured input, summarization, etc. + +See [Supported Providers and Models](/[platform]/ai/concepts/models/#supported-providers-and-models) for a list of supported AI models. + + To define AI routes, open your **amplify/data/resource.ts** file and use `a.generation()` and `a.conversation()` in your schema. ```ts title="amplify/data/resources.ts" @@ -119,7 +123,7 @@ Conversation routes currently ONLY support owner-based authorization and generat -If you have the Amplify sandbox running, when you save this file it will pick up the changes and redeploy the necessary resources for you. +If you have the Amplify sandbox running, when you save this file it will pick up the changes and redeploy the necessary resources for you. ## Connect your frontend