diff --git a/README.md b/README.md index 42903b60..12ffd907 100644 --- a/README.md +++ b/README.md @@ -26,11 +26,12 @@ https://github.com/user-attachments/assets/9d60a3e8-4a1c-4b5e-acbb-26af2d3eabd1 ## Table of Contents -- [Next AI Draw.io ](#next-ai-drawio-) +- [Next AI Draw.io](#next-ai-drawio) - [Table of Contents](#table-of-contents) - [Examples](#examples) - [Features](#features) - [MCP Server (Preview)](#mcp-server-preview) + - [Claude Code CLI](#claude-code-cli) - [Getting Started](#getting-started) - [Try it Online](#try-it-online) - [Run with Docker (Recommended)](#run-with-docker-recommended) @@ -131,7 +132,7 @@ No installation needed! Try the app directly on our demo site: [![Live Demo](./public/live-demo-button.svg)](https://next-ai-drawio.jiang.jp/) -> Note: Due to high traffic, the demo site currently uses minimax-m2. For best results, we recommend self-hosting with Claude Sonnet 4.5 or Claude Opus 4.5. +> Note: Thanks to [ByteDance Doubao](https://console.volcengine.com/ark/region:ark+cn-beijing/overview?briefPage=0&briefType=introduce&type=new&utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project) sponsorship, the demo site now uses the powerful K2-thinking model! For best results, we recommend self-hosting with Claude Sonnet 4.5 or Claude Opus 4.5. > **Bring Your Own API Key**: You can use your own API key to bypass usage limits on the demo site. Click the Settings icon in the chat panel to configure your provider and API key. Your key is stored locally in your browser and is never stored on the server. @@ -190,7 +191,7 @@ cp env.example .env.local Edit `.env.local` and configure your chosen provider: -- Set `AI_PROVIDER` to your chosen provider (bedrock, openai, anthropic, google, azure, ollama, openrouter, deepseek, siliconflow) +- Set `AI_PROVIDER` to your chosen provider (doubao,bedrock, openai, anthropic, google, azure, ollama, openrouter, deepseek, siliconflow) - Set `AI_MODEL` to the specific model you want to use - Add the required API keys for your provider - `TEMPERATURE`: Optional temperature setting (e.g., `0` for deterministic output). Leave unset for models that don't support it (e.g., reasoning models). @@ -222,6 +223,7 @@ Be sure to **set the environment variables** in the Vercel dashboard as you did ## Multi-Provider Support +- [ByteDance Doubao](https://console.volcengine.com/ark/region:ark+cn-beijing/overview?briefPage=0&briefType=introduce&type=new&utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project) - AWS Bedrock (default) - OpenAI - Anthropic @@ -232,6 +234,7 @@ Be sure to **set the environment variables** in the Vercel dashboard as you did - DeepSeek - SiliconFlow + All providers except AWS Bedrock and OpenRouter support custom endpoints. 📖 **[Detailed Provider Configuration Guide](./docs/ai-providers.md)** - See setup instructions for each provider. @@ -272,6 +275,8 @@ public/ # Static assets including example images ## Support & Contact +**Special thanks to [ByteDance Doubao](https://console.volcengine.com/ark/region:ark+cn-beijing/overview?briefPage=0&briefType=introduce&type=new&utm_campaign=doubao&utm_content=aidrawio&utm_medium=github&utm_source=coopensrc&utm_term=project) for sponsoring the API token usage of the demo site!** Register on the ARK platform to get 500K free tokens for all models! + If you find this project useful, please consider [sponsoring](https://github.com/sponsors/DayuanJiang) to help me host the live demo site! For support or inquiries, please open an issue on the GitHub repository or contact the maintainer at: diff --git a/app/about/cn/page.tsx b/app/about/cn/page.tsx index 6c74ae61..6f16b42a 100644 --- a/app/about/cn/page.tsx +++ b/app/about/cn/page.tsx @@ -96,72 +96,68 @@ export default function AboutCN() { -
-
+
+
{/* Header */}

- 模型变更与用量限制{" "} - - (或者说:我的钱包顶不住了) - + 由字节跳动豆包提供支持

{/* Story */}

- 大家对这个项目的热情太高了——看来大家都真的很喜欢画图!但这也带来了一个幸福的烦恼:我们经常触发出上游 - AI 接口的频率限制 - (TPS/TPM)。一旦超限,系统就会暂停,导致请求失败。 -

-

- 由于使用量过高,我已将模型从 Claude 更换为{" "} + 好消息!感谢{" "} + + 字节跳动豆包 + + 的慷慨赞助,演示站点现已接入强大的{" "} - minimax-m2 - - ,以降低成本。 -

-

- 作为一个 + K2-thinking + {" "} + 模型,图表生成效果更佳!点击链接注册即可领取{" "} - 独立开发者 + 50万免费Token - ,目前的 API - 费用全是我自己在掏腰包(纯属为爱发电)。为了保证服务能细水长流,同时也为了避免我个人陷入财务危机,我还设置了以下临时用量限制: + ,适用于所有模型!

- {/* Limits Cards */} -
-
-
- Token 用量 -
-
- {formatNumber(tpmLimit)} - - /分钟 - -
-
+ {/* Usage Limits */} +

+ 当前使用限制: +

+
+
+

+ {formatNumber(dailyRequestLimit)} +

+

+ 请求/天 +

+
+
+

{formatNumber(dailyTokenLimit)} - - /天 - -

+

+

+ Token/天 +

-
-
- 每日请求数 -
-
- {dailyRequestLimit} -
-
- 次 -
+
+

+ {formatNumber(tpmLimit)} +

+

+ Token/分钟 +

@@ -171,48 +167,19 @@ export default function AboutCN() {
{/* Bring Your Own Key */} -
+

使用自己的 API Key

- 您可以使用自己的 API Key - 来绕过这些限制。点击聊天面板中的设置图标即可配置您的 - Provider 和 API Key。 + 您也可以使用自己的 API + Key,支持多种服务商。点击聊天面板中的设置图标即可配置。

您的 Key 仅保存在浏览器本地,不会被存储在服务器上。

- - {/* Divider */} -
-
-
- - {/* Sponsorship CTA */} -
-

- 寻求赞助 (求大佬捞一把) -

-

- 要想彻底解除这些限制,扩容后端是唯一的办法。我正在积极寻求 - AI API 提供商或云平台的赞助。 -

-

- 作为回报(无论是额度支持还是资金支持),我将在 - GitHub 仓库和 Live Demo - 网站的显眼位置展示贵公司的 Logo - 作为平台赞助商。 -

- - 联系我 - -
@@ -377,6 +344,16 @@ export default function AboutCN() { 多提供商支持
    +
  • + + 字节跳动豆包 + +
  • AWS Bedrock(默认)
  • OpenAI / OpenAI兼容API(通过{" "} @@ -388,6 +365,7 @@ export default function AboutCN() {
  • Ollama
  • OpenRouter
  • DeepSeek
  • +
  • SiliconFlow

注意:claude-sonnet-4-5{" "} @@ -395,18 +373,21 @@ export default function AboutCN() {

{/* Support */} -
-

- 支持与联系 -

-