Accessing RASA NLU only server from python code using API

Rasa Open Source Feedback on Rasa Open Source
1

I want to use Rasa NLU server only for my custom dialogue management , which is written in a python code. For that i want to post messages to the nlu server and get the intent rankings. I tried -

text=str(input("Enter the message"))
payload = json.dumps({"sender": "Rasa","message": text})
headers = {'content-type': 'application/json'}
response = requests.request("POST",'http://10.101.1.239:5005/model/parse', json=payload, headers=headers)
response = response.json()
print("response :\n",response)

However it throws an error, -

response : {‘version’: ‘2.8.18’, ‘status’: ‘failure’, ‘message’: ‘An unexpected error occurred. Error: string indices must be integers’, ‘reason’: ‘ParsingError’, ‘details’: {}, ‘help’: None, ‘code’: 500}

But if the payload is -

payload = {'text':'hi how are you?'}
headers = {'content-type': 'application/json'}
r = requests.post('http://10.101.1.239:5005/model/parse', json=payload, headers=headers)

then i get the list of intent rankings properly.

The sender id is necessary as I am trying to manage dialogues externally through my code. Please help

2

Hi @sandeeppandey456 ,

The following should work, it looks like the issue was that you used "message" in your payload instead of "text":

text = str(input("Enter the message"))
payload = {"sender": "Rasa","text": text})
headers = {'content-type': 'application/json'}
response = requests.post('http://10.101.1.239:5005/model/parse', json=payload, headers=headers)
response = response.json()
print("response :\n",response)

That being said, I’m not sure the server will send back the sender_id bit. You could try with message_id: Rasa Open Source Documentation

Alternatively, you could load a NLU model directly in your code: see Using nlu model with Interpreter.load in Rasa 3.0 - #8 by isgaal

Hope that helps

1 Like
3

TypeError: means that you are trying to perform an operation on a value whose type is not compatible with that operation. An Iterable is a collection of elements that can be accessed sequentially . In Python, iterable objects are indexed using numbers . When you try to access an iterable object using a string or a float as the index, an error will be returned as TypeError: string indices must be integers. This means that when you’re accessing an iterable object like a string or float value, you must do it using an integer value.

For example, str[hello"] and str[2.1] as indexes. As these are not integers, a TypeError exception is raised. This means that when you’re accessing an iterable object like a string or float value, you must do it using an integer value . If you are accessing items from a dictionary , make sure that you are accessing the dictionary itself and not a key in the dictionary.

Python supports slice notation for any sequential data type like lists, strings , tuples, bytes, bytearrays, and ranges. When working with strings and slice notation, it can happen that a TypeError: string indices must be integers is raised, pointing out that the indices must be integers, even if they obviously are.