feat: add support for coze

README.md

@@ -33,7 +33,7 @@ exif-ai -i example.jpeg -a ollama
 
 Required options:
 
-- `-a, --api-provider <value>`: Name of the AI provider to use (`ollama` for Ollama, `zhipu` for ZhipuAI, `google` for Google Gemini).
+- `-a, --api-provider <value>`: Name of the AI provider to use (`ollama` for Ollama, `zhipu` for ZhipuAI, `google` for Google Gemini, `coze_bot` for Coze Bot).
 
 Optional options:
 
@@ -133,21 +133,22 @@ Please ensure that you securely manage your API keys. Do not expose them in publ
 
 ## API Providers
 
-Exif AI relies on API providers to generate image descriptions and tags. Currently, we support three providers: ZhipuAI, Ollama and Google Gemini.
+Exif AI relies on API providers to generate image descriptions and tags. Currently, we support four providers: ZhipuAI, Ollama, Google Gemini and Coze.
 
 ### Supported Providers
 
 - ZhipuAI: A leading AI service provider. Requires an API key.
 - Ollama: A local AI service that runs on your machine, eliminating the need for an API key.
 - Google Gemini: A powerful AI service provided by Google.
+- Coze: Coze is a next-generation AI application and chatbot developing platform for everyone.
 
 ### Custom Providers
 
 You can also develop your own custom provider by implementing the provider interface. This allows you to integrate with other AI services or customize the description generation process.
 
 ## Configuration
 
-### Setting API Keys (for ZhipuAI)
+### Zhipu AI
 
 To use [ZhipuAI](https://open.bigmodel.cn/usercenter/apikeys), you need to set the API key. You can do this by setting an environment variable:
 
@@ -163,7 +164,29 @@ To use [Google Gemini](https://ai.google.dev/), you need to set the API key. You
 export API_KEY=your_google_api_key
 ```
 
-### Ollama Configuration
+### Coze Bot
+
+To use [Coze](https://www.coze.com/) bot, you need to set the API key. You can do this by setting an environment variable:
+
+```bash
+export COZE_API_KEY=your_coze_api_key
+```
+
+When utilizing Coze within the Chinese region, configure the endpoint setting as follows:
+
+```bash
+export COZE_ENDPOINT=https://api.coze.cn
+```
+
+In Coze Bot, the `model` parameter corresponds to the bot's identifier. To interact with the Coze API, use the following command format:
+
+```bash
+exif-ai -a coze_bot -i image.jpg -m 7402199305639034921
+```
+
+Here, `-a coze_bot` specifies the Coze API, `-i image.jpg` indicates the input image file, and `-m 7402199305639034921` is the unique identifier for the bot model you wish to use.
+
+### Ollama
 
 Ollama runs locally and does not require an API key. Ensure that Ollama is installed and properly configured on your machine. Refer to the [Ollama GitHub repository](https://github.com/ollama/ollama) for installation and setup instructions.
 

README.zh-CN.md

@@ -131,14 +131,15 @@ Exif AI依赖于API供应商来生成图像描述和标签。目前，我们支
 - ZhipuAI：领先的AI服务供应商。需要API密钥。
 - Ollama：在您的机器上运行的本地AI服务，无需API密钥。
 - Google Gemini：由Google提供的强大AI服务。
+- Coze: 扣子是新一代 AI 大模型智能体开发平台。您可以使用API来调用扣子的bot或工作流。
 
 ### 自定义供应商
 
 您还可以通过实现供应商接口来开发您自己的自定义供应商。这允许您与其他AI服务集成或自定义描述生成过程。
 
 ## 配置
 
-### 设置API密钥（适用于ZhipuAI）
+### ZhipuAI
 
 要使用[ZhipuAI](https://open.bigmodel.cn/usercenter/apikeys)，您需要设置API密钥。您可以通过设置环境变量来完成此操作：
 
@@ -154,7 +155,30 @@ export ZHIPUAI_API_KEY=your_zhipuai_api_key
 export API_KEY=your_google_api_key
 ```
 
-### Ollama Configuration
+### Coze
+
+要使用[Coze](https://www.coze.com/) Bot，您需要设置API密钥。您可以通过设置环境变量来完成此操作：
+
+```bash
+export COZE_API_KEY=your_coze_api_key
+```
+
+在中国地区使用Coze时，请按照以下方式配置端点设置：
+
+```bash
+export COZE_ENDPOINT=https://api.coze.cn
+```
+
+在Coze中，`model`参数对应于bot的id。要使用Coze API进行交互，请使用以下命令格式：
+
+
+```bash
+exif-ai -a coze_bot -i image.jpg -m 7402199305639034921
+```
+
+在此处，`-a coze_bot`指定了Coze API，`-i image.jpg`表示输入图像文件，而`-m 7402199305639034921`是您希望使用的bot的id。
+
+### Ollama
 
 Ollama在本地运行，不需要API密钥。请确保Ollama已安装在您的机器上并正确配置。有关安装和设置说明，请参考[Ollama](https://github.com/ollama/ollama)。
 

manual.md

@@ -10,15 +10,15 @@ exif-ai [options]
 
 # DESCRIPTION
 
-The `exif-ai` command is a Node.js CLI tool that uses AI to analyze image content and write descriptive metadata to the EXIF information of an image file. It supports three AI providers: Ollama, ZhipuAI and Google Gemini. Ollama runs locally, while ZhipuAI and Google Gemini requires an API key.
+The `exif-ai` command is a Node.js CLI tool that uses AI to analyze image content and write descriptive metadata to the EXIF information of an image file. It supports four AI providers: Ollama, ZhipuAI, Google Gemini and Coze. Ollama runs locally, while ZhipuAI, Google Gemini and Coze requires an API key.
 
