-
Notifications
You must be signed in to change notification settings - Fork 2.2k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat(google-vertexai): Support Non-Google and Model Garden models in Vertex AI - Anthropic integration #6999
Conversation
Testing
… a way that makes sense. Add option for fetch() that determines how to handle missing MediaBlobs.
… a way that makes sense. Add option for fetch() that determines how to handle missing MediaBlobs.
Change default action if invalid blob. Add "ignore" action for invalid blobs.
Bug fix for BlobStore.store with how it handles the key
Required making some functions and methods async
# Conflicts (resolved): # libs/langchain-google-common/src/chat_models.ts # libs/langchain-google-common/src/utils/gemini.ts
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Overall looks fantastic - left some nits/comments and will try myself before cutting a release
@jacoblee93 - Thanks! Very much appreciate the feedback. Any thoughts on the problems with docs? |
…e plain object instead.
Fixes #2562
Fixes #6207
The ultimate objective is to add full support to Vertex AI for the various 3P models that are provided via API as well as custom user endpoints they may deploy for personal models
This will be done through an API object that provides methods that both turn the LangChain objects into model-API compatible objects that will be formatted in JSON as well as take the JSON result and convert it to LangChain objects.
In this first batch, we get the Gemini support integrated with this API object and add Anthropic / Claude support.
This work was supported by Google Cloud Credits provided by Google.