💄 style: improve pdf and xlsx file parse #7783

arvinxx · 2025-05-10T11:22:28Z

💻 变更类型 | Change Type

🔀 变更说明 | Description of Change

针对 PDF 和 xlsx 优化对应的 content 解析逻辑

📝 补充信息 | Additional Information

vercel · 2025-05-10T11:22:33Z

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
lobe-chat-database	✅ Ready (Inspect)	Visit Preview		May 10, 2025 11:35am
lobe-chat-preview	✅ Ready (Inspect)	Visit Preview	💬 Add feedback	May 10, 2025 11:35am

lobehubbot · 2025-05-10T11:22:37Z

👍 @arvinxx

Thank you for raising your pull request and contributing to our Community
Please make sure you have followed our contributing guidelines. We will review it as soon as possible.
If you encounter any problems, please feel free to connect with us.
非常感谢您提出拉取请求并为我们的社区做出贡献，请确保您已经遵循了我们的贡献指南，我们会尽快审查它。
如果您遇到任何问题，请随时与我们联系。

gru-agent · 2025-05-10T11:22:51Z

TestGru Assignment

Summary

Link	CommitId	Status	Reason
Detail	`54ab0bd`	✅ Finished

Files

File	Pull Request
packages/file-loaders/src/loaders/excel/prompt.ts	❌ Failure (Can not find job finish reason, check job progress for details.)
src/server/services/mcp/index.ts	❌ Failure (Can not find job finish reason, check job progress for details.)
packages/file-loaders/src/loaders/excel/index.ts	❌ Failure (Can not find job finish reason, check job progress for details.)
packages/file-loaders/src/loaders/pdf/prompt.ts	❌ Failure (Can not find job finish reason, check job progress for details.)
packages/file-loaders/src/loaders/pdf/index.ts	❌ Failure ([Tests Failed] The test file already comprehensively covers the updated code. Any failures are due to missing fixtures or snapshots, not test code issues.)

Tip

You can @gru-agent and leave your feedback. TestGru will make adjustments based on your input

codecov · 2025-05-10T11:26:40Z

Codecov Report

All modified and coverable lines are covered by tests ✅

Project coverage is 88.64%. Comparing base (39e871f) to head (54ab0bd).
Report is 6 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #7783      +/-   ##
==========================================
+ Coverage   88.63%   88.64%   +0.01%     
==========================================
  Files         815      818       +3     
  Lines       59652    59725      +73     
  Branches     3978     5472    +1494     
==========================================
+ Hits        52873    52946      +73     
  Misses       6779     6779

Flag	Coverage Δ
app	`88.64% <100.00%> (+0.01%)`	⬆️
server	`95.65% <ø> (ø)`

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

lobehubbot · 2025-05-10T11:40:54Z

❤️ Great PR @arvinxx ❤️

The growth of project is inseparable from user feedback and contribution, thanks for your contribution! If you are interesting with the lobehub developer community, please join our discord and then dm @arvinxx or @canisminor1990. They will invite you to our private developer channel. We are talking about the lobe-chat development or sharing ai newsletter around the world.
项目的成长离不开用户反馈和贡献，感谢您的贡献! 如果您对 LobeHub 开发者社区感兴趣，请加入我们的 discord，然后私信 @arvinxx 或 @canisminor1990。他们会邀请您加入我们的私密开发者频道。我们将会讨论关于 Lobe Chat 的开发，分享和讨论全球范围内的 AI 消息。

### [Version 1.85.3](v1.85.2...v1.85.3) <sup>Released on **2025-05-10**</sup> #### 🐛 Bug Fixes - **misc**: Remove mcp client cache. #### 💄 Styles - **misc**: Improve pdf and xlsx file content parser. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: Remove mcp client cache, closes [#7776](#7776) ([0582134](0582134)) #### Styles * **misc**: Improve pdf and xlsx file content parser, closes [#7783](#7783) ([0376870](0376870)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

lobehubbot · 2025-05-10T11:55:25Z

🎉 This PR is included in version 1.85.3 🎉

The release is available on:

