[Bug] 将.txt文件加入知识库进行分块向量化时，向量化失败。

[ALing188]

📦 部署环境

Docker

📌 软件版本

v1.27.3

💻 系统环境

Ubuntu, Other Linux

🌐 浏览器

Chrome, Edge

🐛 问题描述

不管是在对话窗口上传.txt文件，还是在知识库中上传MP4、MP3、pdf文件，在上传成功后进行分割向量化总是会分割失败。API接口接口拥有向量化的能力，也测试了其他多家API key.

📷 复现步骤

No response

🚦 期望结果

能够正常将文件向量化

📝 补充信息

[lobehubbot]

👀 @ALing188

Thank you for raising an issue. We will investigate into the matter and get back to you as soon as possible.
Please make sure you have given us as much context as possible.
非常感谢您提交 issue。我们会尽快调查此事，并尽快回复您。 请确保您已经提供了尽可能多的背景信息。

[dosubot[bot]]

Hey @ALing188! I'm here to help you with bugs, questions, and more while we wait for a human maintainer. Let's squash those bugs together! 🤖

I found some similar issues and discussions that might help you resolve the vectorization failure:

1. Closed Issue: [Bug] Can't upload docs on knowledge - This issue was related to file uploads getting stuck. The suggested solutions included checking MinIO configuration, network and firewall settings, Docker resource allocation, Logto authentication, and reviewing error logs for more insights.

2. Closed Issue: [Bug] 求助，pdf文件上传后向量化失败，不知道哪里出问题了，请指教 - The solution here was to try changing the API provider, which resolved the vectorization issue for the user.

3. Closed Issue: [Bug] database版知识库不能正常分块 - This issue was resolved by increasing the ASYNC_TASK_TIMEOUT value, which determines the maximum time allowed for the chunking task to complete before it times out.

You might want to check these areas in your setup to see if they help resolve the issue you're facing with vectorization ^[1][2][3].

To continue talking to Dosu, mention @dosu.

[ALing188]

问题已经解决，原因是api使用的接口代理地址格式不规范。

[lobehubbot]

Bot detected the issue body's language is not English, translate it automatically. 👯👭🏻🧑‍🤝‍🧑👫🧑🏿‍🤝‍🧑🏻👩🏾‍🤝‍👨🏿👬🏿

---

The problem has been solved because the interface proxy address format used by the API is not standardized.

[lobehubbot]

✅ @ALing188

This issue is closed, If you have any questions, you can comment and reply.
此问题已经关闭。如果您有任何问题，可以留言并回复。