Fix URL construction bug and add proxy server warnings for Gemini models #13698
+17
−3
Conversation
This file contains hidden or 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
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
| ) | ||
| raise VertexAIError( | ||
| status_code=error_code, | ||
| message=f"{err.response.text or 'Not Found'} | {hint}", |
There was a problem hiding this comment.
this will throw an error on python 3.8
can you avoid using |
| @@ -301,7 +301,7 @@ def _check_custom_proxy( | |||
| """ | |||
| if api_base: | |||
| if custom_llm_provider == "gemini": | |||
| url = "{}:{}".format(api_base, endpoint) | |||
| url = "{}/{}".format(api_base.rstrip("/"), endpoint.lstrip("/")) | |||
There was a problem hiding this comment.
the : is for google ai studio calls because that's how the endpoint is constructed.
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent" \
see :generateContent
Your changes would cause these requests to fail @kankute-sameer
krrishdholakia
requested changes
Aug 19, 2025
Insh3ll
reviewed
Aug 20, 2025
| @@ -301,7 +301,7 @@ def _check_custom_proxy( | |||
| """ | |||
| if api_base: | |||
| if custom_llm_provider == "gemini": | |||
| url = "{}:{}".format(api_base, endpoint) | |||
| url = "{}/{}".format(api_base.rstrip("/"), endpoint.lstrip("/")) | |||
There was a problem hiding this comment.
api_base + endpoint seems to still be missing the model information
If api_base=https://api.example.com/v1beta, appending the generateContent endpoint results in the URL https://api.example.com/v1beta:generateContent.
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Outdated suggestions cannot be applied.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.
Fix URL construction bug and add proxy server warnings for Gemini models
Relevant issues
Fixes #13693 - Invalid port error when using Gemini models with LiteLLM proxy server
Pre-Submission checklist
Please complete all items before asking a LiteLLM maintainer to review your PR
tests/litellm/directory, Adding at least 1 test is a hard requirement - see detailsmake test-unitType
🐛 Bug Fix
🧹 Refactoring
Changes
Bug Fix: URL Construction Error
_check_custom_proxymethod"{}:{}".format(api_base, endpoint)to"{}/{}".format(api_base.rstrip('/'), endpoint.lstrip('/'))Invalid port: '4000:generateContent'errorEnhanced Error Handling
api_baseWe have NOT fixed the fundamental architectural issue where Gemini models automatically route to
/generateContentendpoints when using a LiteLLM proxy server.What Still Happens
/generateContentendpointcustom_llm_provider="openai"as a workaroundWhy This Can't Be Fully Fixed Here
This is a design-level architectural mismatch between:
api_baseforvertex_ai_betamodels #4317)