当前位置: 首页 > news >正文

mac llama_index agent算术式子计算示例

本文通过简单数学计算,示例llama_index使用agent解决复杂任务过程。

假设mac本地llama_index环境已安装,过程参考

mac测试ollama llamaindex-CSDN博客

测试mac笔记本内存8G,所以使用较小LLM完成示例。

ollama pull qwen3:1.7b

qwen3:1.7b能力较弱,需要prompt明确要求使用agent工具,遵守计算前后顺序。

prompt示例如下

"使用agent工具计算,遵守计算的先后顺序, 20 + (2 x 3) * 4?"

程序示例如下

from llama_index.core.agent import ReActAgent
from llama_index.core.tools import FunctionTool
from llama_index.core import Settings
from llama_index.llms.ollama import OllamaSettings.embed_model = OllamaEmbedding(model_name="yxl/m3e:latest")  
Settings.llm = Ollama(model="qwen3:1.7b", request_timeout=360) # 定义数学计算工具
def multiply(a: float, b: float) -> float:"""Multiply two numbers and returns the product"""return a * bmultiply_tool = FunctionTool.from_defaults(fn=multiply)def add(a: float, b: float) -> float:"""Add two numbers and returns the sum"""return a + badd_tool = FunctionTool.from_defaults(fn=add)# 实例化 ReActAgent
agent = ReActAgent.from_tools([multiply_tool, add_tool], verbose=True
)# 测试代理
response = agent.chat("使用agent工具计算,遵守计算的先后顺序, 20 + (2 x 3) * 4?")
print(response)

如下所示,llama_index将示例式子计算过程分解为agent工具的调用过程。

首先是红色部分,调用multiply完成2*3=6。

然后是棕色部分,调用multiply完成6*4=24。

最后是紫色部分,调用add完成20+24=44。

> Running step 91dcc552-f7b2-4cc3-9af1-cf07812cc8b8. Step input: 请使用agent工具计算,遵守计算的先后顺序, 20 + (2 x 3) * 4?
Thought: <think>
Okay, let's see. The user wants to calculate 20 + (2 x 3) * 4 using the agent tool. Hmm, first I need to break down the expression according to the order of operations. Parentheses come first, so I should calculate 2 x 3 first. That's 6. Then multiply by 4, which gives 24. Now add that to 20. So 20 + 24 equals 44. Wait, but the tools available are multiply and add. Let me check the tools again. The multiply tool takes two numbers, and the add tool adds two numbers. So I need to do the multiplication first. Let me do the steps: first multiply 2 and 3, then multiply the result by 4, then add 20. So the steps would be: multiply 2 and 3 to get 6, then multiply by 4 to get 24, then add 20. So the final answer should be 44. I need to use the tools in the correct order. Let me use the multiply tool first for 2 and 3, then multiply the result by 4, then add 20. Let's see how that works.
</think>

Thought: I need to calculate 20 + (2 x 3) * 4 using the available tools. First, multiply 2 and 3, then multiply the result by 4, and finally add 20.
Action: multiply
Action Input: {"a": 2, "b": 3}
Observation: 6

Thought: Now multiply the result (6) by 4.
Action: multiply
Action Input: {"a": 6, "b": 4}
Observation: 24

Thought: Add 24 to 20.
Action: add
Action Input: {'a': 24, 'b': 20}
Observation: 44

> Running step ab11a064-bdde-42df-9fcf-3aa409e18eab. Step input: None
Thought: I can answer without using any more tools. I'll use the user's language to answer
Answer: 44
44

对于更复杂任务和能力更强的LLM,处理过程是类似的。

更强的LLM能更有效的将复杂问题分解为多个agent调用过程,通过agent协同解决复杂问题。

reference

---

mac测试ollama llamaindex

https://blog.csdn.net/liliang199/article/details/149542926

http://www.lryc.cn/news/598878.html

相关文章:

  • Springmvc的自动解管理
  • 元素竖向的百分比设定是相对于父容器的高度吗?
  • 文思助手、新华妙笔 AI材料星的公文写作深度测评
  • 分布式推客系统开发全解:微服务拆分、佣金结算与风控设计
  • skywalking应用性能监控
  • iview Select的Option边框显示不全(DatePicker也会出现此类问题)
  • k8s之Ingress服务接入控制器
  • vlm MiniCPM 学习部署实战
  • MinIO Go 客户端使用详解:对象存储开发实战指南
  • 探索双链表:C语言中的链式结构魔法
  • matplotlib的详细知识点
  • AUTOSAR进阶图解==>AUTOSAR_SWS_BSWModeManager
  • ANSYS Fluent 管内流动仿真
  • MySQL 8.0 OCP 1Z0-908 题目解析(35)
  • 字符串和对象的深拷贝和浅拷贝
  • 电商接口常见误区与踩坑提醒
  • Spring Cloud Alibaba Sentinel 源码阅读之流量控制算法
  • PCL 间接平差拟合球
  • Spring MVC 统一响应格式:ResponseBodyAdvice 从浅入深
  • 论文阅读:《针对多目标优化和应用的 NSGA-II 综述》一些关于优化算法的简介
  • 7.24 C/C++蓝桥杯 | 排序算法
  • 面试题(技术面+hr面)
  • Sklearn 机器学习 数值标准化
  • C++高效实现轨迹规划、自动泊车、RTS游戏、战术迂回包抄、空中轨迹、手术机器人、KD树
  • JSONObject相关知识点
  • 【MediaTek】AN7563编译出现npu/en7563/host/Makefile: No such file or directory
  • Silly Tavern 教程②:首次启动与基础设置
  • Windows 如何更改 ModelScope 的模型下载缓存位置?
  • 循环神经网络--LSTM模型
  • 跨境支付入门~国际支付结算(区块链篇)