前言:在ChatGLM3-6B模型中,我们调用了tool工具(ChatGLM3-6B-Base,ChatGLM3-6B-32K没有调用tool功能),这里我们进行简单的demo。
如何制作tools(下列代码中有两个tool:“track”,“text-to-speech”):
tools = [
{
"name": "track",
"description": "追踪指定股票的实时价格",
"parameters": {
"type": "object",
"properties": {
"symbol": {
"description": "需要追踪的股票代码"
}
},
"required": ['symbol']
}
},
{
"name": "text-to-speech",
"description": "将文本转换为语音",
"parameters": {
"type": "object",
"properties": {
"text": {
"description": "需要转换成语音的文本"
},
"voice": {
"description": "要使用的语音类型(男声、女声等)"
},
"speed": {
"description": "语音的速度(快、中等、慢等)"
}
},
"required": ['text']
}
}
]
system_info = {"role": "system", "content": "Answer the following questions as best as you can. You have access to the following tools:", "tools": tools}
tools参数解释:
"name":为tool工具名;
"description":对工具的作用进行描述;
"parameters":
"type":默认为"object";
"properties":在此定义工具的属性以及对属性值的描述;
"required": 需要返回的属性;
加载模型:
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("path_to_model", trust_remote_code=True)
model = AutoModel.from_pretrained("path_to_model", trust_remote_code=True, device='cuda')
model = model.eval()
在调用模型时,我们的query和tool相关时,模型会自动调用tool并反馈:
history = [system_info]
query = "帮我查询股票10111的价格"
response, history = model.chat(tokenizer, query, history=history)
print(response)
response输出为{'name': 'track', 'parameters': {'symbol': '10111'}} #模型的反馈
这里result模拟的是外部的反馈数据,将反馈和history一起传递给模型
(这里 role="observation" 表示输入的是工具调用的返回值而不是用户输入,不能省略。)
import json
result = json.dumps({"price": 12412}, ensure_ascii=False)
response, history = model.chat(tokenizer, result, history=history, role="observation")
print(response)
这是repsonse的值
“根据您的查询,我已经成功调用了追踪股票价格的API,并返回了股票代码为10111的实时股价。根据API调用结果,当前股票的价格为12412元。希望这个信息对您有所帮助! ”