Hanah

from openai import OpenAI
from pydantic import Field  # 導入Field，用於Pydantic模型中定義字段的元數據
from llama_index.core.llms import (
    CustomLLM,
    CompletionResponse,
    LLMMetadata,
)
from llama_index.core.embeddings import BaseEmbedding
from llama_index.core.llms.callbacks import llm_completion_callback
from typing import List, Any, Generator
# 定義OurLLM類，繼承自CustomLLM基類
class OurLLM(CustomLLM):
    api_key: str = Field(default=api_key)
    base_url: str = Field(default=base_url)
    model_name: str = Field(default=chat_model)
    client: OpenAI = Field(default=None, exclude=True)  # 顯式聲明 client 字段

    def __init__(self, api_key: str, base_url: str, model_name: str = chat_model, **data: Any):
        super().__init__(**data)
        self.api_key = api_key
        self.base_url = base_url
        self.model_name = model_name
        self.client = OpenAI(api_key=self.api_key, base_url=self.base_url)  # 使用傳入的api_key和base_url初始化 client 實例

    @property
    def metadata(self) -> LLMMetadata:
        """獲取LLM元數據。"""
        return LLMMetadata(
            model_name=self.model_name,
        )

    @llm_completion_callback()
    def complete(self, prompt: str, **kwargs: Any) -> CompletionResponse:
        response = self.client.chat.completions.create(model=self.model_name, messages=[{"role": "user", "content": prompt}])
        if hasattr(response, 'choices') and len(response.choices) > 0:
            response_text = response.choices[0].message.content
            return CompletionResponse(text=response_text)
        else:
            raise Exception(f"意外的響應格式: {response}")

    @llm_completion_callback()
    def stream_complete(
        self, prompt: str, **kwargs: Any
    ) -> Generator[CompletionResponse, None, None]:
        response = self.client.chat.completions.create(
            model=self.model_name,
            messages=[{"role": "user", "content": prompt}],
            stream=True
        )

        try:
            for chunk in response:
                chunk_message = chunk.choices[0].delta
                if not chunk_message.content:
                    continue
                content = chunk_message.content
                yield CompletionResponse(text=content, delta=content)

        except Exception as e:
            raise Exception(f"意外的響應格式: {e}")

llm = OurLLM(api_key=api_key, base_url=base_url, model_name=chat_model)

response = llm.stream_complete("你是誰？")
for chunk in response:
    print(chunk, end="", flush=True)

import sys
import os

sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..")))

from llama_index.core.agent import ReActAgent
from llama_index.core.tools import FunctionTool


def multiply(a: float, b: float) -> float:
    """乘以兩個數並返回乘積"""
    return a * b


def add(a: float, b: float) -> float:
    """將兩個數相加並返回總和"""
    return a + b


def main():

    multiply_tool = FunctionTool.from_defaults(fn=multiply)
    add_tool = FunctionTool.from_defaults(fn=add)

    # 創建ReActAgent實例
    agent = ReActAgent.from_tools([multiply_tool, add_tool], llm=llm, verbose=True)

    response = agent.chat("20+（2*4）等於多少？使用工具計算每一步")

    print(response)


if __name__ == "__main__":
    main()

def get_weather(city: str) -> int:
    """
    獲取指定城市的天氣溫度。

    參數：
    city (str): 城市的名稱或縮寫。

    返回：
    int: 城市的溫度。對於'NY'（紐約）返回20，
         對於'BJ'（北京）返回30，對於未知城市返回-1。
    """

    # 將輸入城市轉換為大寫以處理不區分大小寫的比較
    city = city.upper()

    # 檢查城市是否為紐約（'NY'）
    if city == "NY":
        return 20  # 對於紐約返回20°C

    # 檢查城市是否為北京（'BJ'）
    elif city == "BJ":
        return 30  # 對於北京返回30°C

    # 如果城市既不是'NY'也不是'BJ'，則返回-1以表示未知城市
    else:
        return -1

weather_tool = FunctionTool.from_defaults(fn=get_weather)

agent = ReActAgent.from_tools([multiply_tool, add_tool, weather_tool], llm=llm, verbose=True)

response = agent.chat("紐約天氣怎麼樣?")