### Run SiliconFlow setup wizard

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-dsh

Launches the dsh-siliconflow-setup executable bundled with the plugin. It reads and writes credentials and settings under $DSH_HOME (default ~/.dsh), and guides through setting default provider, entering API key, fetching models, and selecting default model.

```bash
npx @siliconflow-official/dsh-llm-siliconflow
```

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

### Launch wiseflow with uv and run script

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-wiseflow

Run these commands in order to set up the environment and start wiseflow. The first run requires creating a virtual environment, syncing dependencies, installing Chromium, and making run.sh executable.

```bash
cd wiseflow
uv venv # Only needed the first time
source .venv/bin/activate  # Linux/macOS# 
# Or on Windows:
# .venv\Scripts\activate
uv sync # Only needed the first time
python -m playwright install --with-deps chromium # Only needed the first time
chmod +x run.sh # Only needed the first time
./run.sh
```

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

### Install uv and clone wiseflow repository

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-wiseflow

Run these commands to install uv and clone the wiseflow project. The first command installs uv, and the second clones the repository.

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
git clone https://github.com/TeamWiseFlow/wiseflow.git
```

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

### Docker Self-Hosted Installation Commands

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-OpenDesign

Clone the Open Design repository, set up the deployment environment, generate an API token, and start the service with Docker Compose. After launching, visit http://localhost:7456.

```bash
git clone https://github.com/nexu-io/open-design.git
cd open-design/deploy
cp .env.example .env
echo "OD_API_TOKEN=$(openssl rand -hex 32)" >> .env
docker compose up -d
```

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

### Install SiliconFlow adapter plugin for dsh

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-dsh

Installs the SiliconFlow adapter plugin into the dsh profile using npx. This is required before running the setup wizard.

```bash
npx @deepseek-ai/dsh plugin --profile web add @siliconflow-official/dsh-llm-siliconflow
```

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

### Start DB-GPT Web Server

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-DB-GPT

Starts the DB-GPT web server on port 5670.

```bash
dbgpt start webserver --port 5670
```

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

### Create Virtual Environment and Install Dependencies

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-DB-GPT

Creates a conda environment with Python 3.10 and installs DB-GPT with proxy model dependencies.

```bash
# cd 到 DB-GPT 源码根目录
cd DB-GPT

# DB-GPT 要求python >= 3.10
conda create -n dbgpt_env python=3.10
conda activate dbgpt_env

# 这里选择代理模型类依赖安装
pip install -e ".[proxy]"
```

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

### Start MindSearch frontend with Gradio

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-mindsearch

Run this command to start the MindSearch frontend using Gradio. Other frontends are available in MindSearch's README.

```bash
python frontend/mindsearch_gradio.py
```

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

### Example model output in JSON

Source: https://docs.siliconflow.cn/docs/userguide/guides/json-mode

The model's output in JSON format, as shown in the guide.

```json
{"男子冠军": "马龙", "女子冠军": "陈梦"}
```

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

### Deploy AstrBot via Docker

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-astrbot

Clones the AstrBot repository and starts it with Docker Compose. Requires Docker and Git to be installed.

```bash
git clone https://github.com/AstrBotDevs/AstrBot
cd AstrBot
docker compose up -d
```

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

### Deploy LangBot with Docker

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-langbot

Clones the LangBot repository and starts the service using Docker Compose. Requires Git and Docker to be installed.

```bash
git clone https://github.com/langbot-app/LangBot  
cd LangBot
docker compose up -d
```

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

### Start Chat2Graph server

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-chat2graph

Runs the startup script to launch the Chat2Graph server.

```bash
./bin/start.sh
```

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

### Prepare .env configuration file

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-chat2graph

Copies the .env.template to .env and opens it in vim for editing.

```bash
cp .env.template .env && vim .env
```

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

### Batch input file with thinking_budget for reasoning models

Source: https://docs.siliconflow.cn/docs/userguide/guides/batch

Example .jsonl input for reasoning models, using thinking_budget to cap chain-of-thought length. The structure is identical to the general example but highlights the thinking_budget parameter.

```jsonl
{"custom_id": "request-1", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "deepseek-ai/DeepSeek-V3.2", "messages": [{"role": "system", "content": "You are a highly advanced and versatile AI assistant"}, {"role": "user", "content": "How does photosynthesis work?"}], "stream": true, "max_tokens": 1514,"thinking_budget": 32768}}
{"custom_id": "request-2", "method": "POST", "url": "/v1/chat/completions", "body": {"model": "deepseek-ai/DeepSeek-V3.2", "messages": [{"role": "system", "content": "You are a highly advanced and versatile AI assistant"}, {"role": "user", "content": "Imagine a world where everyone can fly. Describe a day in this world."}], "stream": true, "max_tokens": 1583,"thinking_budget": 32768}}
```

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

### Visual Recognition with Qwen2.5-VL-72B-Instruct

Source: https://docs.siliconflow.cn/docs/userguide/capabilities/multimodal-vision

Initializes the OpenAI client with SiliconFlow's base URL and sends an image URL with a text prompt to analyze the image content. The model 'Qwen/Qwen2.5-VL-72B-Instruct' is used.

```python
from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.siliconflow.cn/v1"
)

response = client.chat.completions.create(
    model="Qwen/Qwen2.5-VL-72B-Instruct",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://example.com/tech-conference.jpg"
                    }
                },
                {
                    "type": "text",
                    "text": "What kind of tech conference is shown in this image? Analyze the expressions and atmosphere of the attendees"
                }
            ]
        }
    ]
)

print(response.choices[0].message.content)
```

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

### 200 response example

Source: https://docs.siliconflow.cn/docs/api/audio-speech-post

Example of the binary audio data returned on success.

```json
"音频的二进制数据"
```

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

### Check Node.js Environment

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-codex

Run these commands to verify Node.js and npm are installed. Node.js 20 LTS or later is recommended.

```bash
node -v
npm -v
```

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

### Verify Codex Installation

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-codex

Check that Codex CLI is installed by printing its version.

```bash
codex --version
```

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

### Running Open Design from Source

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-OpenDesign

Clone the repository, enable Corepack, install dependencies with pnpm, and run the web development server. Requires Node.js 24+ and pnpm 10.33.x.

```bash
git clone https://github.com/nexu-io/open-design.git
cd open-design
corepack enable && pnpm install
pnpm tools-dev run web
```

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

### Start MindSearch backend with SiliconFlow API

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-mindsearch

Run these commands to start the MindSearch backend. First set the SILICON_API_KEY environment variable to your copied key, then launch the backend with the internlm_silicon model format and DuckDuckGo search engine.

```bash
# 指定硅基流动的 API Key
export SILICON_API_KEY=上面流程中复制的密钥
# 启动
python -m mindsearch.app --lang en --model_format internlm_silicon --search_engine DuckDuckGoSearch
```

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

### Install Codex CLI

Source: https://docs.siliconflow.cn/docs/usercases/use-siliconcloud-in-codex

Install Codex CLI globally using npm.

```bash
npm install -g @openai/codex
```