chore: upgrade litellm to 1.77.5+ to support latest OpenAI models #707
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
Update litellm dependency from 1.67.4/1.61.11 to 1.77.5+ to add support for newer OpenAI models including GPT-5.2 series (gpt-5.2-instant, gpt-5.2-thinking, gpt-5.2-pro) and other recent model releases. Changes: - backend: litellm 1.67.4 -> 1.80.0 - core: litellm 1.61.11 -> 1.80.13 This resolves "Unknown model" errors when using newer OpenAI models with OpenAI-like providers.
Contributor
|
The latest updates on your projects. Learn more about Vercel for GitHub.
2 Skipped Deployments
|
Mini256
added a commit
that referenced
this pull request
Jan 9, 2026
## Summary Update minimum version requirements for llama-index packages to match the versions already installed as dependencies of litellm 1.80.0: - **llama-index-llms-openai**: `0.6.5` → `0.6.12` - **llama-index-llms-openai-like**: `0.3.3` → `0.5.3` ## Motivation After upgrading litellm to 1.80.0 in #707, these llama-index packages were automatically upgraded as transitive dependencies. This PR explicitly updates the minimum version requirements in `pyproject.toml` to: - Document the actual versions being used - Ensure compatibility with the latest OpenAI models - Prevent accidental downgrades in future dependency resolutions ## Changes - Updated `backend/pyproject.toml`: - `llama-index-llms-openai>=0.6.12` (was 0.6.5) - `llama-index-llms-openai-like>=0.5.3` (was 0.3.3) ## Testing - ✅ Verified packages are already at these versions (installed as litellm dependencies) - ✅ No new packages need to be installed (`uv sync` completed with no changes) - ✅ Confirmed versions with `uv pip list`: - llama-index-llms-openai: 0.6.12 - llama-index-llms-openai-like: 0.5.3 ## Related PRs - #707 - Initial litellm upgrade that brought in these versions as dependencies
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.
Summary
Upgrade dependencies to support newer OpenAI models including GPT-5.2 series:
1.67.4→1.80.0(backend),1.61.11→1.80.13(core)0.6.5→0.6.120.3.3→0.5.3Motivation
The current versions don't recognize newer OpenAI models like GPT-5.2 series, causing "Unknown model" errors when using OpenAI-like providers. This update adds support for:
Changes
Backend (
backend/pyproject.toml)litellm>=1.77.5llama-index-llms-openai>=0.6.12llama-index-llms-openai-like>=0.5.3Core (
core/pyproject.toml)litellm>=1.77.5Lock Files
backend/uv.lockandcore/uv.lockwithuv syncTesting
References