更新时间:2023-12-02 21:51:58
Rasa具有功能强大的API,如此处.
Rasa has a highly functional API as documented here.
要回答特定问题,您可以通过以下命令将训练数据传递给Rasa NLU API:
To answer the specific question you can pass training data to the Rasa NLU API via the below commands:
如果您的训练数据在文件中:
If your training data is in a file:
curl -XPOST localhost:5000/train?project=my_project -d @data/examples/rasa/demo-rasa.json
如果您的训练数据为json格式:
If your training data is in json format:
curl --request POST \
--url 'http://localhost:5000/train?project=test&fixed_model_name=tested-project' \
--header 'content-type: application/json' \
--data ' {
"rasa_nlu_data": {
"regex_features": [
{
"name": "zipcode",
"pattern": "[0-9]{5}"
}
],
"entity_synonyms": [
{
"value": "chinese",
"synonyms": ["Chinese", "Chines", "chines"]
},
{
"value": "vegetarian",
"synonyms": ["veggie", "vegg"]
}
],
"common_examples": []
}
}'
显然,您需要创建json文件或有效负载.并且在Node中您不会使用curl,而是使用 request 之类的库.
Obviously you'll need to create the json file or payload. and in Node you wouldn't be using curl, but a library like request.
我写了系列教程可能有助于您开始与Rasa的API进行交互.
I've written a series of tutorials that may be good to help you get started interacting with Rasa's API.