Gavvy Sales Engine — 内测版
pip install 即用的 AI 销售团队 — 类目驱动,卖任何商品,多渠道触达。 内测阶段 v4.0.0
一分钟上手
# 1. 安装
pip install gavvy-salesmaster fastapi uvicorn
# 2. 启动(自动生成 API Key + 打开 Dashboard)
gavvy start
打开 http://localhost:8877 → 点击"销售流程" → 新建流程 → 开卖。
能做什么
| 功能 | 说明 | 版本 |
|---|---|---|
| CRM 客户管理 | 客户/联系人/合同/报价 | Community |
| 产品目录 | 4个默认类目+商品,支持自定义 | Community |
| 类目规则引擎 | 广告法检测、利润率控制、合规检测 | Community |
| 文档读取提炼卖点 | 指定文件夹路径,自动提取卖点 | Community |
| 销售流程向导 | 7步配置→自动执行 | Community |
| 寻客引擎 | 多平台搜索客户(Bing/mock) | Pro |
| AI Agent 对话 | 6个销售 Agent 自动跟进 | Pro |
| 渠道发送 | 邮件/微信/企微/钉钉 | Pro |
| 桌面代理 | pyautogui 模拟真人操作微信 | Pro |
| 数据飞轮 | 从成交数据自动优化策略 | Enterprise |
配置
首次启动
gavvy start
自动生成 API Key,保存到 ~/.gavvy/api_key.txt。
API Key(可选)
# Community 版(默认,所有功能可用但含升级提示)
# export GAVVY_API_KEY=sk-ent-你的Key
# Pro 版(真实寻客+Agent LLM+渠道发送)
# export GAVVY_API_KEY=sk-pro-你的Key
# Enterprise 版(全部功能)
# export GAVVY_API_KEY=sk-ent-你的Key
端口
# 默认 8877
gavvy start --port 8888
# 或
export GAVVY_PORT=8888 && gavvy start
快速体验链路
方法 A:一键脚本
python3 scripts/gavvy-quickstart.py
方法 B:手动操作
- 启动:
gavvy start - 打开 http://localhost:8877
- 导航 → 销售流程
- 点击"+ 新建流程"
- 按向导:
- 选类目(软件服务)
- 输入关键词(AI 客服, CRM)
- 选商品(Gavvy Sales)
- 设置过滤规则
- 选平台(1688/alibaba)
- 选渠道(email)
- 确认执行 → 自动寻客+生成提案
方法 C:API 调用
# 查看产品目录
curl http://localhost:8877/api/products
# 创建流程
curl -X POST http://localhost:8877/api/flow/create \
-H 'Content-Type: application/json' \
-d '{"name":"我的流程"}'
# 查看流程状态
curl http://localhost:8877/api/flow/list
项目结构
~/.gavvy/ ← 配置和数据目录
├── config.json ← 配置
├── api_key.txt ← API Key
└── logs/ ← 日志
pip install gavvy-salesmaster
└── gavvy start ← 一键启动
内测须知
- 当前为 Alpha 版,API 可能变更
- 数据存在本地
~/.gavvy/,pip update 不丢失 - 桌面代理需要安装
pip install pyautogui - 遇到问题:查看日志
~/.gavvy/logs/server.log - 反馈请提交 Issue 或联系内测群
技术栈
- Python 3.11+, FastAPI, Uvicorn
- 零外部依赖即可运行(仅需 fastapi+uvicorn)
- 可选:pyautogui(桌面代理)、httpx(企业版加速)
Gavvy Team · 内测版 v4.0.0
Metadata
Release files for gavvy-salesmaster 4.0.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| gavvy_salesmaster-4.0.0.tar.gz | 496.3 kB | Without provenance | Details for gavvy_salesmaster-4.0.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| gavvy_salesmaster-4.0.0-py3-none-any.whl | Python 3 | none | any | Details for gavvy_salesmaster-4.0.0-py3-none-any.whl |
Total release size: 6.9 MB
Release files / gavvy_salesmaster-4.0.0.tar.gz
| Download URL | gavvy_salesmaster-4.0.0.tar.gz |
|---|---|
| Size | 496.3 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
e1624572bbaba455e3e53df286d33596088b3374a71a5d9562c8785c5f1c8048
|
|
BLAKE2b-256 checksum How to use checksums |
9bcbd14bb5170d117a283e0869d191415de4ee0bf8ae895966d62912bedf23af
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / gavvy_salesmaster-4.0.0-py3-none-any.whl
| Download URL | gavvy_salesmaster-4.0.0-py3-none-any.whl |
|---|---|
| Size | 6.4 MB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
b51b3f1fc707217fe8d084351c558d22629d6405b7292221170af1e5998059cd
|
|
BLAKE2b-256 checksum How to use checksums |
fb557dbba59ab191de8d4b2a13ff9942dfb9c979fae397356528f24f1484a1da
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for gavvy-salesmaster 4.0.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.