 # OPTIONS
 
 * `-i, --input <file>`:
 Specify the path to the input image file.
 
 * `-a, --api-provider <name>`:
-Choose the AI provider to use. Acceptable values are ollama or zhipu.
+Choose the AI provider to use. Acceptable values are ollama, zhipu, google or coze.
 
 * `-p, --prompt <text>`:
 Set a custom prompt for the AI provider. If not specified, a default prompt is used.
@@ -78,6 +78,8 @@ An AI service provider that requires an API key. Set the environment variable ZH
 * Google Gemini:
 An AI service provider that requires an API key. Set the environment variable API_KEY with your key.
 
+* Coze:
+
 # CONFIGURATION
 
 ## Zhipu AI

package.json

@@ -1,7 +1,7 @@
 {
   "name": "exif-ai",
-  "version": "3.1.0",
-  "description": "A Node.js CLI and library that uses Ollama, ZhipuAI or Google Gemini to intelligently write image description and/or tags to exif metadata by it's content.",
+  "version": "3.1.1",
+  "description": "A Node.js CLI and library that uses Ollama, ZhipuAI, Google Gemini or Coze to intelligently write image description and/or tags to exif metadata by it's content.",
   "homepage": "https://github.com/tychenjiajun/exif-ai",
   "repository": {
     "type": "git",
@@ -40,14 +40,16 @@
     "cli",
     "cli-tool",
     "metadata",
-    "gemini"
+    "gemini",
+    "coze"
   ],
   "author": {
     "name": "Jiajun Chen",
     "email": "[email protected]"
   },
   "license": "GPL-2.0-only",
   "dependencies": {
+    "@coze/coze-js": "^0.2.0",
     "@fluent/bundle": "^0.18.0",
     "@google/generative-ai": "^0.19.0",
     "chokidar": "^4.0.0",

src/exif-ai.ts

@@ -31,7 +31,7 @@ async function findFilesRecursive(
 }
 const program = new Command();
 program
-  .version("3.1.0")
+  .version("3.1.1")
   .description(getText("description") ?? "")
   .requiredOption("-a, --api-provider <provider>", getText("api-provider"))
   .option("-T, --tasks <tasks...>", getText("tasks"))

src/fluent/index.ts

@@ -8,8 +8,8 @@ const bundles: Record<string, FluentBundle> = {
 
 bundles["en-US"].addResource(
   new FluentResource(`
-description = A Node.js CLI that uses Ollama, ZhipuAI or Google Gemini to intelligently write image description and/or tags to exif metadata by it's content.
-api-provider = Name of the AI provider to use ('ollama' for Ollama, 'zhipu' for ZhipuAI, 'google' for Google Gemini).
+description = A Node.js CLI that uses Ollama, ZhipuAI, Google Gemini or Cozw to intelligently write image description and/or tags to exif metadata by it's content.
+api-provider = Name of the AI provider to use ('ollama' for Ollama, 'zhipu' for ZhipuAI, 'google' for Google Gemini, 'coze_bot' for Coze Bot).
 input = Path to the input image file.
 model = Specify the AI model to use, if supported by the provider.
 description-tags = List of EXIF tags to write the description to. Defaults to common description tags.
@@ -31,8 +31,8 @@ face-group-ids = List of face group IDs to use for face recognition.
 
 bundles["zh-CN"].addResource(
   new FluentResource(`
-description = 一个Node.js命令行工具，它使用Ollama或ZhipuAI根据图像内容智能地将图像描述和/或标签写入EXIF元数据。
-api-provider = 要使用的AI供应商名称（'ollama'代表Ollama，'zhipu'代表ZhipuAI，'google'代表Google Gemini）。
+description = 一个Node.js命令行工具，它使用Ollama或ZhipuAI或Google Gemini或Coze根据图像内容智能地将图像描述和/或标签写入EXIF元数据。
+api-provider = 要使用的AI供应商名称（'ollama'代表Ollama，'zhipu'代表ZhipuAI，'google'代表Google Gemini, 'coze_bot'代表Coze）。
 input = 输入图像文件的路径。
 model = 指定要使用的AI模型，如果供应商支持。
 description-tags = 要写入描述的EXIF标签列表。默认为常见描述标签。

src/index.ts

@@ -179,6 +179,18 @@ export async function execute({
         })
       : undefined;
 
+    let file_id: string | undefined;
+
+    if ("uploadFile" in providerModule) {
+      if (verbose) console.log("Uploading file to provider");
+      const { id } = await providerModule.uploadFile({
+        path,
+        buffer,
+      });
+
+      file_id = id;
+    }
+
     const [description, tags] = await Promise.all([
       tasks.includes("description")
         ? getDescription({
@@ -190,6 +202,8 @@ export async function execute({
             verbose,
             descriptionTags,
             existingTags,
+            path: resolvedPath,
+            file_id,
           })
         : undefined,
       tasks.includes("tag") || tasks.includes("tags")
@@ -202,6 +216,8 @@ export async function execute({
             tagTags,
             existingTags,
             additionalTags: faces,
+            path: resolvedPath,
+            file_id,
           })
         : tasks.includes("face")
           ? getTags({
@@ -212,6 +228,8 @@ export async function execute({
               tagTags,
               existingTags,
               additionalTags: faces,
+              path: resolvedPath,
+              file_id,
             })
           : undefined,
     ]);