binary-husky / binary-husky/gpt_academic
[Bug]: Traceback (most recent call last): File ".\request_llms\bridge_chatgpt.py", line 316, in predict raise ValueError(f'无法读取以下数据，请检查配置。\n\n{chunk_decoded}') ValueError: 无法读取以下数据，请检查配置。
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 71.4k
- Forks
- 8.3k
- PR merge metrics
- No merged PRs in 30d
Description
Installation Method | 安装方法与平台
OneKeyInstall (一键安装脚本-windows)
Version | 版本
Latest | 最新版
OS | 操作系统
Windows
Describe the bug | 简述
当回复文字过长时出现以下报错（token长度设置正常）
Traceback (most recent call last):
File ".\request_llms\bridge_chatgpt.py", line 316, in predict
raise ValueError(f'无法读取以下数据，请检查配置。\n\n{chunk_decoded}')
ValueError: 无法读取以下数据，请检查配置。
: ping - 2024-08-11 11:59:38.557353
出现问题后先出现解析不和常规的错误，之后炸出一大串json文本，其中包含回复的内容但被分散到了每一个json中，
我看到issues里有一个类似的但因为我的模型是本地部署运行的不存在网络连接问题，并且较短回复是正常的，
Screen Shot | 有帮助的截图
（2图这里是部分）
Terminal Traceback & Material to Help Reproduce Bugs | 终端traceback（如有） + 帮助我们复现的测试材料样本（如有）
No response
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start in request_llms/bridge_chatgpt.py at predict line 316 and inspect how streamed response chunks are decoded when a local model returns a long reply. Reproduce the Windows OneKeyInstall case with a long response; done means the reply is parsed without the ValueError or fragmented JSON output.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, backend
- Issue type
- Bug
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 35/100