examples/langchain_tooluse.ipynb
本文档主要介绍如何让千问调用 LangChain 框架中实现好的谷歌搜索、 WolframAlpha 等工具。将主要基于 ReAct Prompting 技术，一种特殊的链式思考（Chain-of-Thought，简称 CoT）提示技巧，来实现这一目的。
# 安装千问的依赖
!cd Qwen-7b
!pip install -r requirements.txt
# 安装 langchain 相关依赖
!pip install langchain google-search-results wolframalpha arxiv;
以下引入几个常用 APIs 作为演示：
注1：此处推荐模仿此案例，细致地构造给千问看的工具描述。
注2：谷歌搜索（SERPAPI）， WolframAlpha 需自行申请它们的 API_KEY 后才能使用。
from langchain import SerpAPIWrapper
from langchain.utilities.wolfram_alpha import WolframAlphaAPIWrapper
from langchain.utilities import ArxivAPIWrapper
from langchain.tools.python.tool import PythonAstREPLTool
from typing import Dict, Tuple
import os
import json
from transformers import AutoModelForCausalLM, AutoTokenizer
from transformers.generation import GenerationConfig
# 为了使用谷歌搜索（SERPAPI）， WolframAlpha，您需要自行申请它们的 API KEY，然后填入此处
os.environ['SERPAPI_API_KEY'] = '重要！请在这里填入您的 SERPAPI_API_KEY！'
os.environ['WOLFRAM_ALPHA_APPID'] = '重要！请在这里填入您的 WOLFRAM_ALPHA_APPID！'
search = SerpAPIWrapper()
WolframAlpha = WolframAlphaAPIWrapper()
arxiv = ArxivAPIWrapper()
python=PythonAstREPLTool()
def tool_wrapper_for_qwen(tool):
def tool_(query):
query = json.loads(query)["query"]
return tool.run(query)
return tool_
# 以下是给千问看的工具描述：
TOOLS = [
{
'name_for_human':
'google search',
'name_for_model':
'Search',
'description_for_model':
'useful for when you need to answer questions about current events.',
'parameters': [{
"name": "query",
"type": "string",
"description": "search query of google",
'required': True
}],
'tool_api': tool_wrapper_for_qwen(search)
},
{
'name_for_human':
'Wolfram Alpha',
'name_for_model':
'Math',
'description_for_model':
'Useful for when you need to answer questions about Math, Science, Technology, Culture, Society and Everyday Life.',
'parameters': [{
"name": "query",
"type": "string",
"description": "the problem to solved by Wolfram Alpha",
'required': True
}],
'tool_api': tool_wrapper_for_qwen(WolframAlpha)
},
{
'name_for_human':
'arxiv',
'name_for_model':
'Arxiv',
'description_for_model':
'A wrapper around Arxiv.org Useful for when you need to answer questions about Physics, Mathematics, Computer Science, Quantitative Biology, Quantitative Finance, Statistics, Electrical Engineering, and Economics from scientific articles on arxiv.org.',
'parameters': [{
"name": "query",
"type": "string",
"description": "the document id of arxiv to search",
'required': True
}],
'tool_api': tool_wrapper_for_qwen(arxiv)
},
{
'name_for_human':
'python',
'name_for_model':
'python',
'description_for_model':
"A Python shell. Use this to execute python commands. When using this tool, sometimes output is abbreviated - Make sure it does not look abbreviated before using it in your answer. "
"Don't add comments to your python code.",
'parameters': [{
"name": "query",
"type": "string",
"description": "a valid python command.",
'required': True
}],
'tool_api': tool_wrapper_for_qwen(python)
}
]
根据prompt模版、query、工具的信息构建prompt
TOOL_DESC = """{name_for_model}: Call this tool to interact with the {name_for_human} API. What is the {name_for_human} API useful for? {description_for_model} Parameters: {parameters} Format the arguments as a JSON object."""
REACT_PROMPT = """Answer the following questions as best you can. You have access to the following tools:
{tool_descs}
Use the following format:
Question: the input question you must answer
Thought: you should always think about what to do
Action: the action to take, should be one of [{tool_names}]
Action Input: the input to the action
Observation: the result of the action
... (this Thought/Action/Action Input/Observation can be repeated zero or more times)
Thought: I now know the final answer
Final Answer: the final answer to the original input question
Begin!
