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.dtcms.com/a/296504.html

相关文章:

  • 力扣刷题(第九十七天)
  • 强化学习入门三(SARSA)
  • 专题:2025微短剧行业生态构建与跨界融合研究报告|附100+份报告PDF汇总下载
  • LeetCode 1695.删除子数组的最大得分:滑动窗口(哈希表)
  • 07 RK3568 Debian11 网络优先级
  • “抓了个寂寞”:一次实时信息采集的意外和修复
  • 网络基础19--OSPF路由协议(上)
  • 基于QT(C++)实现(图形界面)通讯录系统
  • JavaJSP
  • 【SpringAI实战】FunctionCalling实现企业级自定义智能客服
  • Qt 调用ocx的详细步骤
  • 单片机学习课程
  • 数据推荐丨海天瑞声7月数据集上新啦!
  • 海外红人营销的下一站:APP出海如何布局虚拟网红与UGC生态?
  • idea监控本地堆栈
  • Redis分布式锁的学习(八)
  • 无源域自适应综合研究【2】
  • Qt连接MySql数据库
  • SAP B1 DTW成功登录后点击下一步提示没有权限读取清单
  • QML 模型
  • 阿里云SLS未开启索引时无法查询日志内容
  • 11.事务
  • 【GoLang#1】:Go 语言概述(背景 | 环境配置 | 特点 | 学习)
  • Redis单线程模型(含面试题)
  • pytorch常用函数
  • 【MySQL数据库备份与恢复1】二进制日志,mysqlbinlog
  • Linux Wlan 无线网络驱动开发-scan协议全流程详解
  • 企业安全基石:解锁等保测评的战略价值
  • 循环神经网络--LSTM模型
  • 15.2 DeepSpeed显存优化实战:7B大模型训练资源从84GB压缩到10GB!