#7809: Permit bedrock application inference profiles #7822
+10
−0
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
dosubot
bot
added
the
size:S
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎
1 Skipped Deployment
|
dosubot
bot
added
the
auto:nit
|
invoke approach is complicated indeed but this patch looks hacky and like a workaround. I will see what I can do when i have time unless langchain team is okay for this patch. 🙏 |
|
Thanks, I think it's actually pretty clean given the meta data is parsed from the model id. All that is unavailable in the inference id arn. Curious to hear how you could do it another way with that limitation. I expect you'd need to do an intermediate lookup or supply a second field as I have. |
jacoblee93
reviewed
Mar 13, 2025
| For example, "arn%3Aaws%3Abedrock%3Aus-east-1%3A1234567890%3Aapplication-inference-profile%2Fabcdefghi", will override this.model in final /invoke URL call. | ||
| Must still provide `model` as normal modelId to benefit from all the metadata. | ||
| */ | ||
| modelAlias?: string; |
There was a problem hiding this comment.
Should we call this applicationInferenceProfile?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Fixes #7809
Bedrock Chat Model did not have a way to invoke Application Inference Profiles. Solving this was complicated at first... how do you keep all that modelId-derived metadata parsing?
So I added a
modelAliasfield that simply overridesthis.modelto be used in the /invoke URL. It expects to be URL encoded. Worked great in my local testing. You can find me on Twitter @bios_hazard