All - Activity - asokolow - Rasa Community Forum

How to call Rasa 1.0 via RESTful API?

Be careful it will call the NLU only and the NLU is working with the format ‘{"text":"hello"}’ if you want the complete pipeline (nlu + core), you will have to use the rest/webhook path mentioned by @JiteshGaikwad.

Slots are not set using rasa X

Hey, while doing interactive learning with my bot, I noticed that the slots are not properly updated under rasa x. My action endpoint is properly set and it works well using interactive from rasa 1.0. How can I solve this?

How to call Rasa 1.0 via RESTful API?

Hi jhsu, You could solve your problem by using the argument --credentials and joining a credential file as the following:

# This file contains the credentials for the voice & chat platforms
# which your bot is using.
# https://rasa.com/docs/rasa/user-guide/messaging-and-voice-channels/
rest:
# …

Rasa 1.0 minor issue with --cors *

Hello, I’m simply reporting a small issue when adding " --cors * " to the command line:

PYTHONPATH=…/…/…/ python …/…/…/rasa/main.py run -m models --enable-api --log-file out.log --endpoints endpoints.yml --credentials credentials.yml --cors *

I’ve got the following error:

Traceback (most recent...)

Transition from v0.x.x to v1.0 confusing

Hey there! First of all, great job for Rasa X it is a very nice feature! I’ve been working with Rasa NLU/Core v0.x.x for over a year now not as a pip module but directly using the source code because I need to slightly change it for my applications (GPU, custom message broker, etc.).

Rasa_nlu interpreter - how to load latest model?

Hi, If you target the parent directory of your models, normally it should load the latest version. Could you try this solution?

Why my interactive concert bot training only stop when the next action is ActionListen?

For rasa-core, I run python3.6. I’m usually working with PyCharm but for interactive learning, I work in the terminal.

Why my interactive concert bot training only stop when the next action is ActionListen?

Yes, you are right! Is it happening all the time?

Intent is not being identified

Hi Leonardo, you could probably improve your intent featurizer by using regex features! You should have a look at rasa-nlu.

How to use tracker in a custom class and call custom function in an action class?

Hi there, Does not mean that Action is the parameter of ActionCalculation! It means that ActionCalculation inherits from Action class. The entry point of your ActionCalculation is run(), inside this function you can call your custom function sum().

Why my interactive concert bot training only stop when the next action is ActionListen?

What do you mean by “stop”? Ending the dialog flow? From my perspective, it seems logical that the bot triggers action_listen after an utter_greet. What does it mean:

You said something like “Hello” (action_listen)

The bot replies with its own greeting (utter_greet)

The bot is then waiting...

Text-to-Speech

If your targeted application is web-based, I suggest to have a look at TensorflowJS instead of Keras! Tensorflow is a bit more complex than Keras but it is worth every penny (a.k.a time)!

Text-to-Speech

For the ASR (speech-to-text): Last summer, my job was to build an embedded speech recognizer that could run on a Jetson TX2 with realtime capability. My work was inspired by a mix of DeepSpeech (Mozilla) and Wave2letter (Facebook) architecture. If you are new to the subject, I suggest to u...

Text-to-Speech

Sure, I’m currently back engineering the source code! I’ll let you know.

Text-to-Speech

Hey! I do not manage to find any relevant information about this subject, what is the best practice to include a text-to-speech engine inside rasa core? I got my own TTS engine, I just want to switch between textual feedback to a synthesized one.

Should I implement this feature inside my action...

Details about conversational-ai-workshop-18

Thank you for the answer … What would be the impact on the training/accuracy if the slots were set to “text”?

Details about conversational-ai-workshop-18

Hey, What is the reason to set the slots as unfeaturized? ( conversational-ai-workshop-18/domain.yml at master · RasaHQ/conversational-ai-workshop-18 · GitHub). If set in such a way, how the embedded policy knows what has already been set so far (unfeaturized -> no memory)? Thx

Does the value of an entity influence the action policy?

I agree with you but … I’ve already a severity slot which is set when a user “says”: inform{"severity":"mild"} … In this case, I want to register the information. I had to set autofill to None and raised an event when the intent “inform” is detected … I guess I will have to do the magic trick inside ...

Does the value of an entity influence the action policy?

Hey there! I know that the action policy could be influenced by the intents, entities, and the slots values. But in the case of the entity, does its value influence the decision or does it simply check if the value exists or not? Here is an example:

Let’s say my user could ask for an explanation about 3...

Embedding Policy Results

Hi! Great feature! 🙂 Did you benchmark the training time? I’m currently training a model by using this policy on a GTX 1080ti (12go) + 32Go ram + 32 core CPU and each epoch takes about ~10 min … I’m using:

policies:
- name: EmbeddingPolicy
  epochs: 2000
  attn_shift_range: 5

Auto slot filling depending on the intent

Hey there, It has been a while! Let’s say I’ve two intents “inform” and “explain” and one slot “severity”. In my use case, both mentioned intents could carry the entity “severity”:

intents:

entities:

slots: severity: type: unfeaturized

Is it possible in the domain?...

Rasa NLU 0.13.0 is released!

Hey, are the changes available on the github?

Slot filling "asynchronously"

Thank you, I will have a look now! 🙂 it seems to be a good approach.

Slot filling "asynchronously"

I agree with you, I thought about this too! Thank you, we are on the same track.

Slot filling "asynchronously"

Hey there, Hey I’ve a question about slot filling… Let’s say my bot is simply triggered by intents from a user without any entities. All the relevant information for the slots would come from a third-party software that will periodically (e.g. 30sec) send information. Is there a way to update the slots?

Introduce yourself!

Hey there, I’m Alex, I’m working as a R&D engineer in a research center in Belgium (Multitel). I’ve been working for 7 years as a speech processing engineer (recognition and enhancement). I also worked in other fields like biomedical signal processing and image processing. I discovered RASA 6 months ago...