nilin1998

pgvector POST /knowledge_base/search_docs HTTP/1.1" 500 Internal Server Error

4

当向量知识库选用pgvector，查询向量数据库是报错，错误如下： INFO: 127.0.0.1:58621 - "POST /knowledge_base/search_docs HTTP/1.1" 500 Internal Server Error 2024-02-26 09:20:10,509 - _client.py[line:1013] - INFO: HTTP Request: POST http://127.0.0.1:7861/knowledge_base/search_docs "HTTP/1.1 500 Internal Server Error" ERROR: Exception in ASGI...

0.3.1版本中仍然出现httpx.RemoteProtocolError: peer closed connection without sending complete message body (incomplete chunked read)

11

当前选用的模型为glm4-chat,对话时报错，详细的错误为： ``` INFO: 127.0.0.1:62988 - "GET /tools HTTP/1.1" 200 OK 2024-07-16 16:39:32,138 httpx 21692 INFO HTTP Request: GET http://127.0.0.1:7861/tools "HTTP/1.1 200 OK" OpenAIChatInput( user=None, extra_headers=None, extra_query=None, extra_json=None, timeout=None, messages=[{'content': '你好',...

多卡训练占用显存

1

我在精度为fp16的情况下，单卡微调训练占用16G显存，使用多卡训练，则需要两个16G显存，但我的理解中，多卡训练时，所需的16G显存平均分到每张卡上，每张卡只占用8G显存。请问问题出在哪里了呢 单卡： 多卡：

使用demo中训练后的Lora模型，结果出现大量重复

3

加载项目中的output/adgen-chatglm-6b-lora模型，运行cli_demo.py，结果中出现了大量重复语句，如图： 

[Bug] ERROR Missing dependencies for SOCKS support.

1

### Search before asking - [x] I had searched in the [issues](https://github.com/eosphoros-ai/DB-GPT/issues?q=is%3Aissue) and found no similar issues. ### Operating system information Linux ### Python version information >=3.11 ### DB-GPT version...