Inconcistency between Responses API and Chat Completions API on rate limit errors
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 4/5
- 预计耗时
- 3-5 天
- 新手友好度
- 55/100
- Issue 类型
- 缺陷
- 描述清晰度
- 基本清楚
- 活跃度
- 活跃
- 技术栈
- python
调研方向
从 responses.create(..., stream=True) 入口开始,将其 rate-limit 错误处理与 Chat Completions 的流式处理路径进行比较,尤其关注迭代之前的客户端重试逻辑。使用较长的输入在 Azure 托管的模型上重现,然后确定并测试在创建流以及读取流时引发的错误应具有一致的行为。
由索引模型根据 Issue 内容生成。
描述
Confirm this is an issue with the Python library and not an underlying OpenAI API
- This is an issue with the Python library
Describe the bug
I noticed that rate limit errors are raised differently in the two APIs during streaming. In chat completions the error is raised and retried by the client itself on the initial call, before reading the stream. On the other hand, the first call to responses.create(...) returns a stream object successfully and then upon reading the stream, an APIError is raised indicating a rate limit. As a result, the whole retrying logic in the client is completely skipped and the user has to implement their own. It is also unclear whether an error could be raised mid-stream which adds to the complexity of the fix.
After inspecting the client's code, I initially thought that this is not a library issue but a misalignment with the model's service. I contacted Microsoft support since they host our models but they insisted I raise an issue here.
To Reproduce
To reproduce this you would need an Azure hosted OpenAI model ( I have personally already tried this with gpt-4o and gpt-5 ). Lower your token rate limit threshold to a low enough value and use the below snippet.
Code snippets
from openai import OpenAI
client = OpenAI(
base_url = "your-endpoint-v1",
api_key="your-api-key"
)
response = client.responses.create(
model="your-model",
store=False,
stream=True,
input='a long enough prompt'*10000 # to hit a rate limit
)
for event in response:
continue # an APIError is raised here
OS
Linux, Windows
Python version
Python >=3.11.9
Library version
openai v1.109.1
- 主要语言
- Python
- 星标
- 31.9k
- 派生
- 8k
- 平均合并
- 14 小时 16 分钟
- 30 天内合并 PR
- 151
环境准备
在浏览器里用你自己的 GitHub 账号启动这个项目的开发容器。
- 没有 Dockerfile 或 Docker Compose 文件
- 有 Pull Request 模板
- 阅读贡献指南
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
openai/openai-python 的其他 Issue
-
难度 2/5 1-3 小时 新手友好度 72/100
openai/openai-python#4022 · 23 条评论 ·
维护者通常 1 天内回复
-
fix(auth): SubjectTokenProviderError drops response and duplicates error message in workload identity providers可能已有人在做 @mohmedmm 于 19 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 86/100
openai/openai-python#4017 · 5 条评论 ·
维护者通常 1 天内回复
-
Querystring drops explicit empty-string scalar values可能已有人在做 @sylvesterkaczmarek 于 41 天前认领。 未关闭sdk-breaking-change v4
难度 2/5 1-3 小时 新手友好度 86/100
openai/openai-python#3837 ·
维护者通常 1 天内回复
-
Define + export `ServiceTiers` string literal可能已有人在做 @SparshGarg999 于 68 天前认领。 未关闭
难度 2/5 1-3 小时 新手友好度 68/100
openai/openai-python#3556 · 3 条评论 ·
维护者通常 1 天内回复
-
Empty OPENAI_BASE_URL prevents fallback to default API endpoint可能已有人在做 @Sehastrajit-S 于 34 天前认领。 未关闭bug
难度 2/5 1-3 小时 新手友好度 68/100
openai/openai-python#2927 · 7 条评论 ·
维护者通常 1 天内回复
查看 openai/openai-python 的全部 Issue
相似的 Issue
-
难度 1/5 1 小时以内 新手友好度 80/100
521xueweihan/HelloGitHub#4063 ·
-
难度 2/5 1-3 小时 新手友好度 78/100
-
难度 2/5 1-3 小时 新手友好度 62/100
Vanilla-OS/apx-gui#112 ·
-
Devstral and Voxtral: section 5 fails in us-east-1 with 400 "Model does not support audio modality"未关闭
难度 2/5 1-3 小时 新手友好度 76/100
aws-samples/sample-per-model-bedrock#409 ·
维护者通常 1 天内回复
-
DuckDB 2.0 breaks to_pyarrow_batches可能已有人在做 @DG47 今天认领。 未关闭
难度 2/5 1-3 小时 新手友好度 76/100
ibis-project/ibis#12196 ·
维护者通常 1 天内回复