mirror of
https://github.com/zenlm/zen-blog.git
synced 2026-11-03 14:11:45 +00:00
zeekay
7af02e40e8
- Replace Hugo static site generator with Next.js 15 + fumadocs-mdx - Convert 71 blog posts from Hugo format to MDX/MD - Convert Hugo shortcodes (figure, button, video, example, fullwidth) to MDX components (Figure, LinkButton, Video, Fullwidth) - Add remark-math + rehype-katex for LaTeX math rendering - Copy JSON case files to public/cases/ for reference - Update branding for Zen LM (site-nav, footer, metadata) - Static export for Cloudflare Pages deployment - Chinese (.zh.md) translations deferred for future migration
13 lines
1014 B
JSON
13 lines
1014 B
JSON
{
|
|
"title": "Example: Text Information Recognition & Processing",
|
|
"messages": [
|
|
{
|
|
"role": "User",
|
|
"content": "A brief summary of the blog\n{{< figure src=\"http://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen-VL/blog/4_text_information_2.jpeg\" width=\"8%\">}}"
|
|
},
|
|
{
|
|
"role": "Qwen-VL",
|
|
"content": "The blog post announces several new updates and improvements to OpenAI's platform, including:\n\n* GPT-4 Turbo with a 128K context window, which is more capable and supports a 128K context window.\n* New Assistants API that makes it easier for developers to build their own assistive AI apps and tools.\n* New multimodal capabilities in the platform, including text-to-speech (TTS).\n* Improved instruction following and JSON mode.\n* Reproducible outputs and log probabilities.\n* Updated GPT-3.5 Turbo with a 16K context window by default.\n\nThe post also mentions that these updates will be rolled out to all paying customers starting at 10am PT today."
|
|
}
|
|
]
|
|
} |