本地部署Deep Recall需要完成以下关键步骤:
- environmental preparation::
- Python 3.8+环境
- NVIDIA驱动(如需GPU加速)
- 至少16GB内存(处理7B模型时)
- Dependent Installation::
- 创建隔离虚拟环境:
python -m venv venv
- Install the base package:
pip install -r requirements.txt
- Development tools:
pip install -r requirements-dev.txt
- 创建隔离虚拟环境:
- Service Initialization::
- 向量数据库:执行
python scripts/init_vector_db.py
- 配置文件:按需修改
config/
目录下的内存、GPU分配等参数
- 向量数据库:执行
- validation test::
- 运行单元测试:
pytest tests/
- 启动demo服务:
python -m deep_recall.api_server
- 运行单元测试:
注意:Windows用户需安装Visual C++ Build Tools,完整指南参考项目CONTRIBUTING.md。
This answer comes from the articleDeep Recall: an open source tool that provides an enterprise-class memory framework for large modelsThe