python - 使用 RASA 的 API 的正确方法是什么(rasa.core.processor - 遇到异常)?

标签 python nlp python-requests rasa-core rasa

我安装了 rasa-demo 代码示例。为了打开 rasa API,我做了:

user@User:~/rasa-demo ‹master*›$ rasa run
No chat connector configured, falling back to the REST input channel. To connect your bot to another channel, read the docs here: https://rasa.com/docs/rasa/user-guide/messaging-and-voice-channels
2020-06-19 13:20:02 INFO     root  - Starting Rasa server on http://localhost:5005
2020-06-19 13:20:08 INFO     absl  - Using /var/folders/h5/9rj1zn8x4s59bk_mg_ktzv740000gn/T/tfhub_modules to cache modules.
2020-06-19 13:20:08 INFO     absl  - Downloading TF-Hub Module 'http://models.poly-ai.com/convert/v1/model.tar.gz'.
2020-06-19 13:20:26 INFO     absl  - Downloading http://models.poly-ai.com/convert/v1/model.tar.gz: 22.35MB
2020-06-19 13:20:43 INFO     absl  - Downloading http://models.poly-ai.com/convert/v1/model.tar.gz: 42.35MB
2020-06-19 13:21:02 INFO     absl  - Downloading http://models.poly-ai.com/convert/v1/model.tar.gz: 82.35MB
2020-06-19 13:21:21 INFO     absl  - Downloading http://models.poly-ai.com/convert/v1/model.tar.gz: 118.59MB
2020-06-19 13:21:40 INFO     absl  - Downloading http://models.poly-ai.com/convert/v1/model.tar.gz: 148.59MB
2020-06-19 13:21:41 INFO     absl  - Downloaded http://models.poly-ai.com/convert/v1/model.tar.gz, Total size: 152.02MB
2020-06-19 13:21:41 INFO     absl  - Downloaded TF-Hub Module 'http://models.poly-ai.com/convert/v1/model.tar.gz'.
2020-06-19 13:22:14 INFO     root  - Rasa server is up and running.

如何通过 API 查询聊天机器人?我希望能够发出请求并通过请求进行对话,而不是使用 shell。到目前为止,当我尝试对 rasa 服务器进行 curl 时:

在:

user@User:~ $ curl -XPOST localhost:5005/webhooks/rest/webhook -d '{"message":"hi"}'

输出:

[]%

在 rasa 运行服务器上,我得到这样的响应:

2020-06-19 13:23:17 ERROR    rasa.core.actions.action  - Failed to run custom action 'action_greet_user'. Couldn't connect to the server at 'http://localhost:5055/webhook'. Is the server running? Error: Cannot connect to host localhost:5055 ssl:default [Connection refused]
2020-06-19 13:23:17 ERROR    rasa.core.processor  - Encountered an exception while running action 'action_greet_user'. Bot will continue, but the actions events are lost. Please check the logs of your action server for more information.
2020-06-19 13:24:04 ERROR    rasa.core.actions.action  - Failed to run custom action 'action_greet_user'. Couldn't connect to the server at 'http://localhost:5055/webhook'. Is the server running? Error: Cannot connect to host localhost:5055 ssl:default [Connection refused]
2020-06-19 13:24:04 ERROR    rasa.core.processor  - Encountered an exception while running action 'action_greet_user'. Bot will continue, but the actions events are lost. Please check the logs of your action server for more information.

它不起作用。 作为 API 请求 Rasa 服务器的正确方法是什么?阅读 docs 后,我不清楚如何正确使用 API。

我也试过这个:

在:

import requests

response = requests.get('http://localhost:5005/webhooks/rest/webhook') 
print(response) 
print(response.headers) 
print(response.content)

输出:

<Response [405]>
{'Connection': 'keep-alive', 'Keep-Alive': '5', 'Allow': 'POST', 'Access-Control-Allow-Credentials': 'true', 'Content-Length': '60', 'Content-Type': 'text/plain; charset=utf-8'}
b'Error: Method GET not allowed for URL /webhooks/rest/webhook'

最佳答案

我最终发现这就是您请求终点的方式:

localhost:5005/model/parse -s -d '{ "text": "hi" }'

文档应该更清晰。

关于python - 使用 RASA 的 API 的正确方法是什么(rasa.core.processor - 遇到异常)?,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/62400205/

相关文章:

python - 印地语到英语音译

python - 从多个页面抓取表格并从链接添加数据

python - 如何使用 python 请求进行多个 api 调用

Python-获取嵌套字典中的键列表

python - 为什么 pygame.MOUSEBUTTONDOWN 永远不等于我的按钮,即使用户单击它?

python - Python 请求模块的下载速度低得离谱

python - 在 Spacy 中从 Glove 加载矢量时出错

python - 绘制 Keras 单个时期内的损失演变

python - 为Textacy中的单个单词计算TF-IDF

python - 是否可以在请求中刷新 session ?