-
model_settings.yaml中配置了xinference的http地址
RAG对话没有任何问题。可以使用。
但是多功能对话报错了，后台日志：
-
chat.py里get_ChatOpenAI创建model为什么把loacl_wrap设置成True？
这样openai_api_base=127.0.0.1:7861/v1但是xinference的接口不是127.0.0.1:9997/v1么？
 and found no similar issues.
### Operating system information
Linux
### P…
yuerf updated
1 month ago
-
### System Info / 系統信息
Python: Python 3.10.14
os:
```
DISTRIB_ID=Kylin
DISTRIB_RELEASE=V10
DISTRIB_CODENAME=kylin
DISTRIB_DESCRIPTION="Kylin V10 SP1"
DISTRIB_KYLIN_RELEASE=V10
DISTRIB_VER…
-
### System Info / 系統信息
centos7，docker:26.0.0
### Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？
- [X] docker / docker
- [ ] pip install / 通过 pip install 安装
- [ ] installation from sou…
-
### System Info / 系統信息
**Master node use pip install
Worker node use docker**
- Ubuntu 22.04
- RTX 4090
- CUDA Version: 11.8
- Nvidia Driver Version: 550.90.07
- torch :2.3.1
- python: 3…
-
**问题描述 / Problem Description**
向知识库上传文档时，调整了chunk_size和chunk_overlap的值，均未超过1000
但是上传失败了
**复现问题的步骤 / Steps to Reproduce**
1. 设置chunk_size=700 chunk_overlap=300
2. 上传文档
**预期的结果 / Expected Resu…
-
### Do you need to file an issue?
- [x] I have searched the existing issues and this feature is not already filed.
- [ ] My model is hosted on OpenAI or Azure. If not, please look at the "model pr…
-
### Describe the bug
我们在压测xinference时候发现，V100 2卡，调用/v1/chat/completions接口，stream参数是True，模型用qwen-14b-chat，用jmeter10并发进行压测，压测1分钟xinference就挂了，如果stream是False,是可以的.
### 报错日志
```
2024-07-08 11:34:3…