Question: {query}"""
def build_planning_prompt(TOOLS, query):
tool_descs = []
tool_names = []
for info in TOOLS:
tool_descs.append(
TOOL_DESC.format(
name_for_model=info['name_for_model'],
name_for_human=info['name_for_human'],
description_for_model=info['description_for_model'],
parameters=json.dumps(
info['parameters'], ensure_ascii=False),
)
)
tool_names.append(info['name_for_model'])
tool_descs = '\n\n'.join(tool_descs)
tool_names = ','.join(tool_names)
prompt = REACT_PROMPT.format(tool_descs=tool_descs, tool_names=tool_names, query=query)
return prompt
prompt_1 = build_planning_prompt(TOOLS[0:1], query="加拿大2023年人口统计数字是多少？")
print(prompt_1)
将prompt作为输入获得response
# 国内连 hugginface 网络不好，这段代码可能需要多重试
checkpoint = "Qwen/Qwen-7B-Chat"
TOKENIZER = AutoTokenizer.from_pretrained(checkpoint, trust_remote_code=True)
MODEL = AutoModelForCausalLM.from_pretrained(checkpoint, device_map="auto", trust_remote_code=True).eval()
MODEL.generation_config = GenerationConfig.from_pretrained(checkpoint, trust_remote_code=True)
MODEL.generation_config.do_sample = False # greedy
stop = ["Observation:", "Observation:\n"]
react_stop_words_tokens = [TOKENIZER.encode(stop_) for stop_ in stop]
response_1, _ = MODEL.chat(TOKENIZER, prompt_1, history=None, stop_words_ids=react_stop_words_tokens)
print(response_1)
def parse_latest_plugin_call(text: str) -> Tuple[str, str]:
i = text.rfind('\nAction:')
j = text.rfind('\nAction Input:')
k = text.rfind('\nObservation:')
if 0 <= i < j: # If the text has `Action` and `Action input`,
if k < j: # but does not contain `Observation`,
# then it is likely that `Observation` is ommited by the LLM,
# because the output text may have discarded the stop word.
text = text.rstrip() + '\nObservation:' # Add it back.
k = text.rfind('\nObservation:')
if 0 <= i < j < k:
plugin_name = text[i + len('\nAction:'):j].strip()
plugin_args = text[j + len('\nAction Input:'):k].strip()
return plugin_name, plugin_args
return '', ''
def use_api(tools, response):
use_toolname, action_input = parse_latest_plugin_call(response)
if use_toolname == "":
return "no tool founds"
used_tool_meta = list(filter(lambda x: x["name_for_model"] == use_toolname, tools))
if len(used_tool_meta) == 0:
return "no tool founds"
api_output = used_tool_meta[0]["tool_api"](action_input)
return api_output
api_output = use_api(TOOLS, response_1)
print(api_output)
拼接上述返回答案，形成新的prompt，并获得生成最终结果
prompt_2 = prompt_1 + response_1 + ' ' + api_output
stop = ["Observation:", "Observation:\n"]
react_stop_words_tokens = [TOKENIZER.encode(stop_) for stop_ in stop]
response_2, _ = MODEL.chat(TOKENIZER, prompt_2, history=None, stop_words_ids=react_stop_words_tokens)
print(prompt_2, response_2)
def main(query, choose_tools):
prompt = build_planning_prompt(choose_tools, query) # 组织prompt
print(prompt)
stop = ["Observation:", "Observation:\n"]
react_stop_words_tokens = [TOKENIZER.encode(stop_) for stop_ in stop]
response, _ = MODEL.chat(TOKENIZER, prompt, history=None, stop_words_ids=react_stop_words_tokens)
while "Final Answer:" not in response: # 出现final Answer时结束
api_output = use_api(choose_tools, response) # 抽取入参并执行api
api_output = str(api_output) # 部分api工具返回结果非字符串格式需进行转化后输出
if "no tool founds" == api_output:
break
print("\033[32m" + response + "\033[0m" + "\033[34m" + ' ' + api_output + "\033[0m")
prompt = prompt + response + ' ' + api_output # 合并api输出
response, _ = MODEL.chat(TOKENIZER, prompt, history=None, stop_words_ids=react_stop_words_tokens) # 继续生成
print("\033[32m" + response + "\033[0m")
# 请尽可能控制备选工具数量
query = "加拿大2022年的人口数量有多少？" # 所提问题
choose_tools = TOOLS # 选择备选工具
print("=" * 10)
main(query, choose_tools)
query = "求解方程 2x+5 = -3x + 7" # 所提问题
choose_tools = TOOLS # 选择备选工具
print("=" * 10)
main(query, choose_tools)
query = "编号是1605.08386的论文讲了些什么？" # 所提问题
choose_tools = TOOLS # 选择备选工具
print("=" * 10)
main(query, choose_tools)
query ="使用python对下面的列表进行排序： [2, 4135, 523, 2, 3]"
choose_tools = TOOLS # 选择备选工具
print("=" * 10)
main(query, choose_tools)