Using the Bidirectional Streaming API

[zhou-san]

Package

langchain-aws

Checked other resources

• I added a descriptive title to this issue
• I searched the LangChain documentation with the integrated search
• I used the GitHub search to find a similar issue and didn't find it
• I am sure this is a feature request and not a bug report or question

Feature Description

I would like to use langchain-aws to communicate with Nova 2 Sonic Model.

From the official doc: https://docs.aws.amazon.com/nova/latest/userguide/speech-bidirection.html, it requires to call InvokeModelWithBidirectionalStream API. Wondering if it's supported in langchain-aws.

Thanks

Use Case

for using Nova 2 Sonic model

Proposed Implementation (optional)

Additional Context

https://docs.aws.amazon.com/nova/latest/userguide/speech-bidirection.html

[huankimtran]

Hi team, any update on this? Looking forward for this as well!