Skip to content

fix(graphrag-llm): accept non-OpenAI service_tier values in LLMCompletionResponse #2390

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.

Sign up for GitHub

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

Open
LijuanTang94 wants to merge 1 commit into
base: main
Choose a base branch
from
+10 −0
Open

fix(graphrag-llm): accept non-OpenAI service_tier values in LLMCompletionResponse #2390

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions .semversioner/next-release/patch-2026053119245844167500.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
{
"type": "patch",
"description": "Allow non-OpenAI service_tier values in LLMCompletionResponse so indexing does not fail with LiteLLM-routed providers (e.g. Gemini via OpenRouter)."
}
6 changes: 6 additions & 0 deletions packages/graphrag-llm/graphrag_llm/types/types.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -91,6 +91,12 @@ class LLMCompletionResponse(ChatCompletion, Generic[ResponseFormat]):
provided ResponseFormat model.
"""

# Widen OpenAI's strict `service_tier` literal. Non-OpenAI providers routed
# through LiteLLM (e.g. Gemini via OpenRouter) return values outside OpenAI's
# enum, which would otherwise fail pydantic validation when constructing this
# model. graphrag-llm does not use this field. See issue #2389.
service_tier: str | None = None # type: ignore

formatted_response: ResponseFormat | None = None # type: ignore
"""Formatted response according to the specified response_format json schema."""

Expand Down