Flipped
Flipped
+1不知道出现什么问题
> 我是这样配的，用的智谱的embedding-2 的 api，貌似可以： > > ``` > embeddings: # 配置知识库的embedding服务，以下示例填写了两类embedding服务的配置方法，第一个是openai的embedding模型服务的配置方法，第二个是本地部署的embedding模型服务的配置方法，如果有多个可以添加多个 > embedding-2: # 知识库下拉框中显示的embedding模型的名称，可自定义 > component: openai > openai_api_base: "https://open.bigmodel.cn/api/paas/v4" > openai_api_key: "xxx" > model: "embedding-2" > ``` 我按照这种情况...
> @Upcreat thanks for the bug report. The error comes from Ollama generating the embedding for your text. Maybe our embedding model (`nomic-embed-text`) is not working with Chinese? We're working...
thank you for your reply. It was found that the problem was caused by insufficient video memory due to too much GPU usage.
ok，谢谢您！
按照教程，手动上传到阿里云的oss上面了，不知道是不是模型没理解问答的内容还是提示词没写好。大佬方便分享一下您的提示词吗
ok ,我试试