2. Quickstart

Environmental requirements

Before referring to this document to install Coze Studio, ensure that your software and hardware environment meet the following requirements:

Requirements	Description
CPU	2 Core
RAM	4 GiB
Docker	Pre-install Docker, Docker Compose, and start the Docker service. For detailed operations, please refer to the Docker documentation: * macOS: It is recommended to install using Docker Desktop, refer to the Docker Desktop For Mac installation guide. * Linux: Refer to the Docker installation guide and the Docker Compose installation guide. * Windows: It is recommended to install using Docker Desktop, refer to the Docker Desktop For Windows installation guide.

Install Coze Studio

Step 1: Retrieve the source code

Execute the following command in the local project to retrieve the latest version of the Coze Studio source code.

# Clone the code
git clone https://github.com/coze-dev/coze-studio.git

Step 2: Configure the model

Coze Studio is an AI app development platform based on LLM. Before deploying and starting the open-source version of Coze Studio for the first time, you need to configure the model service in the Coze Studio project. Otherwise, you won't be able to properly select a model when creating an agent or workflow. This documentation uses the Volcano Ark model as an example to demonstrate how to configure the model service for Coze Studio. If you plan to use OpenAI or other online model services, you should refer to the model configuration documentation to correctly fill out the configuration files.

1. Copy the template files of the doubao-seed-1.6 model from the template directory and paste them into the configuration file directory.

   cd coze-studio
   # Copy the model configuration template
   cp backend/conf/model/template/model_template_ark_doubao-seed-1.6.yaml backend/conf/model/ark_doubao-seed-1.6.yaml

2. Modify the template file in the configuration file directory.

   1. Enter the directory backend/conf/model. Open the file ark_doubao-seed-1.6.yaml.
   2. Set the fields id, meta.conn_config.api_key, and meta.conn_config.model, and save the file.
      • id: The model ID in Coze Studio, defined independently by the developer, must be a non-zero integer and globally unique. Please do not modify the model ID after the model goes online.
      • meta.conn_config.api_key: The API Key for the online model service, in this example it is the API Key for Volcengine Ark. Refer to obtaining Volcengine Ark API Key for the retrieval method.
      • meta.conn_config.model: The model ID for the online model service. In this example, it is the Endpoint ID for the Volcengine Ark doubao-seed-1.6 model access point. Refer to obtaining Endpoint ID for the retrieval method.

Step 3: Deploy and start the service.

The first deployment and startup of Coze Studio requires retrieving the image and building the local image, which may take a while. Please be patient. During the deployment process, you will see the following log information. If you see the prompt "Container coze-server Started," it means that the Coze Studio service has successfully started.

# Start the service
cd docker
cp .env.example .env
docker compose --profile '*' up -d

Step 4: Log in

After starting the service, you can open Coze Studio by accessing http://localhost:8888/ through your browser. Here, 8888 is the backend listening port. At this point, you have successfully deployed Coze Studio. You can register an account and explore the various features and services of Coze Studio as guided on the page.