db-gpt基础(0.7.0)

uv工具

uv官网：https://docs.astral.sh/uv/getting-started/installation/

uv官网中文个人翻译：https://hellowac.github.io/uv-zh-cn/

github地址：https://github.com/hellowac/uv-zh-cn

启动准备

代码克隆

git clone https://github.com/eosphoros-ai/DB-GPT.git

安装UV依赖管理

python -m pip install --upgrade pip
python -m pip install --upgrade pipx
python -m pipx ensurepath
# pipx install uv --global 和 pip install uv 任意一种即可
pipx install uv --global

依赖同步
Linux命令：

uv sync --all-packages \
--extra "base" \
--extra "proxy_openai" \
--extra "rag" \
--extra "storage_chromadb" \
--extra "dbgpts" \
--extra "hf" \
--extra "cpu" \
--index-url=https://pypi.tuna.tsinghua.edu.cn/simple

Windows命令：

uv sync --all-packages --extra "base" --extra "proxy_openai" --extra "rag" --extra "storage_chromadb" --extra "dbgpts" --extra "hf" --extra "cpu" --index-url=https://pypi.tuna.tsinghua.edu.cn/simple

内嵌模型下载：

git clone https://hf-mirror.com/BAAI/bge-large-zh-v1.5

服务启动

配置文件参数，文件路径configs/dbgpt-proxy-deepseek.toml

[system]
# Load language from environment variable(It is set by the hook)
language = "${env:DBGPT_LANG:-zh}"
api_keys = []
encrypt_key = "your_secret_key"

# Server Configurations
[service.web]
host = "0.0.0.0"
port = 5670

# 数据库配置
[service.web.database]
type = "mysql"
host = "127.0.0.1"
port = "3306"
database = "dbgpt"
user = "root"
password ="mysql"

[service.model.worker]
host = "127.0.0.1"

# 向量数据库
[rag.storage]
[rag.storage.vector]
type = "Chroma"
persist_path = "pilot/data"


# 代理模型访问
[models]
[[models.llms]]
name = "deepseek-r1:7b"
provider = "proxy/deepseek"
api_base = "http://192.168.0.160:11434/v1"
api_key = "your_deepseek_api_key"

[[models.embeddings]]
name = "BAAI/bge-large-zh-v1.5"
provider = "hf"
path = "/data/models/bge-large-zh-v1.5"

命令启动

# 方法一：
uv run dbgpt start webserver --config configs/dbgpt-proxy-deepseek.toml

# 方法二
uv run python packages/dbgpt-app/src/dbgpt_app/dbgpt_server.py --config configs/dbgpt-proxy-deepseek.toml

pycharm配置启动的application