Your semantic-release bot 📦🚀

## [Version 1.85.0](v1.84.16...v1.85.0) <sup>Released on **2025-05-12**</sup> #### ♻ Code Refactoring - **misc**: Add perf stat support for openai factory, Remove doubao Provider, upgrade anthropic sdk. #### ✨ Features - **misc**: Support upload files direct into chat context. #### 🐛 Bug Fixes - **misc**: Fix changelog issue on desktop app, fix config import issue in the desktop version, fix desktop upload image on macOS, fix electron state init on window, fix nothing return when reset the client db, fix streamable http url valid and refactor local files to local system, fix window close issue and release Window/Linux beta, remove mcp client cache. #### 💄 Styles - **misc**: Add new gemini & Mistral models, add qwen3 for ollama, add Qwen3 models for infiniai, add reasoning tokens and token usage statistics for Google Gemini, add write file tool to local-file plugin, add Xiaohongshu crawler rules, fix init state of loading, improve pdf and xlsx file content parser, Show Aliyun Bailian tokens usage tracking. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### Code refactoring * **misc**: Add perf stat support for openai factory, closes [lobehub#7677](https://github.com/jaworldwideorg/OneJA-Bot/issues/7677) ([40464d1](40464d1)) * **misc**: Remove doubao Provider, closes [lobehub#7573](https://github.com/jaworldwideorg/OneJA-Bot/issues/7573) ([0cf3bcc](0cf3bcc)) * **misc**: Upgrade anthropic sdk, closes [lobehub#7773](https://github.com/jaworldwideorg/OneJA-Bot/issues/7773) ([39e871f](39e871f)) #### What's improved * **misc**: Support upload files direct into chat context, closes [lobehub#7751](https://github.com/jaworldwideorg/OneJA-Bot/issues/7751) ([39b790e](39b790e)) #### What's fixed * **misc**: Fix changelog issue on desktop app, closes [lobehub#7740](https://github.com/jaworldwideorg/OneJA-Bot/issues/7740) ([f0a12af](f0a12af)) * **misc**: Fix config import issue in the desktop version, closes [lobehub#7800](https://github.com/jaworldwideorg/OneJA-Bot/issues/7800) ([2cb8635](2cb8635)) * **misc**: Fix desktop upload image on macOS, closes [lobehub#7741](https://github.com/jaworldwideorg/OneJA-Bot/issues/7741) ([07d5374](07d5374)) * **misc**: Fix electron state init on window, closes [lobehub#7707](https://github.com/jaworldwideorg/OneJA-Bot/issues/7707) ([ef05b49](ef05b49)) * **misc**: Fix nothing return when reset the client db, closes [lobehub#7738](https://github.com/jaworldwideorg/OneJA-Bot/issues/7738) ([90efb13](90efb13)) * **misc**: Fix streamable http url valid and refactor local files to local system, closes [lobehub#7794](https://github.com/jaworldwideorg/OneJA-Bot/issues/7794) ([37fd5fe](37fd5fe)) * **misc**: Fix window close issue and release Window/Linux beta, closes [lobehub#7780](https://github.com/jaworldwideorg/OneJA-Bot/issues/7780) ([82c48b9](82c48b9)) * **misc**: Remove mcp client cache, closes [lobehub#7776](https://github.com/jaworldwideorg/OneJA-Bot/issues/7776) ([0582134](0582134)) #### Styles * **misc**: Add new gemini & Mistral models, closes [lobehub#7730](https://github.com/jaworldwideorg/OneJA-Bot/issues/7730) ([b7753e2](b7753e2)) * **misc**: Add qwen3 for ollama, closes [lobehub#7746](https://github.com/jaworldwideorg/OneJA-Bot/issues/7746) ([806d905](806d905)) * **misc**: Add Qwen3 models for infiniai, closes [lobehub#7657](https://github.com/jaworldwideorg/OneJA-Bot/issues/7657) ([edd1732](edd1732)) * **misc**: Add reasoning tokens and token usage statistics for Google Gemini, closes [lobehub#7501](https://github.com/jaworldwideorg/OneJA-Bot/issues/7501) ([b466b42](b466b42)) * **misc**: Add write file tool to local-file plugin, closes [lobehub#7684](https://github.com/jaworldwideorg/OneJA-Bot/issues/7684) ([e22e932](e22e932)) * **misc**: Add Xiaohongshu crawler rules, closes [lobehub#7717](https://github.com/jaworldwideorg/OneJA-Bot/issues/7717) ([cc3724d](cc3724d)) * **misc**: Fix init state of loading, closes [lobehub#7694](https://github.com/jaworldwideorg/OneJA-Bot/issues/7694) ([1d97a68](1d97a68)) * **misc**: Improve pdf and xlsx file content parser, closes [lobehub#7783](https://github.com/jaworldwideorg/OneJA-Bot/issues/7783) ([0376870](0376870)) * **misc**: Show Aliyun Bailian tokens usage tracking, closes [lobehub#7660](https://github.com/jaworldwideorg/OneJA-Bot/issues/7660) ([3ef0542](3ef0542)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

