• Home
  • About
    • Nithish Raghunandanan photo

      Nithish Raghunandanan

      Working at the intersection of AI, Software & Communities

    • Learn More
    • LinkedIn
    • Twitter
    • Github
    • SlideShare
    • Instagram
    • Youtube
  • Posts
    • All Posts
    • All Tags
  • Projects
  • Talks
  • Blog

Talks

20 Jul 2026

Reading time ~11 minutes

Real-World Applications of Image Generation Models

Date: 30 August 2025

Event: PyCon Poland 2025

Explore AI-generated art with this talk on image generation models like diffusion models and GANs. Watch live demos on virtual cameras, fine-tuning for personalized images, inpainting, and ControlNet. Learn practical applications, Python integration, and ethical considerations in the innovative world of AI-powered creativity.

Slides

Evaluating the Effectiveness of Retrieval Augmented Generation (RAG) in Real-World Applications

Date: 7th March 2025

Event: SCALE 2025

With the rise of large language models (LLMs) enhanced by retrieval augmented generation (RAG), it has become essential to develop rigorous evaluation methodologies to assess their effectiveness across diverse use cases. RAG combines a model’s generative capabilities with information retrieval, allowing for contextually relevant responses grounded in up-to-date, factual knowledge. This talk will focus on the unique challenges and best practices for evaluating RAG applications covering quantitative metrics (e.g., accuracy, relevance, etc).

The audience will gain insights into how to choose the right evaluation framework, balance retrieval precision with generation creativity, and interpret evaluation results to enhance RAG systems’ deployment success in settings like customer support, content generation, research assistance, and more.

Video

Slides

AI Photo Generation with Python: A Developer’s Guide

Date: 25 January 2025

Event: PyConWeb 2025

The line between traditional photography and AI-generated imagery is becoming increasingly blurred, thanks to advancements in AI technologies like generative adversarial networks (GANs) and diffusion models. This talk will focus on building a Python application that uses AI to generate realistic photos. The talk will provide a practical roadmap for turning an idea into a fully functional application. Attendees will gain insights into the challenges of ensuring photo realism, optimizing performance, and handling ethical considerations like authenticity and copyright. The session will also include a demo of a sample AI photo application.

Slides

Next-Gen Apps: Enhancing User Experience with Large Language Models

Date: 18th October 2024

Event: PyCon Portugal 2024

Large Language Models(LLMs) are good at reasoning based on their knowledge. This talk explores how you can use the power of LLMs to add intelligence like coding assistants, text-to-sequel, etc to existing applications.

One of the simplest ways to start adding intelligence is by using an LLM with fine-tuned prompts. You can find the answers to questions like: - What are some of the things that you need to consider while prompt engineering? - What are the limits of prompt engineering?

After finding out the limits of prompt engineering, let us understand how to augment the knowledge of the LLM using vector databases. You can learn things like: - Ingesting the data into the vector databases. - Considerations in data ingestion to improve the LLM performance.

We will also cover the concept of AI agents that given a set of capabilities or tools can figure out how to use them where relevant in an intelligent fashion. You can learn - How do agents work? - Where are they useful?

After this talk, you will learn how to add intelligence to existing applications with the help of the ever-popular LLMs using open-source frameworks.

Video

Slides

Building Custom Chatbots with Custom Data

Date: 29th August 2024

Event: PyCon Poland 2024

In today’s world, users are increasingly using AI tools (ChatGPT, Copilot, etc) to solve their coding problems. These AI tools using Large Language Models (LLMs) are quite good at coming up with answers for well-established technologies. However, when it comes to new or ever-changing technologies, the LLMs tend to hallucinate. In such cases, it would benefit to have a custom AI bot trained on the technology documentation. In this talk, I cover how to build a chatbot that can answer questions using the existing documentation and code snippets using the Retrieval Augmented Generation (RAG) technique.

