Bots in production

Hey! Now I’m working with implementing dragonfly technology to my bot. I have a telegram channel that covers space topics and this one will be implemented to the bot so the users can see places as photos after typing commands. I wonder is there any good advice or tips for implementing such a thing? Now I am halfway through but maybe someone did something like that before and I would not mind hearing about your experience. Thanks.

Link to our bot in production - IDP | Home Page

Background

The “India Data Portal” is a one-stop open-access portal for journalists to access, interact with, and visualize information, data, and knowledge related to agriculture and financial inclusion, while also aiding other beneficiaries – researchers, students, policymakers, administrators, NGOs, and entrepreneurs. The portal contains a data repository with processed and documented public datasets on related themes.

The Challenge

To resolve queries related to specific datasets, helping users to create different visualizations in a guided manner, in addition to not only solving generic queries about the portal and its usage but also to provide functionality in order to get a user’s feedback through a specifically designed form. Furthermore, this support needs to be multilingual.

The Solution

Our chatbot provides a Multilingual solution to the IDP team which can handle the user queries(generic and specific) and guide them on how to utilize the portal for their specific tasks. This helped the journalists to understand and make different visualizations by using different datasets from the portal, providing information regarding the fellowship program and various ongoing masterclasses and training sessions. Furthermore, users can also provide feedback by utilizing the functionality of a form.

2 Likes

Awesome! Is it currently running in production? I would love to try it out if there is a chance!

@Juste i am just trying move the developed bot to production can you let me know the practical server,hardware,os,memory requirements for 10000 users concurrency at once.

has anybody integrated with a voice service? I am wondering what issues you had from a Customer Experience lens (eg: bot interrupting) and how they were overcome :pray:

Hello, I have been involved in the development of conversational agents for a long time both at the university and now in my company. Namely, I started making conversational agents with version 2.0, at that time I wasn’t monitoring my memory that much. Now that I’m working for myself and we’re making a product for one company that includes speech technologies related to a robot and we have 50 conversational agents built for them, I’m interested in how, if there is any possibility, we can reduce the consumption of models. I am using the default pipeline and rasa version 3.3. I wonder if by changing the batch size I can change this. Currently, each model consumes between 800MB-1GB RAM depending on the size of the model. I also have a question, because it seems from my testing that the learning of the rasa models takes place on the cores, and I’m wondering if I can use some command to limit this or choose how many cores I want the rasa to occupy during training or startup. If, of course, anyone knows the answers to these questions, I would be very happy and maybe clarify some things for me.

Kind regards, Daniel