xlsx，pdf均会分块失败

[minemine-m]

📦 部署环境

Docker

📦 部署模式

服务端模式(lobe-chat-database 镜像)

📌 软件版本

1.73.0

💻 系统环境

Other Linux

🌐 浏览器

Edge

🐛 问题描述

xlsx，pdf均会分块失败

📷 复现步骤

No response

🚦 期望结果

No response

📝 补充信息

No response

[lobehubbot]

👀 @minemine-m

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。

[lobehubbot]

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

---

📦 Deployment environment

Docker

📦 Deployment mode

Server-side mode (lobe-chat-database mirror)

📌 Software version

1.73.0

💻 System environment

Other Linux

🌐 Browser

Edge

🐛 Question description

xlsx, pdf will fail in chunking

📷 Reproduction steps

No response

🚦 Expected results

No response

📝 Supplementary information

No response

[soulgod001]

正常的，不支持xlsx，pdf不记得了，文档里有写要集成Unstructured，不过我到现在还没找到咋集成

[lobehubbot]

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

---

Normal, does not support xlsx, I don't remember pdf, I wrote in the document to integrate Unstructed, but I haven't found how to integrate

[jackywang75]

感觉文件向量化处理这块，lobechat明显不如cherry studio。
目前两个工具都用，感觉lobechat还有很多的待提高空间。

[lobehubbot]

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

---

It feels that lobechat is obviously not as good as cherry studio in file vector processing.
Currently both tools are used, and I feel that lobechat still has a lot of room to improve.

[Steve235lab]

PDF必须是做过OCR处理的才能分块成功，你可以试试先用ocrmypdf在本地处理一下再上传分块

[lobehubbot]

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

---

PDF must be processed by OCR before blocking successfully. You can try to use ocrmypdf to process locally before uploading chunking.