You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
2. Deploy and start the service. When deploying and starting Coze Studio for the first time, it may take a while to retrieve images and build local images. Please be patient. During deployment, you will see the following log information. If you see the message "Container coze-server Started," it means the Coze Studio service has started successfully.
53
54
54
-
2. Configure the model.
55
-
1. Copy the template files of the doubao-seed-1.6 model from the template directory and paste them into the configuration file directory.
2. Modify the template file in the configuration file directory.
63
-
1. Enter the directory `backend/conf/model`. Open the file `ark_doubao-seed-1.6.yaml`.
64
-
2. Set the fields `id`, `meta.conn_config.api_key`, `meta.conn_config.model`, and save the file.
65
-
***id**: The model ID in Coze Studio, defined by the developer, must be a non-zero integer and globally unique. Agents or workflows call models based on model IDs. For models that have already been launched, do not modify their IDs; otherwise, it may result in model call failures.
66
-
***meta.conn_config.api_key**: The API Key for the model service. In this example, it is the API Key for Ark API Key. For more information, see [Get Volcengine Ark API Key](https://www.volcengine.com/docs/82379/1541594) or [Get BytePlus ModelArk API Key](https://docs.byteplus.com/en/docs/ModelArk/1361424?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source).
67
-
***meta.conn_config.model**: The Model name for the model service. In this example, it refers to the Model ID or Endpoint ID of Ark. For more information, see [Get Volcengine Ark Model ID](https://www.volcengine.com/docs/82379/1513689) / [Get Volcengine Ark Endpoint ID](https://www.volcengine.com/docs/82379/1099522) or [Get BytePlus ModelArk Model ID](https://docs.byteplus.com/en/docs/ModelArk/model_id?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source) / [Get BytePlus ModelArk Endpoint ID](https://docs.byteplus.com/en/docs/ModelArk/1099522?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source).
68
-
> For users in China, you may use Volcengine Ark;for users outside China, you may use BytePlus ModelArk instead.
69
-
3. Deploy and start the service.
70
-
When deploying and starting Coze Studio for the first time, it may take a while to retrieve images and build local images. Please be patient. During deployment, you will see the following log information. If you see the message "Container coze-server Started," it means the Coze Studio service has started successfully.
71
55
```Bash
72
-
# Start the service
73
-
cd docker
56
+
cd coze-studio
57
+
# start service
58
+
# for macOS or Linux
59
+
make web
60
+
# for windows
74
61
cp .env.example .env
75
-
docker compose up -d
62
+
docker compose -f ./docker/docker-compose.yml up
76
63
```
64
+
77
65
For common startup failure issues, **please refer to the [FAQ](https://github.com/coze-dev/coze-studio/wiki/9.-FAQ)**.
78
-
4. After starting the service, you can open Coze Studio by accessing `http://localhost:8888/` through your browser.
66
+
3. Register an account by visiting `http://localhost:8888/sign`, entering your username and password, and clicking the Register button.
67
+
4. Configure the model at `http://localhost:8888/admin/#model-management` by adding a new model.
68
+
5. Visit Coze Studio at `http://localhost:8888/`.
79
69
80
70
> [!WARNING]
81
71
> If you want to deploy Coze Studio in a public network environment, it is recommended to assess security risks before you begin, and take corresponding protection measures. Possible security risks include account registration functions, Python execution environments in workflow code nodes, Coze Server listening address configurations, SSRF (Server - Side Request Forgery), and some horizontal privilege escalations in APIs. For more details, refer to [Quickstart](https://github.com/coze-dev/coze-studio/wiki/2.-Quickstart#security-risks-in-public-networks).
***id**:Coze Studio 中的模型 ID,由开发者自行定义,必须是非 0 的整数,且全局唯一。智能体或工作流根据模型 ID 来调用模型。对于已上线的模型,请勿修改模型 ID,否则可能导致模型调用失败。
66
-
***meta.conn_config.api_key**:模型服务的 API Key,在本示例中为火山方舟的 API Key,获取方式可参考[获取火山方舟 API Key](https://www.volcengine.com/docs/82379/1541594) 或[获取 Byteplus ModelArk API Key](https://docs.byteplus.com/en/docs/ModelArk/1361424?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source)。
67
-
***meta.conn_config.model**:模型服务的 Model name,在本示例中为火山方舟的 Model ID 或 Endpoint ID,获取方式可参考 [获取火山方舟 Model ID](https://www.volcengine.com/docs/82379/1513689) / [获取火山方舟 Endpoint ID](https://www.volcengine.com/docs/82379/1099522),或者参考[获取 BytePlus ModelArk Model ID](https://docs.byteplus.com/en/docs/ModelArk/model_id?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source) / [获取 BytePlus ModelArk Endpoint ID](https://docs.byteplus.com/en/docs/ModelArk/1099522?utm_source=github&utm_medium=readme&utm_campaign=coze_open_source)。
> 如果要将 Coze Studio 部署到公网环境,建议在部署前评估整体评估安全风险,例如账号注册功能、工作流代码节点 Python执行环境、Coze Server 监听地址配置、SSRF 和部分 API 水平越权的风险,并采取相应防护措施。详细信息可参考[快速开始](https://github.com/coze-dev/coze-studio/wiki/2.-%E5%BF%AB%E9%80%9F%E5%BC%80%E5%A7%8B#%E5%85%AC%E7%BD%91%E5%AE%89%E5%85%A8%E9%A3%8E%E9%99%A9)。
0 commit comments