时间戳

首页 > 解决方案 > Dialogflow 上下文/会话：获得后续响应？

python - Dialogflow 上下文/会话：获得后续响应？

问题描述

我有一个基于网络实现的对话流代理，我正在使用 Dialogflow v2 API 进行查询。但是，目前每个查询的响应都是独立的。我如何收到后续回复（以及适当的流畅对话）？

示例（我想要的）： 我：“你好，清理我的包” 机器人：“你确定要清理你的包吗” 我：“是” 机器人：“清理了包”

实际： 我：“你好，清理我的包” 机器人：“你确定要清理你的包” 我：“是” 机器人：“抱歉，不确定你的意思”

Sample code:

"""DialogFlow API Detect Intent Python sample with text inputs.
Examples:
  python detect_intent_texts.py -h
  python detect_intent_texts.py --project-id PROJECT_ID \
  --session-id SESSION_ID \
  "hello" "book a meeting room" "Mountain View"
  python detect_intent_texts.py --project-id PROJECT_ID \
  --session-id SESSION_ID \
  "tomorrow" "10 AM" "2 hours" "10 people" "A" "yes"
"""

import argparse
import uuid
import json


# [START dialogflow_detect_intent_text]
def detect_intent_texts(project_id, session_id, texts, language_code):
    """Returns the result of detect intent with texts as inputs.
    Using the same `session_id` between requests allows continuation
    of the conversaion."""
    import dialogflow_v2 as dialogflow
    session_client = dialogflow.SessionsClient()

    session = session_client.session_path(project_id, session_id)
    print('Session path: {}\n'.format(session))

    for text in texts:
        text_input = dialogflow.types.TextInput(text=text, language_code=language_code)

        query_input = dialogflow.types.QueryInput(text=text_input)

        response = session_client.detect_intent(session=session, query_input=query_input)

        print('=' * 20)
        print('Query text: {}'.format(response.query_result.query_text))
        print('Detected intent: {} (confidence: {})\n'.format(response.query_result.intent.display_name,response.query_result.intent_detection_confidence))



        print('Fulfillment text: {}\n'.format(response))
        #test = str(response)
        #test = str(response.query_result.webhook_payload)
        #print(test)

# [END dialogflow_detect_intent_text]


if __name__ == '__main__':
    parser = argparse.ArgumentParser(
        description=__doc__,
        formatter_class=argparse.RawDescriptionHelpFormatter)
    parser.add_argument(
        '--project-id',
        help='Project/agent id.  Required.',
        required=True)
    parser.add_argument(
        '--session-id',
        help='Identifier of the DetectIntent session. '
        'Defaults to a random UUID.',
        default=str(uuid.uuid4()))
    parser.add_argument(
        '--language-code',
        help='Language code of the query. Defaults to "en-US".',
        default='en-US')
    parser.add_argument(
        'texts',
        nargs='+',
        type=str,
        help='Text inputs.')

    args = parser.parse_args()  
    detect_intent_texts(
        args.project_id, args.session_id, args.texts, args.language_code)'

标签： pythonapidialogflow-es

解决方案

您需要为是/否设置嵌套意图，然后在您采取相应措施之后。

推荐阅读