yujunjun/midscene
1
0
Fork 0
mirror of https://github.com/web-infra-dev/midscene.git synced 2026-01-06 12:11:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs: lazy loading report.gif (#503)

Browse Source
This commit is contained in:
neverland 2025-03-26 11:40:04 +08:00 committed by GitHub
parent 1f3fc5b580
commit dcf6296dc2
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
apps/site/docs/en/index.mdx
View File

@ -62,7 +62,7 @@ Midscene wants to provide a way to make automation more stable and easier to deb
What's more, there is a playground in the report file for you to adjust your prompt without re-running all your scripts.
<p align="center">
<img src="/report.gif" alt="visualized report" />
<img src="/report.gif" alt="visualized report" loading="lazy" />
</p>
## Support both general-purpose LLM and open-source model

3
apps/site/docs/zh/index.mdx
View File

@ -48,10 +48,9 @@ Midscene 希望让自动化脚本变得更稳定、更易于调试，因此我
此外，Midscene 报告里还集成了一个 Playground，用以在报告中重新运行 Prompt 并进行调优。
<p align="center">
<img src="/report.gif" alt="visualized report" />
<img src="/report.gif" alt="visualized report" loading="lazy" />
</p>
## 自定义模型
Midscene 同时支持通用 LLM 和开源模型。你可以使用通用的 LLM 模型，如 `gpt-4o`，它在大多数场景都表现很好。