python_ai/qwen_agenttext.py

import pprint
import urllib.parse
import json5
from qwen_agent.agents import Assistant
from qwen_agent.tools.base import BaseTool, register_tool
import requests
import baidusearch
import tqdm

# 使用示例



# Step 1 (Optional): Add a custom tool named `my_image_gen`.
@register_tool('my_image_gen')
class MyImageGen(BaseTool):
    # The `description` tells the agent the functionality of this tool.
    description = 'AI painting (image generation) service, input text description, and return the image URL drawn based on text information.'
    # The `parameters` tell the agent what input parameters the tool has.
    parameters = [{
        'name': 'prompt',
        'type': 'string',
        'description': 'Detailed description of the desired image content, in English',
        'required': True
    }]

    def call(self, params: str, **kwargs) -> str:
        # `params` are the arguments generated by the LLM agent.
        prompt = json5.loads(params)['prompt']
        # 对提示词进行URL编码
        prompt = urllib.parse.quote(prompt)
        #
        return json5.dumps(
            {'image_url': f'https://image.pollinations.ai/prompt/{prompt}'},
            ensure_ascii=False)


@register_tool('chaxun')
class MyImageGen(BaseTool):
    # The `description` tells the agent the functionality of this tool.
    description = '如果你不会，请使用此工具进行联网查询'
    # The `parameters` tell the agent what input parameters the tool has.
    parameters = [{
        'name': 'prompt',
        'type': 'string',
        'description': '请你描述需要提问的信息,以此帮助你了解更多的信息',
        'required': True
    }]

    def call(self, params: str, **kwargs) -> str:
        # `params` are the arguments generated by the LLM agent.
        prompt = json5.loads(params)['prompt']
        # 对提示词进行URL编码
        prompt = urllib.parse.quote(prompt)
        #
        search_tool = baidusearch.search(prompt, num_results=20)
        print(search_tool)
        return search_tool
# Step 2: Configure the LLM you are using.
# 这里是需要配置模型的地方。需要填写模型名字，以及model_server，即模型所在服务器名字，如果没有，也可以考虑使用api_key。
llm_cfg = {
    # Use the model service provided by DashScope:
    # model：模型名称
    # model_server：模型所在的服务器
    # api_key： 所使用到的api-key，可以显示的设置，也可以从环境变量中获取

    'model':"qwen2-72b-instruct",
    'model_server': 'DashScope',  # base_url, also known as api_base
    'api_key': 'sk-ea89cf04431645b185990b8af8c9bb13',
    # 'api_key': 'YOUR_DASHSCOPE_API_KEY',
    # It will use the `DASHSCOPE_API_KEY' environment variable if 'api_key' is not set here.

    # Use a model service compatible with the OpenAI API, such as vLLM or Ollama:
    # 'model': 'Qwen1.5-7B-Chat',
    # 'model_server': 'http://localhost:8000/v1',  # base_url, also known as api_base
    # 'api_key': 'EMPTY',

    # (Optional) LLM hyperparameters for generation:
    # 用于调整生成参数的可选配置
    'generate_cfg': {
        'top_p': 0.8
    }
}

# Step 3: Create an agent. Here we use the `Assistant` agent as an example, which is capable of using tools and reading files.

# agent的提示词指令
system_instruction = '''
你是一个乐于助人的助手。
收到用户的请求后，您应：
你应该进行思考，判断是否使用工具，
如果遇到你不会回答,请使用工具[chaxun]
'''

# 工具列表，指定Assistant可以访问的工具，一个是自定义的工具，一个是代码执行器
tools = ["chaxun"]  # `code_interpreter` is a built-in tool for executing code.
# 助理可以读取的文件路径
# files = ['./examples/resource/doc.pdf']  # Give the bot a PDF file to read.

# 初始化Assistant
bot = Assistant(llm=llm_cfg,
                system_message=system_instruction,
                function_list=tools,
                # files=files
                )

# Step 4: Run the agent as a chatbot.
messages = []  # This stores the chat history.
def getxinx(context):
    # For example, enter the query "draw a dog and rotate it 90 degrees".
    # query = input('user query: ')
    # Append the user query to the chat history.
    messages=[({'role': 'user', 'content': context})]
    print(messages)
    response = []
    event_id = 0
    for rsp in bot.run(messages=messages):
        response.append(rsp)
        yield "请稍等.."
    # len()
    # for i in bot.run(messages=messages):
    #     #     for number in range(1, 10):
    #     print(i)
    #     print(i[len(i)-1]['content'])
    #     event_id += 1
    #     yield f"id: {event_id}\n"
    #     yield f"event: time-update\n"
    #     if(i[len(i)-1]['role']=='assistant'):
    #         yield "data: {}\n\n".format(str(i[len(i)-1]['content'].replace('\n\n','')))  # 每次生成一个数字就发送
    #     else:
    #         yield f"data: \n\n"  # 每次生成一个数字就发送
    # Streaming output.