Coding With AI: Vector Search and RAG

Date: April 2024

Event: Couchbase Webinar

A conversational webcast with Matthew Groves on how developers can use AI to address common challenges in their applications. We covered vector search & vector embeddings and why it helps to integrate them into your database, using LangChain for richer data interactions, Retrieval Augmented Generation (RAG) to minimize LLM hallucinations, and hybrid search combining vectors with SQL & full-text search in a single query.

Watch the webcast

Select ML from Databases

Date: 26th May 2022

Event: PyCon Lithuania 2022

This talk introduces a new workflow for building your machine learning models using the capabilities of modern databases that support machine learning use cases natively. There is an overview of how machine learning models are being created today to how they could look in the near future by utilising the features provided by current databases.

Video

Slides

Select ML from Databases

Date: 4th December 2021

Event: Pyjamas 2021

This talk introduces a new workflow for building your machine learning models using the capabilities of modern databases that support machine learning use cases natively. There is an overview of how machine learning models are being created today to how they could look in the near future by utilising the features provided by current databases.

Video

Slides

Virtual Tourism in COVID Times

Date: 28th July 2021

Event: EuroPython 2021

The introduction to the talk would cover the motivation for the solution. As someone who loves to travel and has been travelling quite extensively in Europe over the past years, the lockdown & travel restrictions preventing travels are quire hard to adjust to. This gave me the idea to build a dashboard around my past travels to improve my spirits.

In the next part, I cover how I get the data. In this case, I use the location history from Google Maps. A brief description of the data is included along with what data I select. I also cover some of the problems faced like the non standardization of the raw data (timestamps, latitude / longitude pairs) & how to resolve it.

In the next part, I explain how I can do some basic analysis with the raw data like the distribution & visualization of my travels over time interactively. This will go through some code examples on how you can build these components using matplotlib & how to make them interactive using Streamlit without writing any Javascript code.

In the next section, I explain how I can augment this data with data from other sources like public images from Flickr to bring out my memories. This would also explain how to integrate these components using Streamlit. This would also cover the deployment aspects of the solution. Also covered here would be some future additions that I am considering.

In the final part, I conclude the presentation with my learnings from building this app to do some virtual tourism in COVID times. I cover some of the scenarios where Streamlit could be useful & other places where it might not be suitable.

Video

Slides

Life of a Data Engineer

Date: 29 March 2021

Event: Alumni Talk at Federal Institute of Science and Technology, Kerala, India

This talk was delivered as part of the Alumni Talk series at FISAT, Kerala, India. The talk covered the different aspects of a career in Data Engineering including Data Analysis, Data Engineering & Data Science.

Slides

Creating Data Apps using Pure Python: Building Custom Apps using Streamlit

Date: 7th February 2021

Event: FOSDEM ‘21

Have you always wanted a flexible & interactive visualization that is easy for others to work with without handling all the Javascript libraries? Or do you want to build a user interface for your Machine Learning Model? This talk has you covered with building data apps in Python using Streamlit with examples of a Travel Visualization App using Google Maps Data & an UI for the ImageNet Model.

In this talk, I showcase couple of different use cases where you can build your data focussed applications using Streamlit, an open source library in pure Python.

In the first use case, I cover how you can build interactive dashboards using different Streamlit components. These dashboards can be easily deployed & the consumers can easily work with the interactive dashboards without worrying about all the dependencies that need to be installed to run the Jupyter notebooks. In the showcase, I will go over how you can build a dashboard of your historical travels using Google Maps Location History including some memories from them from Flickr.

In the second showcase, I will describe how users can create a quick interface for their machine learning model using Streamlit. These interfaces are much faster to develop than building a custom frontend interface for machine learning models with the help of Javascript libraries. In the demo, I showcase how I built an UI for the ImageNet Model.

The showcases will showcase how these data based web apps can be built using Python functions & Streamlit components.

