胶州做网站wordpress 插件 pdf

一、用 Llama-index 创建 Agent

LlamaIndex 实现 Agent，需要导入：

• Function Tool：将工具函数放在 Function Tool 对象中
  • 工具函数 -> 完成 Agent 任务。⚠️大模型会根据函数注释来判断使用哪个函数来完成任务，所以，注释一定要写清楚函数功能和返回值
• ReActAgent：通过结合推理（Reasoning）和行动（Acting）来创建动态的 LLM Agent 的框架
  • 初始推理：agent首先进行推理步骤，以理解任务、收集相关信息并决定下一步行为
  • 行动：agent基于其推理采取行动——例如查询API、检索数据或执行命令
  • 观察：agent观察行动的结果并收集任何新的信息
  • 优化推理：利用新消息，代理再次进行推理，更新其理解、计划或假设
  • 重复：代理重复该循环，在推理和行动之间交替，直到达到满意的结论或完成任务

1. 测试模型

• 使用一个数学能力较差的模型

# https://bailian.console.aliyun.com/#/model-market/detail/chatglm3-6b?tabKey=sdk
from dashscope import Generation messages = [{'role': "system", 'content': 'You are a helpful assistant.'},{'role': "user", 'content': '9.11 和 9.8 哪个大？'},
]gen = Generation()
response = gen.call(api_key=os.getenv("API_KEY"),model='chatglm3-6b',messages=messages,result_format='message',
)print(response.output.choices[0].message.content)

9.11 比 9.8 更大。

2. 自定义一个接口类

# https://www.datawhale.cn/learn/content/86/3058
from llama_index.core.llms import CustomLLM, LLMMetadata, CompletionResponse
from llama_index.core.llms.callbacks import llm_completion_callback
import os
from typing import Any, Generatorclass MyLLM(CustomLLM):api_key: str = Field(default=os.getenv("API_KEY"))base_url: str = Field(default=os.getenv("BASE_URL"))client: Generation = Field(default=Generation(), exclude=True)model_name: str@propertydef metadata(self) -> LLMMetadata:return LLMMetadata(model_name=self.model_name,context_window=32768,  # 根据模型实际情况设置num_output=512)@llm_completion_callback()def complete(self, prompt: str, **kwargs: Any) -> CompletionResponse:messages = [{'role': "user", 'content': prompt},  # 根据API需求调整]response = self.client.call(api_key=self.api_key,model=self.model_name,messages=messages,result_format='message',)return CompletionResponse(text=response.output.choices[0].message.content)@llm_completion_callback()def stream_complete(self, prompt: str, **kwargs: Any) -> Generator[CompletionResponse, None, None]:response = self.client.call(api_key=self.api_key,model=self.model_name,messages=[{'role': "user", 'content': prompt}],stream=True,)current_text = ""for chunk in response:content = chunk.output.choices[0].delta.get('content', '')current_text += contentyield CompletionResponse(text=current_text, delta=content)# 实例化时使用大写环境变量名
llm = MyLLM(api_key=os.getenv("API_KEY"), base_url=os.getenv("BASE_URL"), model_name='chatglm3-6b'
)

3. 使用 ReActAgent & FunctionTool 构建 Agent

from llama_index.core.tools import FunctionTool
from llama_index.core.agent import ReActAgentdef compare_number(a: float, b: float) -> str:"""比较两个数的大小"""if a > b:return f"{a} 大于 {b}"elif a < b:return f"{a} 小于 {b}"else:return f"{a} 等于 {b}"tool = FunctionTool.from_defaults(fn=compare_number)
agent = ReActAgent.from_tools([tool], llm=llm, verbose=True)
response = agent.chat("9.11 和 9.8 哪个大？使用工具计算")
print(response)

> Running step 8c56594a-4edd-4d63-a196-99198df94e12. Step input: 9.11 和 9.8 哪个大？使用工具计算
Observation: Error: Could not parse output. Please follow the thought-action-input format. Try again.
Running step 22bbb997-4b52-4230-8a4d-d8eda252b7d1. Step input: None
Thought: The user is asking to compare the numbers 9.11 and 9.8, and they would like to know which one is greater. I can use the compare_number function to achieve this.
Action: compare_number
Action Input: {'a': 9.11, 'b': 9.8}
Observation: 9.11 小于 9.8
> Running step c6ce4186-3ea7-48c8-8f76-7d219118afc4. Step input: None
Thought: 根据比较结果，9.11小于9.8。
Answer: 9.11 < 9.8
9.11 < 9.8

