如何使用对话流 python api 在 shell（最好是 repl.it）中制作文本机器人？

Question

I am trying to make a simple chatbot in my repl.it shell, but it errors, saying that it "Could not automatically determine credentials.", I have looked over it many times, and can't figure out how to do it. In addition, I might have other things wrong but I can't tell since I can't get past this error. If anyone can help me with this, or if you have an example that I can follow, that would be great https://repl.it/@RyandaKing/ThoughtfulWorrisomeQuadrant

import dialogflow
from google.api_core.exceptions import InvalidArgument

DIALOGFLOW_PROJECT_ID = 'newagent-1-rhjebl'
DIALOGFLOW_LANGUAGE_CODE = 'en-US'
GOOGLE_APPLICATION_CREDENTIALS = 'newagent-1-rhjebl-29ae80f7e64d.json'
SESSION_ID = '110497386060607202274'
text_to_be_analyzed = "Hello"
session_client = dialogflow.SessionsClient()
session = session_client.session_path(DIALOGFLOW_PROJECT_ID, SESSION_ID)
text_input = dialogflow.types.TextInput(text=text_to_be_analyzed, language_code=DIALOGFLOW_LANGUAGE_CODE)
query_input = dialogflow.types.QueryInput(text=text_input)
try:
    response = session_client.detect_intent(session=session, query_input=query_input)
except InvalidArgument:
    raise
print("Query text:", response.query_result.query_text)
print("Detected intent:", response.query_result.intent.display_name)
print("Detected intent confidence:", response.query_result.intent_detection_confidence)
print("Fulfillment text:", response.query_result.fulfillment_text)

Answer 1

The reason is that you improperly use the private key contained by .json . As described here you should define the environment variable having the value of .json key file path.

Assuming that the .py and .json files are in the same directory run it like this.

$ cd path/to/app
$ env 'GOOGLE_APPLICATION_CREDENTIALS=newagent-1-rhjebl-29ae80f7e64d.json' python3 app.py