Error raised by inference endpoint: HTTPConnectionPool(host='127.0.0.1', port=11434)

[yeakyang]

Error raised by inference endpoint: HTTPConnectionPool(host='127.0.0.1', port=11434): Max retries exceeded with url: /api/embeddings (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x7a18763b48e0>: Failed to establish a new connection: [Errno 111] Connection refused'))

在初始化知识库chatchat kb -r时出现以上错误，请问如何解决？？

[dosubot[bot]]

@yeakyang 你好！我是Dosu，一个可以帮助你解决问题，回答你的疑问，并成为贡献者的机器人。在等待人类维护者的过程中，我将竭诚为你服务。

I found some similar threads regarding the "Connection refused" error when attempting to connect to the service on port 11434:

1. In an open issue, the suggested solution is to delete the chatchat_data directory and then re-run chatchat kb -r ^[1].
2. Another open issue suggests installing the xinference-client package using pip install xinference-client, ensuring the service is running, and registering the local models in the xinference platform ^[2].
3. A closed issue recommends upgrading the langchain version to 0.0.266 and rebuilding the knowledge base. If the issue persists, pulling the latest code from the repository might help, as the problem was fixed in a recent update ^[3].

These solutions might help resolve the connection issue you're experiencing.

To continue talking to Dosu, mention @dosu.

---

^{Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other}

[github-actions[bot]]

这个问题已经被标记为 stale ，因为它已经超过 30 天没有任何活动。

[github-actions[bot]]

这个问题已经被自动关闭，因为它被标为 stale 后超过 14 天没有任何活动。