我目前正在为一个项目构建一个聊天机器人,它不断回复相同的内容
主要功能在这里
def AXIS():
knowledge_base:dict = open('knowledge_base.json','r',errors = 'ignore')
while True:
user_input:str = input('You:')
if user_input.lower() in ("q", "quit", "shut down", "shutdown", "cancel", "power off", "poweroff", "power down", "powerdown", "off", "turn off", "turnoff"):
print("AXIS: powering down")
break
best_match: str | None = find_best_match(user_input, list['q("question") for q in knowledge_base.json("questions")'])
if best_match:
answer: str = get_answer_for_question(best_match, knowledge_base)
print(f'AXIS: {answer}')
else:
print('AXIS: I don\'t know the answer. please teach me?')
new_answer: str = input('Type the answer or "skip" to skip: ')
if new_answer.lower() != 'skip':
knowledge_base["questions"].append({"question": user_input, "answer": new_answer})
save_knowledge_base('knowledge_base.json', knowledge_base)
print('AXIS: I have learned a new response!')
if __name__ =='__main__':
AXIS()
我不知道从哪里开始解决这个问题
knowledge_base 目前非常简单,如下所示。
{
"questions": [
]
}
当您教授聊天机器人时,知识库会建立在自身之上
这是其他功能
import json
from difflib import get_close_matches
def save_knowledge_base(file_path: str, data: dict):
with open(file_path,'w')as file:
json.dump(data,file, indent=2)
def find_best_match(user_question: str, questions: list[str]):
matches: list = get_close_matches(user_question, questions, n=1, cutoff=0.6)
return matches[0] if matches else None
def get_answer_for_question(question: str, knowledge_base: dict):
for q in knowledge_base["questions"]:
if q["question"] == question:
return q["answer"]
我正在按照 YouTube 教程来构建它。 https://www.youtube.com/watch?v=CkkjXTER2KE
错误在这里
You:hi
---------------------------------------------------------------------------
TypeError Traceback (most recent call last)
<ipython-input-81-46ef27f29e5d> in <cell line: 21>()
20
21 if __name__ =='__main__':
---> 22 AXIS()
2 frames
/usr/lib/python3.10/difflib.py in get_close_matches(word, possibilities, n, cutoff)
700 s = SequenceMatcher()
701 s.set_seq2(word)
--> 702 for x in possibilities:
703 s.set_seq1(x)
704 if s.real_quick_ratio() >= cutoff and \
TypeError: 'types.GenericAlias' object is not iterable
它向我显示错误位于预安装的 difflib.py 文件的该区域中
if not n > 0:
raise ValueError("n must be > 0: %r" % (n,))
if not 0.0 <= cutoff <= 1.0:
raise ValueError("cutoff must be in [0.0, 1.0]: %r" % (cutoff,))
result = []
s = SequenceMatcher()
s.set_seq2(word)
for x in possibilities:
s.set_seq1(x)
if s.real_quick_ratio() >= cutoff and \
s.quick_ratio() >= cutoff and \
s.ratio() >= cutoff:
result.append((s.ratio(), x))
knowledge_base("questions")
:你正在调用字典;也许您想要方括号:knowledge_base["questions"]
?
尽管这个错误不应该导致您收到错误消息。但是你告诉人们
knowledge_base
是第 26 行中的一个字典。那么也许它是一个派生类型?什么是type(knowledge_base)
?
我注意到以下几点:
def load_knowledge_base(file_path: str):
return dict
...
您正在返回一个类型! 我怀疑这是否是故意的。也许只是简单地删除该行?
它明确解释了错误消息。如果您返回实际实例化的字典,而不是类型,您将遇到我在顶部提到的错误。所以你至少有两件事需要解决。