The connector now provides new server actions for Anthropic Claude version 3 models. The following models (model parameters) are currently supported
The version 3 models use a different request structure than the version 2 models. You can find detailed documentation here https://docs.anthropic.com/claude/reference/messages_post
Two utility server actions are available for creating content elements
The following values are supported for the MediaType for Image
To get started read the following blog post: Get Started with OutSystems and Amazon Bedrock
Possible Model input parameter values:
Anthropic_Claude_TextToText
claude-v2:1
claude-v2
claude-v1
claude-instant-v1
AI21_Jurassic_TextToText
j2-ultra-v1
j2-mid-v1
Amazon_Titan_TextToText
titan-text-lite-v1
titan-text-express-v1
Cohere_Command_TextToText
command-text-v14
command-light-text-v14
Meta_Llama_TextToText
llama2-13b-chat-v1
llama2-70b-chat-v1
Stability_StableDiffusion_TextToImage
stable-diffusion-xl-v0
stability.stable-diffusion-xl-v1
Cohere_Command_TextToEmbeddings
embed-english-v3
embed-multilingual-v3
--------
Amazon Bedrock Agents
New in version 1.1.1 you can invoke a configured Amazon Bedrock Agent.
The server action Bedrock_InvokeAgent takes the following parameters
The result is text generated by the agent.
Read my article on how to get started with AWS Bedrock Runtime component on my blog
https://lcnc.blog/get-started-with-outsystems-and-amazon-bedrock-80cef32a79ea
Currently this integration implements the following foundation model interactions