load vertex_credentials on every call #8068
Open
+10
−16
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Outdated suggestions cannot be applied.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.
Title
Load Vertex credentials on every completion call (dont cache the access token library wide)
Relevant issues
Fixes #7904
Type
🐛 Bug Fix
Changes
In VertexLLM base, respect the
vertex_credentials
passed into acompletion
on every single call. Prior to this,access_token
was being saved and any subsequent calls to a Vertex model with invalid credentials was still succeeding when it should not have. More info in the bug ticket above.[REQUIRED] Testing - Attach a screenshot of any new tests passing locally
Was unable to run tests locally after doing a poetry install, some required packages are not included ...
e.g.
And a couple others,
opentelemetry
, etc