diff --git a/README.md b/README.md index eb5d090..ae8bcd9 100644 --- a/README.md +++ b/README.md @@ -1,157 +1,161 @@ -## Why + +> [!NOTE] +> 本文档由 WeHub 基于上游 README 翻译整理，属于社区翻译，非官方中文文档。 +> [English](./README.en.md) · [原始项目](https://github.com/PublicAffairs/openai-gemini) · [上游 README](https://github.com/PublicAffairs/openai-gemini/blob/HEAD/README.md) +> 原作者、版权与许可证归属以原始项目及本仓库 LICENSE 文件为准。 -The Gemini API has [Free](https://ai.google.dev/gemini-api/docs/pricing#free) Tier -with *generous limits*, but there are still many tools that work exclusively with the OpenAI API. +## 为什么 -This project provides a personal OpenAI-compatible endpoint for free. +Gemini API 提供[免费](https://ai.google.dev/gemini-api/docs/pricing#free) 层级，*限额慷慨*，但仍有许多工具仅支持 OpenAI API。 + +本项目可免费提供一个个人使用的、兼容 OpenAI 的端点。 -## Serverless? +## 无服务器（Serverless）？ -Although it runs in the cloud, it does not require server maintenance. -It can be easily deployed to various providers for free -(with generous limits suitable for personal use). +虽然它运行在云端，但无需自行维护服务器。 +可免费轻松部署到多种云平台提供商 +（限额慷慨，适合个人使用）。 > [!TIP] -> Running the proxy endpoint locally is also an [option](#serve-locally---with-node-deno-bun)! +> 在本地运行代理端点也是一种[选择](#serve-locally---with-node-deno-bun)！ -## How to start +## 如何开始 -You will need a personal Google [API key](https://aistudio.google.com/app/api-keys). +你需要一个个人的 Google [API 密钥](https://aistudio.google.com/app/api-keys). > [!IMPORTANT] -> Even if you are located outside of the [supported regions](https://ai.google.dev/gemini-api/docs/available-regions#available_regions), -> it is still possible to acquire one using a VPN. +> 即使你位于[支持的地区](https://ai.google.dev/gemini-api/docs/available-regions#available_regions), 之外，仍可通过 VPN 获取。 -Deploy the project to one of the providers, using the instructions below. -You will need to set up an account there. +请按照下方说明，将项目部署到任一提供商。 +你需要在那里注册账号。 -If you opt for “button-deploy”, you'll be guided through the process of forking the repository first, -which is necessary for continuous integration (CI). +如果选择“一键部署”，系统会引导你先 Fork 仓库， +这对持续集成（CI）是必需的。 -### Deploy with Vercel +### 使用 Vercel 部署 [![Deploy with Vercel](https://vercel.com/button)](https://vercel.com/new/clone?repository-url=https://github.com/PublicAffairs/openai-gemini&repository-name=my-openai-gemini) -- Alternatively can be deployed with [cli](https://vercel.com/docs/cli): +- 也可通过 [cli](https://vercel.com/docs/cli): 部署 `vercel deploy` -- Serve locally: `vercel dev` -- Vercel _Functions_ [limitations](https://vercel.com/docs/functions/limitations) (with _Edge_ runtime) +- 本地运行：`vercel dev` +- Vercel _Functions_ [限制](https://vercel.com/docs/functions/limitations)（使用 _Edge_ 运行时） -### Deploy to Netlify +### 部署到 Netlify [![Deploy to Netlify](https://www.netlify.com/img/deploy/button.svg)](https://app.netlify.com/start/deploy?repository=https://github.com/PublicAffairs/openai-gemini&integrationName=integrationName&integrationSlug=integrationSlug&integrationDescription=integrationDescription) -- Alternatively can be deployed with [cli](https://docs.netlify.com/cli/get-started/): +- 也可通过 [cli](https://docs.netlify.com/cli/get-started/): 部署 `netlify deploy` -- Serve locally: `netlify dev` -- Two different api bases provided: - - `/v1` (e.g. `/v1/chat/completions` endpoint) - _Functions_ [limits](https://docs.netlify.com/build/functions/get-started/#synchronous-function) +- 本地运行：`netlify dev` +- 提供两种不同的 API 基址： + - `/v1`（例如 `/v1/chat/completions` 端点） + _Functions_ [限制](https://docs.netlify.com/build/functions/get-started/#synchronous-function) - `/edge/v1` - _Edge functions_ [limits](https://docs.netlify.com/build/edge-functions/limits/) + _Edge functions_ [限制](https://docs.netlify.com/build/edge-functions/limits/) -### Deploy to Cloudflare +### 部署到 Cloudflare [![Deploy to Cloudflare Workers](https://deploy.workers.cloudflare.com/button)](https://deploy.workers.cloudflare.com/?url=https://github.com/PublicAffairs/openai-gemini) -- Alternatively can be deployed manually pasting content of [`src/worker.mjs`](src/worker.mjs) - to https://workers.cloudflare.com/playground (see there `Deploy` button). -- Alternatively can be deployed with [cli](https://developers.cloudflare.com/workers/wrangler/): +- 也可手动部署：将 [`src/worker.mjs`](src/worker.mjs) 的内容粘贴到 + https://workers.cloudflare.com/playground（参见该页面的 `Deploy` 按钮）。 +- 也可通过 [cli](https://developers.cloudflare.com/workers/wrangler/): 部署 `wrangler deploy` -- Serve locally: `wrangler dev` -- _Worker_ [limits](https://developers.cloudflare.com/workers/platform/limits/#worker-limits) +- 本地运行：`wrangler dev` +- _Worker_ [限制](https://developers.cloudflare.com/workers/platform/limits/#worker-limits) -### Deploy to Deno +### 部署到 Deno -See details [here](https://github.com/PublicAffairs/openai-gemini/discussions/19). +详见[此处](https://github.com/PublicAffairs/openai-gemini/discussions/19). -### Serve locally - with Node, Deno, Bun +### 本地运行 - 使用 Node、Deno、Bun -Only for Node: `npm install`. +仅在 Node 环境下：`npm install`。 -Then `npm run start` / `npm run start:deno` / `npm run start:bun`. +然后执行 `npm run start` / `npm run start:deno` / `npm run start:bun`。 -#### Dev mode (watch source changes) +#### 开发模式（监听源码变更） -Only for Node: `npm install --include=dev` +仅在 Node 环境下：`npm install --include=dev` -Then: `npm run dev` / `npm run dev:deno` / `npm run dev:bun`. +然后：`npm run dev` / `npm run dev:deno` / `npm run dev:bun`。 -## How to use -If you open your newly-deployed site in a browser, you will only see a `404 Not Found` message. This is expected, as the API is not designed for direct browser access. -To utilize it, you should enter your API address and your Gemini API key into the corresponding fields in your software settings. +## 如何使用 +如果你在浏览器中打开新部署的站点，只会看到一条 `404 Not Found` 消息。这是预期行为，因为该 API 并非为浏览器直接访问而设计。 +要在软件中使用，请在对应设置字段中填入 API 地址和你的 Gemini API 密钥。 > [!NOTE] -> Not all software tools allow overriding the OpenAI endpoint, but many do -> (however these settings can sometimes be deeply hidden). +> 并非所有软件工具都允许覆盖 OpenAI 端点，但许多工具支持 +> （不过这些设置有时藏得很深）。 -Typically, you should specify the API base in this format: +通常应按以下格式指定 API 基址： `https://my-super-proxy.vercel.app/v1` -The relevant field may be labeled as "_OpenAI proxy_". -You might need to look under "_Advanced settings_" or similar sections. -Alternatively, it could be in some config file (check the relevant documentation for details). +相关字段可能标记为 "_OpenAI proxy_"。 +你可能需要在 "_Advanced settings_" 或类似区域中查找。 +或者它可能位于某个配置文件中（详情请查阅相关文档）。 -For some command-line tools, you may need to set an environment variable, _e.g._: +对于某些命令行工具，你可能需要设置环境变量，_例如_： ```sh OPENAI_BASE_URL="https://my-super-proxy.vercel.app/v1" ``` -_..or_: +_…或_： ```sh OPENAI_API_BASE="https://my-super-proxy.vercel.app/v1" ``` -## Models +## 模型 -Requests use the specified [model] if its name starts with "gemini-", "gemma-", or "models/". -Otherwise, these defaults apply: +若指定的 [model] 名称以 "gemini-"、"gemma-" 或 "models/" 开头，请求将使用该模型。 +否则将应用以下默认值： -- `chat/completions`: `gemini-flash-latest` -- `embeddings`: `gemini-embedding-001` +- `chat/completions`：`gemini-flash-latest` +- `embeddings`：`gemini-embedding-001` [model]: https://ai.google.dev/gemini-api/docs/models -## Built-in tools +## 内置工具 -To use the **web search** tool, append ":search" to the model name -(e.g., "gemini-2.5-flash:search"). +要使用 **web search** 工具，在模型名称后追加 ":search" +（例如 "gemini-2.5-flash:search"）。 -Note: The `annotations` message property is not implemented. +注意：尚未实现 `annotations` 消息的 property。 -## Media +## 媒体 -[Vision] and [audio] input supported as per OpenAI [specs]. -Implemented via [`inlineData`](https://ai.google.dev/api/caching#Part). +支持按 OpenAI [specs] 规范输入 [Vision] 和 [audio]。 +通过 [`inlineData`](https://ai.google.dev/api/caching#Part). 实现。 [vision]: https://platform.openai.com/docs/guides/images-vision?api-mode=chat&format=url#giving-a-model-images-as-input [audio]: https://platform.openai.com/docs/guides/audio?example=audio-in&lang=curl#add-audio-to-your-existing-application [specs]: https://platform.openai.com/docs/api-reference/chat/create -## Gemini-specific functions +## Gemini 专属功能 -There are several features supported by Gemini that are not available in OpenAI models -but can be enabled using the `extra_body` field. -The most notable of these is [`thinking_config`](https://ai.google.dev/gemini-api/docs/openai#thinking). +Gemini 支持多项 OpenAI 模型不具备的功能， +但可通过 `extra_body` 字段启用。 +其中最值得注意的是 [`thinking_config`](https://ai.google.dev/gemini-api/docs/openai#thinking). -For more details, refer to the [Gemini API docs](https://ai.google.dev/gemini-api/docs/openai#extra-body). +更多详情请参阅 [Gemini API 文档](https://ai.google.dev/gemini-api/docs/openai#extra-body). --- -## Supported API endpoints and applicable parameters +## 支持的 API 端点及适用参数 - [x] `chat/completions` - Currently, most of the parameters that are applicable to both APIs have been implemented. + 目前，适用于两个 API 的大多数参数均已实现。
- [x] `messages` @@ -167,24 +171,24 @@ For more details, refer to the [Gemini API docs](https://ai.google.dev/gemini-ap - [ ] `logit_bias` - [ ] `logprobs` - [ ] `top_logprobs` - - [x] `max_tokens`, `max_completion_tokens` - - [x] `n` (`candidateCount` <8, not for streaming) + - [x] `max_tokens`，`max_completion_tokens` + - [x] `n`（`candidateCount` <8，不适用于流式传输） - [x] `presence_penalty` - [x] `reasoning_effort` - [x] `response_format` - [x] "json_object" - - [x] "json_schema" (a select subset of an OpenAPI 3.0 schema object) + - [x] "json_schema"（OpenAPI 3.0 schema 对象的一个选定子集） - [x] "text" - [x] `seed` - - [x] `stop`: string|array (`stopSequences` [1,5]) + - [x] `stop`：string|array（`stopSequences` [1,5]） - [x] `stream` - [x] `stream_options` - [x] `include_usage` - - [x] `temperature` (0.0..2.0 for OpenAI, but Gemini supports up to infinity) + - [x] `temperature`（OpenAI 为 0.0..2.0，但 Gemini 最高支持至无穷大） - [x] `top_p` - [x] `tools` - [x] `tool_choice` - - [ ] `parallel_tool_calls` (is always active in Gemini) + - [ ] `parallel_tool_calls`（在 Gemini 中始终处于启用状态） - [x] [`extra_body`](#gemini-specific-functions)