如何在水蟒提示中使用rasa聊天机器人？

Question

我正在使用rasa构建聊天机器人；我可以在Ubuntubash中与它交互，但我无法在anaconda prompt中与它交互：我确实设法使用bot.py run加载bot，但是当我键入第一条消息时，我收到以下错误消息：

Bot loaded. Type a message and press enter:
'Hello'
XXX lineno: 105, opcode: 0
Traceback (most recent call last):
  File "bot.py", line 90, in <module>
    run()
  File "bot.py", line 68, in run
    agent.handle_channel(ConsoleInputChannel())
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_core\agent.py", line 123, in handle_channel
    processor.handle_channel(input_channel)
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_core\processor.py", line 60, in handle_channel
    input_channel.start_sync_listening(self.handle_message)
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_core\channels\console.py", line 52, in start_sync_listening
    self._record_messages(message_handler)
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_core\channels\console.py", line 45, in _record_messages
    self.sender_id))
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_core\processor.py", line 81, in handle_message
    self._handle_message_with_tracker(message, tracker)
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_core\processor.py", line 221, in _handle_message_with_tracker
    parse_data = self._parse_message(message)
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_core\processor.py", line 210, in _parse_message
    parse_data = self.interpreter.parse(message.text)
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_core\interpreter.py", line 236, in parse
    return self.interpreter.parse(text)
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_nlu\model.py", line 344, in parse
    component.process(message, **self.context)
  File "C:\Users\Vincent\Documents\Chatbot_Eleven_Candidats\Versions\rasa_test4\rasa_nlu\featurizers\count_vectors_featurizer.py", line 149, in process
    bag = self.vect.transform([self._lemmatize(message)]).toarray()
  File "C:\Users\Vincent\Anaconda3\lib\site-packages\sklearn\feature_extraction\text.py", line 923, in transform
    _, X = self._count_vocab(raw_documents, fixed_vocab=True)
  File "C:\Users\Vincent\Anaconda3\lib\site-packages\sklearn\feature_extraction\text.py", line 792, in _count_vocab
    for feature in analyze(doc):
  File "C:\Users\Vincent\Anaconda3\lib\site-packages\sklearn\feature_extraction\text.py", line 266, in <lambda>
    tokenize(preprocess(self.decode(doc))), stop_words)
  File "/usr/local/lib/python3.5/dist-packages/rasa_nlu/featurizers/count_vectors_featurizer.py", line 105, in <lambda>
SystemError: unknown opcode

Answer 1

ConsoleInputChannel（）从Rasa V 0.12开始删除。在

您仍然可以使用命令提示符进行测试，使用

Python-m rasa_核心.运行-d路径到对话-u路径到nlu模型