二、数据库对话 Agent

1. SQLite 数据库

1.1 创建数据库 & 连接

import sqlite3# 连接数据库
conn = sqlite3.connect('mydatabase.db')# 创建游标对象
cursor = conn.cursor()

1.2 创建、插入、查询、更新、删除数据

• 创建

# create
create_tabel_sql = """CREATE TABLE IF NOT EXISTS employees ( id INTEGER PRIMARY KEY, name TEXT NOT NULL, department TEXT,salary REAL );	"""cursor.execute(create_table_sql)# 提交事务
conn.commit()

• 插入

insert_sql = "INSERT INTO employees (name, department, salary) VALUES (?, ?, ?)"# insert single
data = ("Alice", "Engineering", 75000.0)
cursor.execute(insert_sql, data)
cursor.commit()# insert many
employees = [("Bob", "Marketing", 68000.0),("Charlie", "Sales", 72000.0)
]
cursor.executemany(insert_sql, employees)
cursor.commit()

• 查询

# 查询
# 条件查询（按部门筛选） 
cursor.execute("SELECT name, salary FROM employees WHERE department=?", ("Engineering",)) 
engineering_employees = cursor.fetchall() 
print("\nEngineering department:") 
for emp in engineering_employees: print(f"{emp[0]} - ${emp[1]:.2f}")

• 更新

update_sql = "UPDATE employees SET salary = ? WHERE name = ?"
cursor.execute(update_sql, (8000.0, 'Alice'))
cursor.commit()

• 删除

delect_sql = "DELECT FROM employees WHERE name = ?"
cursor.execute(delect_sql, ("Bob",))
conn.commit()

1.3 关闭连接

# 关闭游标和连接（释放资源）
cursor.close()
conn.close()

建立数据库

python建立数据库的方法

import sqlite3
# create sql
sqlite_path = "llmdb.db"
# 1. 创建数据库、创建游标对象
conn = sqlite3.connect(sqlite_path)
curosr = conn.cursor()create_sql = """CREATE TABLE `section_stats` (`部门` varchar(100) DEFAULT NULL,`人数` int(11) DEFAULT NULL);"""insert_sql = """INSERT INTO section_stats (部门, 人数)values(?, ?)"""data = [['专利部', 22], ['商务部', 25]]# 2. 创建数据库
cursor.execute(create_sql)
cursor.commit()
# 3. 插入数据
cursor.executemany(insert_sql, data)
cursor.commit()
# 4. 关闭连接
cursor.close()
conn.close()

2. ollama

安装 ollama
- 官网下载安装： [https://ollama.com](https://ollama.com/)
- 模型安装， 如运行 ollama run qwen2.5:7b（出现了success安装成功）- 然后出现 >>> 符号，即对话窗口， 输入 /bye 推出交互页面- 浏览器输入 127.0.0.1:11434, 如果出现 ollama is running，说明端口运行正常
- 环境配置- `OLLAMA_MODELS` & `OLLAMA_HOST` 环境配置1. 创建存储路径，如`mkdir -p ~/programs/ollama/models`2. 编辑环境变量配置路径 `vim ~/.bash_profile #  ~/.zshrc``export OLLAMA_MODELS=~/programs/ollama/models``export OLLAMA_HOST=0.0.0.0:11434`- 确定mac地址和防火墙允许：系统偏好设置 -> 网络 （安全性和隐私-> 防火墙）- 使配置生效`source ~/.bash_profile #  ~/.zshrc`

3. 配置对话 & Embedding 模型

!pip install llama-index-llms-dashscope

三、RAG 接入Agent

https://github.com/deepseek-ai/DeepSeek-R1/blob/main/README.md

https://github.com/deepseek-ai/DeepSeek-R1/blob/main/README.md