Video FOSDEM Talk

Slides Slides

Impressions

addressing a real pain point: how to put your data app on the web, #Streamlit in #Python, so that others can reuse your work interactively https://t.co/7h8RQH0wPx, https://t.co/Uo3xnswEq7 by @nithishr (thx!) presented @fosdem #FOSDEM2021 to be followed up e.g. with @heroku pic.twitter.com/H96szjrwkG

— Christian Voigt ♡ μ (@chrvoigt) February 7, 2021

Hadn't heard about streamlit before, but your talk sparked the idea to use it for some rapid prototyping in a current project 😉

— 🔴 cyroxx (mütend) (@cyroxx) February 7, 2021

Creating Data Apps Using Python

Date: 6th December 2020

Event: Pyjamas 2020

Have you always wanted a flexible & interactive visualization that is easy for others to work with without handling all the Javascript libraries? Or do you want to build a user interface for your Machine Learning Model? This talk has you covered with building data apps in Python using Streamlit.

Video

Slides

Impressions

Streamlit is quite cool... @nithishr is showing us how to use the python library to show Google data.

So cool!

An awesome talk to end our so awesome conference. pic.twitter.com/R9DswPV1I7

— PyJamas Conf (@PyjamasConf) December 6, 2020

Learnings from Organizing Internal Hackathons

Date: 30th July 2020

Event: DevRelCon Earth 2020

The talk summarizes some of the learnings from organizing internal hackathons including the motivation, processes & the outcomes from it. This was based on the internal hackathon, KI hacks, organized at KI labs. This was delivered virtually during DevRelCon Earth 2020.

Slides

“Where are the keys?” Solving day-to-day Problems using Tech

Date: 25th May 2019

Event: PyConWeb 2019 Munich

Talk at PyConWeb 2019
Talk at PyConWeb

There are many problems that we face in our day to day life. Many of them can be solved rapidly by using a combination of readily available technologies. In this talk, I explain how we solved the shortage of keys in our office using the power of Internet of Things & cloud services.

We faced a shortage of keys for the people in the office. It was really frustrating to open the door multiple times during the day and not to mention the loss of flow while working. We solved this problem by connecting the intercom in the office to the internet using a Raspberry Pi.

In this talk, I explain the challenges we faced & how we overcame them like exposing the service running on Raspberry Pi, security, adding support for multiple clients like Slack, cross-platform mobile apps, Siri commands, etc. The solutions are all simple services which are free or inexpensive to use.

Story Telling using Web Apps

Date: December 4th 2019

Event: Epic Python Gathering, Munich

This talk was delivered as a lightning talk at the Epic Python Gathering in Munich. This talk covers two new open source libraries, Streamlit & Voila, to create interactive web apps out of custom data analysis code snippets/Jupyter notebooks. There were also couple of short demos for the libraries.

Learnings from Organizing an Internal Hackathon

Date: 17th July 2019

Event: DevRel Munich

The talk discusses what goes behind the scenes of an internal hackathon from the motivation, processes & the outcomes from it. This was based on the internal hackathon, KI hacks, organized at KI labs.

Pecha Kucha Talk on Web Scraping

Date: 20th September 2018

Event: Die lange Nacht der (digitalen) Buzzwords #2

In this talk, I explained the concept of web scraping using 20 images for 20 seconds each in Pecha Kucha format. The talk explained the story of how I tried to find my apartment in Munich using web scraping when I initially moved to Munich.

Hodor: Solving Everyday Problems with Tech

Date: 7th June 2018

Event: PyData Munich

In this talk, I give an overview of how we can solve an everyday problem like controlling the office door from Slack. The talk includes a tour of the solution powered by Raspberry Pi coupled with a bunch of free services.

Tutorial: Scraping Data from the Web using Scrapy & Beautiful Soup

Date: November 8th 2017

Event: Pydata Munich

Code

There is a lot of data out there on the internet, but it’s not always in an easy-to-consume format. Luckily, there are a lot of “web scraping” tools out there to help us! These tools take the data and put it into a more structured format, like CSV or Excel. This tutorial showcased how to use Scrapy and BeautifulSoup, two powerful web scraping packages for Python, to grab and collect customer contact information from yellow pages web sites! The session included live coding the scraper for a classifieds website.



talksmeetupconferencepythondata sciencehacks Share Tweet +1