All - Activity - nahidalam - Rasa Community Forum

Nahid Alam

The Universe
Building #Enterprise#AI@Cisco. #NLP lover. Mentor @backstage_cap, Founded @litehouseio for #VoiceFirst interaction, @intel alumni, spoke @TEDx

Announcing the Conversational AI with Rasa series

Jul 30, 2021
Great timing @Juste. Do you have a link specific to the series in youtube?

Revisiting Rasa after 2 years

Mar 7, 2021
Planning to use Rasa for a project after 2 years again! A lot has changed since my last use of Rasa. It seems that even pip install rasa_nlu does not work! Is there a starter project that I can use as a template now?

What our $26m Series B funding means for our community

Jun 23, 2020
Wow congrats Rasa team. Time for a tech team at SF!

Understanding the usage of LSTM in keras_policy

Jan 12, 2019
Need help from experts here @souvikg10 @Juste
I am trying to understand how the dialogue management actually works at Rasa core. I am well aware of the high-level architecture but interested to understand how LSTM is used. So I am looking into the keras_policy.py file. I am a bit confused about so…

Rasa NLU custom pipeline

Jan 12, 2019
Not that I know off…

Rasa NLU custom pipeline

Jan 11, 2019
This is an interesting idea. You have to create the BERT model (or use anything existing) and make it part of the pipeline.
Does this link help? https://rasa.com/docs/nlu/0.13.8/customcomponents/
An interesting blog of someone adding a new model with Rasa is here https://scalableminds.com/blog/Mac…

Understanding Rasa NLU

Dec 2, 2018
I am trying to understand how Rasa NLU actually does intent recognition. In multiple previous conversation with @Juste and @alexweidauer, they mentioned that they use BoW approach for intent recognition. I looked into the codebase [https://github.com/RasaHQ/rasa_nlu/tree/master/rasa_nlu/classifiers] but looks like they do classification using SVM model and don’t see…

New Evaluate and Interactive features

Oct 23, 2018
nevermind, I see that it is part of master as mentioned in the documentation.

New Evaluate and Interactive features

Oct 23, 2018
As discussed in the Rasa summit, I am interested in testing rasa_core.evaluate and the new interactive features. I am guessing the master branch of the Core doesn’t have it yet. Which branch should I get for the Core. Is there any specific version of NLU that it should go with?

A Chatbot from Future: Building an end-to-end Conversational Assistant with Rasa

Oct 2, 2018
I just wrote a blog post on how to use Rasa to build a bot and use the Rasa models as a service and call them from a NodeJS app. Would love your feedback.

Rasa documentation

Sep 20, 2018
Any takers? @Juste @amn41

Rasa documentation

Sep 18, 2018
I am looking into Rasa NLU and Core documentation for better explanation of some of the common classes used throughout the tutorials - Trainer, Agent, Interpreter etc.
Especially looking for what different methods return, what some of the parameter means etc.

Intent is null while calling the Rasa NLU Server

Aug 21, 2018
Getting error
"error": "Unable to initialize persistor"

Intent is null while calling the Rasa NLU Server

Aug 21, 2018
@souvikg10 ok so how do I solve this? I tried below but no luck

$python -m rasa_nlu.server --path /PATH/renewalBot/models/nlu/default/renewalnlu/  
curl --request POST --url http://localhost:5000/parse --header 'content-type: application/json' --data '{"q": "hello", "project": "default","model":"/PATH..."}'  

Intent is null while calling the Rasa NLU Server

Aug 20, 2018
@souvikg10 here is the code

def train_nlu(data, configuration, model_dir, model_name):  
    training_data = load_data(data)  
    trainer = Trainer(config.load(configuration))  
    trainer.train(training_data)  
    model_directory = trainer.persist(model_dir, fixed_model_name = model_name)  
    return model_directory  

Understanding train_online.py

Aug 2, 2018
nevermind, found the issue. In the updated agent object, I didn’t include NLUInterpreter object.

Understanding train_online.py

Aug 2, 2018
@amn41 any thoughts on how to resolve it? It is impossible to debug without train_online working and I have other issues.
I am using Rasa NLU 0.12.3 and Rasa Core version 0.9.8.

def run_renewal_online(input_channel, interpreter,  
         domain_file="renewa...":  
    ```

## Introduce yourself!  
**Aug 1, 2018**  
Hi this is Nahid. I am a Software Engineer leading the creation of a customer service chatbot at Cisco. My mission - automate the heck out of everything! I am intrigued by the challenges of conversational AI/NLP. Feel free to connect to me at LinkedIn ( [https://www.linkedin.com/in/nahidalam/](https://www.linkedin.com/in/nahidalam/))