CODEWITHSUNDEEP
python-3.xchatbotslack-apingrokrasa
Suraj Ghale
Suraj Ghale

Reputation: 301

Failed to connect to duckling http server. Make sure the duckling server is running and the proper host and port are set in the configuration

I have made workplace on slack and app is registered there from where i get the necessary things like slack token and channel to put it into the credentials.yml file of the rasa. After getting all the credentials i tried to connect between the rasa bot and slack using the command as:

rasa run

and my credentials.yml contains:

slack:

  slack_token: "xoxb-****************************************"
  slack_channel: "#ghale"

Here i have used the ngrok to expose a web server running on your local machine to the internet

but getting the error :

rasa.nlu.extractors.duckling_http_extractor - Failed to connect to duckling http server. Make sure the duckling server is running and the proper host and port are set in the configuration. More information on how to run the server can be found on github: https://github.com/facebook/duckling#quickstart Error: HTTPConnectionPool(host='localhost', port=8000): Max retries exceeded with url: /parse (Caused by NewConnectionError(': Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it',))

Upvotes: 1

Views: 5505

Answers (3)

user8291021
user8291021

Reputation: 346

If you are doing numerical extractions (e.g. six to 6 etc), I presume this will be helpful for form filling on Rasa - you need to install docker and then expose duckling on port 8000

First, install docker (assumes Fedora but you can lookup other distros)

sudo dnf install docker

Second, activate docker

sudo systemctl start docker

Last, activate Rasa's docker

docker run -p 8000:8000 rasa/duckling

Your response should be - Status: "Downloaded newer image for docker.io/rasa/duckling:latest Listening on http://0.0.0.0:8000"

Upvotes: 0

Ankit Bansal
Ankit Bansal

Reputation: 477

Just to add to @Tobias's answer;

If you are running some other service on port 8000, then you can bind any other port with th container's port and specify that in your pipeline config.

Example: docker run -p <Desired Port, ex- 1000>:8000 rasa/duckling

Change config file to reflect that. Your pipeline should include

- name: DucklingHTTPExtractor
# https://rasa.com/docs/rasa/nlu/components/#ducklinghttpextractor
  url: http://localhost:<Desired Port, 1000>

Retrain your model with changed config. After training, simply run: rasa run

Upvotes: 3

Tobias
Tobias

Reputation: 1910

Are you using Duckling? Duckling is a rule-based component to extract entities(docs).

If you are not using it, you can remove it from your NLU pipeline. If you want to use it, the easiest way to do so is using docker:

docker run -p 8000:8000 rasa/duckling

The command above will run duckling and expose it on port 8000 of your host.

Upvotes: 5

Related Questions