# Embedding API 后端服务

独立 API 服务，为分析提供 embedding 支持

## 配置虚拟环境

```
# 创建虚拟环境
python -m venv venv

# 激活虚拟环境
./vent/bin/activate

# 安装依赖
pip install -r requirements_version.txt
# （如果没有代理，使用国内镜像安装依赖）
pip install -r requirements_version.txt -i https://pypi.tuna.tsinghua.edu.cn/simple
```

## 运行

```bash
python main.py --host 0.0.0.0 --port 7999
```

## 使用服务

支持的 model: `acge-large-zh` 与 `text-embedding-ada-002`

curl 示例

```bashg
curl http://localhost:7999/v1/embeddings \
  -H "Content-Type: application/json" \
  -d '{
    "input": "The food was delicious and the waiter...",
    "model": "acge-large-zh"
  }'
```

python 示例

```python
from openai import OpenAI
client = OpenAI(base_url="http://localhost:7999/v1", api_key='whatever')

client.embeddings.create(
  model="acge-large-zh",
  input="The food was delicious and the waiter..."
)
```

详细 API 文档位于 <http://localhost:7999/docs>