更新 deploy_reme_issue.md
This commit is contained in:
@@ -172,7 +172,7 @@ public class ReMeMemoryCmdRunner implements CommandLineRunner {
|
|||||||
}
|
}
|
||||||
```
|
```
|
||||||
|
|
||||||
## 对话时观测到 reme 容器抛出异常堆栈,核心异常堆栈信息如下
|
## 坑点1、因环境变量错误导致 API 调用失败(已解决)
|
||||||
|
|
||||||
```
|
```
|
||||||
2026-04-07 15:56:51 | ERROR | base_embedding_model.py:126 | embedding model name=bge-negative-train encounter error with e=('Connection error.',)
|
2026-04-07 15:56:51 | ERROR | base_embedding_model.py:126 | embedding model name=bge-negative-train encounter error with e=('Connection error.',)
|
||||||
@@ -357,13 +357,14 @@ public class ReMeMemoryCmdRunner implements CommandLineRunner {
|
|||||||
2026-04-07 15:56:51 | ERROR | load_today_memory_op.py:103 | Error retrieving today's memories: Connection error.
|
2026-04-07 15:56:51 | ERROR | load_today_memory_op.py:103 | Error retrieving today's memories: Connection error.
|
||||||
```
|
```
|
||||||
|
|
||||||
** 问题源头 **:FlowLLM 的 openai_compatible_embedding_model.py 脚本中使用的环境变量是写死的
|
FlowLLM 的 openai_compatible_embedding_model.py 脚本中使用的环境变量是写死的
|
||||||
|
|
||||||
```python
|
```python
|
||||||
self.api_key = api_key or os.getenv("FLOW_EMBEDDING_API_KEY", "")
|
self.api_key = api_key or os.getenv("FLOW_EMBEDDING_API_KEY", "")
|
||||||
self.base_url = base_url or os.getenv("FLOW_EMBEDDING_BASE_URL", "")
|
self.base_url = base_url or os.getenv("FLOW_EMBEDDING_BASE_URL", "")
|
||||||
```
|
```
|
||||||
|
|
||||||
** 修复方案 **:在 .env 文件添加正确的环境变量
|
在 .env 文件添加上正确的环境变量即可
|
||||||
|
|
||||||
```
|
```
|
||||||
LLM_API_KEY=sk-***
|
LLM_API_KEY=sk-***
|
||||||
@@ -376,7 +377,7 @@ FLOW_LLM_API_KEY=sk-***
|
|||||||
FLOW_LLM_BASE_URL=http://IP:PORT/v1
|
FLOW_LLM_BASE_URL=http://IP:PORT/v1
|
||||||
```
|
```
|
||||||
|
|
||||||
## 再次发起调用出现以下异常堆栈
|
## 坑点2、不知道问题源头(未解决)
|
||||||
|
|
||||||
```
|
```
|
||||||
2026-04-08 10:33:27 | ERROR | base_embedding_model.py:126 | embedding model name=bge-m3 encounter error with e=('Error code: 400 - {\'error\': {\'message\': \'Model "bge-m3" does not support matryoshka representation, changing output dimensions will lead to poor results.\', \'type\': \'BadRequestError\', \'param\': \'\', \'code\': 400}}',)
|
2026-04-08 10:33:27 | ERROR | base_embedding_model.py:126 | embedding model name=bge-m3 encounter error with e=('Error code: 400 - {\'error\': {\'message\': \'Model "bge-m3" does not support matryoshka representation, changing output dimensions will lead to poor results.\', \'type\': \'BadRequestError\', \'param\': \'\', \'code\': 400}}',)
|
||||||
@@ -696,5 +697,3 @@ FLOW_LLM_BASE_URL=http://IP:PORT/v1
|
|||||||
|
|
||||||
[31m[1mopenai.BadRequestError[0m:[1m Error code: 400 - {'error': {'message': 'Model "bge-m3" does not support matryoshka representation, changing output dimensions will lead to poor results.', 'type': 'BadRequestError', 'param': '', 'code': 400}}[0m
|
[31m[1mopenai.BadRequestError[0m:[1m Error code: 400 - {'error': {'message': 'Model "bge-m3" does not support matryoshka representation, changing output dimensions will lead to poor results.', 'type': 'BadRequestError', 'param': '', 'code': 400}}[0m
|
||||||
```
|
```
|
||||||
|
|
||||||
没招了,不知道咋改
|
|
||||||
Reference in New Issue
Block a user