shobrook/saplings 源码下载_部署教程

项目概述

Plug-and-play tree search for agents

项目地址

https://github.com/shobrook/saplings

项目页面预览

shobrook/saplings preview

关键指标

Stars：271
主要语言：Python
License：Apache License 2.0
最近更新：2025-07-27T09:29:45Z
默认分支：master

本站高速下载（国内可用）

源码压缩包下载：点击下载（本站镜像）
SHA256：1499161778918257f8d35d75159dcee6d2ff32dec7d1070da73157bca2da7582

安装部署要点（README 精选）

Installation

$ pip install saplings

Quickstart

<!–Let’s build an agent that uses a web search tool to complete tasks. Our agent will be equipped with Monte Carlo Tree Search (MCTS) as a reasoning algorithm.

from saplings.examples import WebSearchTool
from saplings import MonteCarloAgent, Evaluator, OpenAI

model = OpenAI(model="gpt-4o")
evaluator = Evaluator(model)
tools = [WebSearchTool()]

agent = MonteCarloAgent(tools, model, evaluator)
messages, _, _ = agent.run("Create a table comparing ancient astronomical tools with their origin, accuracy, and modern equivalents.")
```-->

Below is a simple agent implementing Monte Carlo tree search (MCTS). It's equipped with a multiplication tool to solve tricky arithmetic problems.

```python
from saplings.examples import MultiplicationTool
from saplings import MonteCarloAgent, Evaluator, Model

model = Model(model="openai/gpt-4o") # Wraps LiteLLM
evaluator = Evaluator(model)
tools = [MultiplicationTool()]

agent = MonteCarloAgent(tools, model, evaluator)
messages, _, _ = agent.run("Let x = 9418.343 * 8.11 and y = 2x. Calculate (xy)(x^2).")

This is the “bare minimum” for setting up a search agent with saplings –– just a few lines of code. There are a lot more parameters you can control, all covered in the docs. But let’s first walk through the basics of creating your own tools and configuring an agent.