A LLM Agent Python package.
Project description
简介
LLM: 调用大模型的便捷方法,包括本地大模型与线上大模型,其中包括主流大模型API,GLM/Qwen/Yi/MoonShot等100多种大模型。采用了统一的调用风格与方式,使得大模型调用更加便捷。Message: 消息管理机制,方便管理System/User/Assistant Message,并进行大模型对话的记忆管理。Embedding: 提供一系列向量化方法,包括本地与API向量化模型的调用,以及文本的各类向量化匹配、与向数据库对接等功能。RAG: 提供一系列文档知识库问答方法。AgentTask: 提供Agent任务流的调度,实现Agent任务的各种自动化流转。AgentTools: 提供一系列Agent工具函数,实现更方便的Agent使用,如让大模型实现股票期货数据查询问答、数据分析作图等。Other: 其他便捷方法。
如何安装?
# [推荐] 安装最新版本ZLAI的所有模块
pip install zlai[all] -U
# [推荐] 最轻量化安装
pip install zlai[tiny] -U
# [推荐] 安装全部大模型API依赖
pip install zlai[api] -U
您也可以在GitHub/PyPi查看最新代码与最新发行版本。
Star History
微信群
@2024/03/27
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
zlai-0.3.116.tar.gz
(293.5 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
zlai-0.3.116-py3-none-any.whl
(495.5 kB
view details)
File details
Details for the file zlai-0.3.116.tar.gz.
File metadata
- Download URL: zlai-0.3.116.tar.gz
- Upload date:
- Size: 293.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.10.15 Linux/6.8.0-1014-azure
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0912208ced6f117f4bec4d6779ad11317948fe7d8a53863f4c7d12ae670f1c61
|
|
| MD5 |
b8ece72df95996269f02f0d9673b8d88
|
|
| BLAKE2b-256 |
e1c9822e2e211c2402c21a8563b9e2a07ea5f7c5fd0f558a551f9374e3b44c7a
|
File details
Details for the file zlai-0.3.116-py3-none-any.whl.
File metadata
- Download URL: zlai-0.3.116-py3-none-any.whl
- Upload date:
- Size: 495.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/1.8.3 CPython/3.10.15 Linux/6.8.0-1014-azure
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6eae2eddee26cdf0d462e40f3a8c558003eb006ea79d0631a4ff757f198a2690
|
|
| MD5 |
fd48bab207c215bf1e80303986523781
|
|
| BLAKE2b-256 |
4d6a37389c6e198e7689d572a249da347a0048eca8779917b4973e1fe71f58e1
|