Update openai package to stream response by non-reasoning models

Older package (like 1.84.0) seem to always pass reasoning_effort
argument to openai api, which now seems to be throwing unexpected
request argument error when used with non-reasoning models (like
4o-mini).
This commit is contained in:
Debanjum
2025-06-10 19:40:57 -07:00
parent 9b767438e2
commit 985a982148

View File

@@ -42,7 +42,7 @@ dependencies = [
"fastapi >= 0.110.0",
"python-multipart >= 0.0.7",
"jinja2 == 3.1.6",
"openai >= 1.0.0",
"openai >= 1.86.0",
"tiktoken >= 0.3.2",
"tenacity >= 9.0.0",
"magika ~= 0.5.1",