What we’re about
Bluetalks são encontros vibrantes com discussões aprofundadas sobre tecnologia e inovação, apresentando os projetos de pesquisa mais recentes da IBM Research Brasil. Expanda seus horizontes com ideias disruptivas e novas perspectivas sobre tópicos de ponta. Junte-se a nós para explorar ainda mais nossos projetos inovadores.
Ah, os eventos são gratuitos e possuem certificados! Esperamos por vocês! :)
Upcoming events (3)
See all- Network event192 attendees from 110 groups hosting[AI Alliance] Chat with your website using an LLMLink visible for attendees
Abstract
Imagine being able to ask questions about a website in natural language—and receiving meaningful answers instead of simple keyword matches. In this talk, I’ll introduce Allycat, an open-source, end-to-end stack that enables conversational interaction with website content using Large Language Models (LLMs).We’ll walk through the complete pipeline:
- Crawling and indexing website content
- Cleaning and extracting meaningful information from HTML
- Creating embeddings and storing them in a vector database
- Querying the data using an LLM for contextual, accurate responses
We’ll also demonstrate Allycat’s lightweight UI that allows users to interactively test their queries. The entire stack is built with Python and open-source components, making it easy to adopt, adapt, and extend.
You can checkout Allycat here : https://github.com/The-AI-Alliance/allycat
Audience
AI/ML Engineers, Data Engineers, Data Scientists interested in building intelligent, LLM-powered search and chatbot interfaces.Level
Beginner to IntermediateFormat
45-minute presentation with demonstrationAbout the speaker
Sujee Maniyam (AI Engineer, Developer Advocate @ Node51) is an expert in Generative AI, Machine Learning, Deep Learning, Big Data, Distributed Systems, and Cloud technologies. He is passionate about developer education, fostering community engagement. Sujee has led numerous training sessions, hackathons, and workshops. He is also an author, open source contributor and frequent speaker at conferences and meetups.About the AI Alliance
The AI Alliance is an international community of researchers, developers and organizational leaders committed to support and enhance open innovation across the AI technology landscape to accelerate progress, improve safety, security and trust in AI, and maximize benefits to people and society everywhere. Members of the AI Alliance believe that open innovation is essential to develop and achieve safe and responsible AI that benefit society rather than benefit a select few big players. - Network event176 attendees from 111 groups hosting[AI Alliance] GneissWeb: Preparing High Quality Data for LLMs at ScaleLink visible for attendees
Details
IBM recently released GneissWeb, a large dataset yielding around 10 trillion tokens that caters to the data quality and quantity requirements of training Large Language Models. In this talk i will do a deep dive on the philosophy behind this dataset, where it stands w.r.t the other datasets out there, how to recreate it based on the tools IBM has open sourced and some performance figures with it. This talk will be a followup of the talk given by Shahrokh Daijavad of IBM in the month of March.Prerequisites
This is a follow up to our March 6, 2025 session “Introducing GneissWeb - a state-of-the-art LLM pre-training dataset“:- Check the GitHub show notes
- Re-watch on YouTube
About the presenter
Bishwaranjan Bhattacharjee (LinkedIn), Senior Technical Staff Member and Master Inventor, IBM ResearchAbout the AI Alliance
The AI Alliance is an international community of researchers, developers and organizational leaders committed to support and enhance open innovation across the AI technology landscape to accelerate progress, improve safety, security and trust in AI, and maximize benefits to people and society everywhere. Members of the AI Alliance believe that open innovation is essential to develop and achieve safe and responsible AI that benefit society rather than benefit a select few big players.
![[AI Alliance] Chat with your website using an LLM cover photo](https://secure.meetupstatic.com/photos/event/a/0/5/7/event_527561047.webp "[AI Alliance] Chat with your website using an LLM")
![[AI Alliance] GneissWeb: Preparing High Quality Data for LLMs at Scale cover photo](https://secure.meetupstatic.com/photos/event/1/6/7/8/event_527645752.webp "[AI Alliance] GneissWeb: Preparing High Quality Data for LLMs at Scale")
Past events (193)
See all- Network event251 attendees from 109 groups hosting[AI Alliance] Introducing gofannonThis event has passed
