# 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](https://forum.rasa.com/u/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](https://forum.rasa.com/u/souvikg10) [@Juste](https://forum.rasa.com/u/juste)  
I am trying to understand how the dialogue management actually works at Rasa core. I am well aware of the [high-level architecture](/content/docs/core/architecture/index.html) but interested to understand how LSTM is used. So I am looking into the [keras_policy.py](https://github.com/RasaHQ/rasa_core/blob/52f80430a3c9bfb92a688348f171ecd543ffd11c/rasa_core/policies/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/](/content/docs/nlu/0.13.8/customcomponents/index.html)  
An interesting blog of someone adding a new model with Rasa is here [https://scalableminds.com/blog/Mac…](https://scalableminds.com/blog/MachineLearning/2018/08/rasa-universal-sentence-encoder/)

## Understanding Rasa NLU  
**Dec 2, 2018**  
I am trying to understand how Rasa NLU actually does intent recognition. In multiple previous conversation with [@Juste](https://forum.rasa.com/u/juste) and [@alexweidauer](https://forum.rasa.com/u/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](https://forum.rasa.com/u/juste) [@amn41](https://forum.rasa.com/u/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](https://forum.rasa.com/u/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](https://forum.rasa.com/u/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](https://forum.rasa.com/u/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/))