* remove cache * improve caching

### [Version 1.85.3](lobehub/lobe-chat@v1.85.2...v1.85.3) <sup>Released on **2025-05-10**</sup> #### 🐛 Bug Fixes - **misc**: Remove mcp client cache. #### 💄 Styles - **misc**: Improve pdf and xlsx file content parser. <br/> <details> <summary><kbd>Improvements and Fixes</kbd></summary> #### What's fixed * **misc**: Remove mcp client cache, closes [lobehub#7776](lobehub#7776) ([a580435](lobehub@a580435)) #### Styles * **misc**: Improve pdf and xlsx file content parser, closes [lobehub#7783](lobehub#7783) ([4eb8643](lobehub@4eb8643)) </details> <div align="right"> [![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top) </div>

arvinxx added 2 commits May 10, 2025 14:31

remove cache

d2adba1

improve caching

54ab0bd

dosubot bot added the size:M This PR changes 30-99 lines, ignoring generated files. label May 10, 2025

arvinxx changed the title ~~style/improve-pdf-xlsx-parse~~ 💄 style: improve pdf and xlsx file parse May 10, 2025

vercel bot deployed to Preview – lobe-chat-preview May 10, 2025 11:33 View deployment

vercel bot deployed to Preview – lobe-chat-database May 10, 2025 11:35 View deployment

arvinxx merged commit 0376870 into main May 10, 2025
23 checks passed

arvinxx deleted the style/improve-pdf-xlsx-parse branch May 10, 2025 11:40

lobehubbot added the released label May 10, 2025

bbbugg pushed a commit to bbbugg/lobe-chat that referenced this pull request Aug 14, 2025

💄 style: improve pdf and xlsx file content parser (lobehub#7783)

4eb8643

* remove cache * improve caching

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

💄 style: improve pdf and xlsx file parse #7783

💄 style: improve pdf and xlsx file parse #7783

Uh oh!

arvinxx commented May 10, 2025 •

edited

Loading

Uh oh!

vercel bot commented May 10, 2025 •

edited

Loading

Uh oh!

lobehubbot commented May 10, 2025

Uh oh!

gru-agent bot commented May 10, 2025 •

edited

Loading

Uh oh!

codecov bot commented May 10, 2025 •

edited

Loading

Uh oh!

Uh oh!

lobehubbot commented May 10, 2025

Uh oh!

lobehubbot commented May 10, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Uh oh!

💄 style: improve pdf and xlsx file parse #7783

💄 style: improve pdf and xlsx file parse #7783

Uh oh!

Conversation

arvinxx commented May 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

💻 变更类型 | Change Type

🔀 变更说明 | Description of Change

📝 补充信息 | Additional Information

Uh oh!

vercel bot commented May 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

lobehubbot commented May 10, 2025

Uh oh!

gru-agent bot commented May 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

TestGru Assignment

Summary

Files

Uh oh!

codecov bot commented May 10, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Codecov Report

Uh oh!

Uh oh!

lobehubbot commented May 10, 2025

Uh oh!

lobehubbot commented May 10, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

arvinxx commented May 10, 2025 •

edited

Loading

vercel bot commented May 10, 2025 •

edited

Loading

gru-agent bot commented May 10, 2025 •

edited

Loading

codecov bot commented May 10, 2025 •

edited

Loading