feat(grpc): add generation request semantics (#32588)

Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
This commit is contained in:
Connor Carpenter
2026-08-04 18:53:45 -07:00
committed by GitHub
co-authored by ishandhanani Alex Nails
parent 29831d58ef
commit a0b04dbe4c
10 changed files with 982 additions and 86 deletions
+3 -2
View File
@@ -895,7 +895,7 @@ async def generate_request(obj: GenerateReqInput, request: Request):
"error": {
"message": str(e),
"type": "invalid_request_error",
"code": 400,
"code": getattr(e, "status_code", 400),
"retryable": False,
}
}
@@ -2048,7 +2048,8 @@ async def vertex_generate(
def _create_error_response(e):
return ORJSONResponse(
{"error": {"message": str(e)}}, status_code=HTTPStatus.BAD_REQUEST
{"error": {"message": str(e)}},
status_code=getattr(e, "status_code", HTTPStatus.BAD_REQUEST),
)