### Docker Compose Configuration Example

Source: https://docs.cherry-ai.com/websearch/searxng

This YAML snippet provides a basic structure for a docker-compose.yaml file used to configure and run SearXNG. It outlines the service definitions, which can be further customized for local port mapping or integration with existing Nginx setups. This is a foundational configuration for Docker deployments.

```yaml
version: "3.7"

services:

```

--------------------------------

### Install Ollama on Linux

Source: https://docs.cherry-ai.com/pre-basic/providers/ollama

Command to install Ollama on Linux systems using a curl script. This is the initial setup step for using Ollama locally.

```shell
curl -fsSL https://ollama.com/install.sh | sh
```

--------------------------------

### Deploy SearXNG with Docker (Debian)

Source: https://docs.cherry-ai.com/websearch/searxng

This snippet demonstrates how to deploy SearXNG on a Debian server using Docker. It includes steps for updating the package list, installing git, cloning the SearXNG Docker repository, setting an environment variable for image proxy, and creating a basic settings.yml configuration file. This is for server deployment.

```bash
sudo apt update
sudo apt install git -y

# Pull official repository
cd /opt
git clone https://github.com/searxng/searxng-docker.git
cd /opt/searxng-docker

# If your server bandwidth is very small, you can set this to false
export IMAGE_PROXY=true

# Modify configuration file
cat <<EOF > /opt/searxng-docker/searxng/settings.yml
# see https://docs.searxng.org/admin/settings/settings.html#settings-use-default-settings
use_default_settings: true
server:
  # base_url is defined in the SEARXNG_BASE_URL environment variable, see .env and docker-compose.yml
  secret_key: $(openssl rand -hex 32)
  limiter: false  # can be disabled for a private instance
  image_proxy: $IMAGE_PROXY
ui:
  static_use_hash: true
redis:
  url: redis://redis:6379/0
search:
  formats:
    - html
    - json
EOF
```

--------------------------------

### 自动安装 MCP 服务器指令示例

Source: https://docs.cherry-ai.com/advanced-basic/mcp/auto-install

在 Cherry Studio 的大模型对话中输入此指令，即可触发自动安装指定 MCP 服务器的操作。系统将解析指令并调用 `@mcpmarket/mcp-auto-install` 工具。

```plaintext
帮我安装一个 filesystem mcp server
```

--------------------------------

### Configure Ollama API Address in Cherry Studio

Source: https://docs.cherry-ai.com/pre-basic/providers/ollama

Example of the default local API address for Ollama. This is used in Cherry Studio's configuration to connect to the locally running Ollama service.

```http
http://localhost:11434/
```

--------------------------------

### MCP 自动安装工具默认配置示例 (JSON)

Source: https://docs.cherry-ai.com/advanced-basic/mcp/auto-install

此 JSON 对象展示了 `@mcpmarket/mcp-auto-install` 工具在 Cherry Studio 中的默认配置。它定义了工具的名称、描述、激活状态、注册表 URL、执行命令及参数，以及环境变量。此配置可作为自定义的参考。

```json
// `axun-uUpaWEdMEMU8C61K` 为服务id,自定义即可
"axun-uUpaWEdMEMU8C61K": {
  "name": "mcp-auto-install",
  "description": "Automatically install MCP services (Beta version)",
  "isActive": false,
  "registryUrl": "https://registry.npmmirror.com",
  "command": "npx",
  "args": [
    "-y",
    "@mcpmarket/mcp-auto-install",
    "connect",
    "--json"
  ],
  "env": {
    "MCP_REGISTRY_PATH": "详情见https://www.npmjs.com/package/@mcpmarket/mcp-auto-install"
  },
  "disabledTools": []
}
```

--------------------------------

### 启动 vLLM OpenAI 兼容服务 (Shell)

Source: https://docs.cherry-ai.com/pre-basic/providers/zi-ding-yi-fu-wu-shang

启动 vLLM 的 OpenAI 兼容 API 服务。该服务可以被 Cherry Studio 识别为自定义的 OpenAI 提供商。示例使用 'gpt2' 模型。

```shell
python -m vllm.entrypoints.openai.api_server --model gpt2
```

```shell
vllm --model gpt2 --served-model-name gpt2
```