Empty Response on http://localhost:5005/webhooks/rest/webhook - Getting Started with Rasa / Tutorials, Resources & Videos - Rasa Community Forum
👋 Introducing the Rasa Playground
Empty Response on http://localhost:5005/webhooks/rest/webhook
2.7k views
2 links
post by DrEvil75 on Mar 15, 2021
Hello Forum,
I’ve built a rasa assistant and I can communicate with the bot via Webchat and some other channels. I’ve activated the rest: channel in the credentials.yml.
When I POST with a REST-Client to the URL “ http://localhost:5005/webhooks/rest/webhook” with payload {“sender”: “test_user”, “message”: “Hi there!”,} I’ve get the Response 200 and an empty body []. Same behavior with curl -POST http://localhost:5005/webhooks/rest/webhook -d '{"message":"hi"}' -v.
The example from https://rasa.com/docs/rasa/connectors/your-own-website doesn’t work.
Any idea?
Best Regards
Mirko
post by Horizon733 on Mar 16, 2021
Because rest is way different than socketio and in socketio it persists session, that’s is not done in rest. So this is why it works well. If you want it to work like webchat you can try out your own connector too.
post by DrEvil75 on Mar 16, 2021
Please forget my question, everything is fine. The problem is in front of the keyboard… In this case the model was not loaded.
post by Horizon733 on Mar 16, 2021
Oh no problem I am glad it is working
post by NIlimaN on Jun 20, 2022
Hi, do you know how I can test my model that I load from s3?
For example: I use this curl command to test my model that I load locally from my drive: curl -X POST http://localhost:5005/model/parse -d '{"text":"Hi I am Nilima"}'
How do I use the curl command to test the model that I loaded from my s3 bucket? I used an example provided by the Rasa docs : curl -X POST http://localhost:5005/webhooks/rest/webhook -d '{"sender":" test_user", "message":" Stop calling me"}'
But since my model only has the nlu part, no core, meaning that I only need the intent classification and entity extraction from my model. This rest channel above sends me an empty message as: [].
Any idea how I can test my model loaded from s3 bucket for entity extraction and intent classification?