From e9ba392af8cf07befddac0d27d9bb41bb58f3376 Mon Sep 17 00:00:00 2001 From: "1808837298@qq.com" <1808837298@qq.com> Date: Mon, 24 Feb 2025 16:27:20 +0800 Subject: [PATCH] feat: Add model rate limit settings in system configuration --- README.en.md | 1 + README.md | 3 ++- web/src/i18n/locales/en.json | 16 +++++++++++++--- 3 files changed, 16 insertions(+), 4 deletions(-) diff --git a/README.en.md b/README.en.md index 2c1172ea..51cf38bb 100644 --- a/README.en.md +++ b/README.en.md @@ -64,6 +64,7 @@ - Add suffix `-medium` to set medium reasoning effort - Add suffix `-low` to set low reasoning effort 17. 🔄 Thinking to content option `thinking_to_content` in `Channel->Edit->Channel Extra Settings`, default is `false`, when `true`, the `reasoning_content` of the thinking content will be converted to `` tags and concatenated to the content returned. +18. 🔄 Model rate limit, support setting total request limit and successful request limit in `System Settings->Rate Limit Settings` ## Model Support This version additionally supports: diff --git a/README.md b/README.md index 7db01f6a..c19f5f0a 100644 --- a/README.md +++ b/README.md @@ -69,7 +69,8 @@ - 添加后缀 `-high` 设置为 high reasoning effort (例如: `o3-mini-high`) - 添加后缀 `-medium` 设置为 medium reasoning effort (例如: `o3-mini-medium`) - 添加后缀 `-low` 设置为 low reasoning effort (例如: `o3-mini-low`) - 18. 🔄 思考转内容，支持在 `渠道-编辑-渠道额外设置` 中设置 `thinking_to_content` 选项，默认`false`，开启后会将思考内容`reasoning_content`转换为``标签拼接到内容中返回。 +18. 🔄 思考转内容，支持在 `渠道-编辑-渠道额外设置` 中设置 `thinking_to_content` 选项，默认`false`，开启后会将思考内容`reasoning_content`转换为``标签拼接到内容中返回。 +19. 🔄 模型限流，支持在 `系统设置-速率限制设置` 中设置模型限流，支持设置总请求数限制和成功请求数限制 ## 模型支持 此版本额外支持以下模型： diff --git a/web/src/i18n/locales/en.json b/web/src/i18n/locales/en.json index 36e21f05..7036fa20 100644 --- a/web/src/i18n/locales/en.json +++ b/web/src/i18n/locales/en.json @@ -856,7 +856,7 @@ "IP黑名单": "IP blacklist", "不允许的IP，一行一个": "IPs not allowed, one per line", "请选择该渠道所支持的模型": "Please select the model supported by this channel", - "次": "Second-rate", + "次": "times", "达到限速报错内容": "Error content when the speed limit is reached", "不填则使用默认报错": "If not filled in, the default error will be reported.", "Midjouney 设置 (可选)": "Midjouney settings (optional)", @@ -1271,5 +1271,15 @@ "留空则使用账号绑定的邮箱": "If left blank, the email address bound to the account will be used", "代理站地址": "Base URL", "对于官方渠道，new-api已经内置地址，除非是第三方代理站点或者Azure的特殊接入地址，否则不需要填写": "For official channels, the new-api has a built-in address. Unless it is a third-party proxy site or a special Azure access address, there is no need to fill it in", - "渠道额外设置": "Channel extra settings" -} \ No newline at end of file + "渠道额外设置": "Channel extra settings", + "模型请求速率限制": "Model request rate limit", + "启用用户模型请求速率限制（可能会影响高并发性能）": "Enable user model request rate limit (may affect high concurrency performance)", + "限制周期": "Limit period", + "用户每周期最多请求次数": "User max request times per period", + "用户每周期最多请求完成次数": "User max successful request times per period", + "包括失败请求的次数，0代表不限制": "Including failed request times, 0 means no limit", + "频率限制的周期（分钟）": "Rate limit period (minutes)", + "只包括请求成功的次数": "Only include successful request times", + "保存模型速率限制": "Save model rate limit settings", + "速率限制设置": "Rate limit settings" +}