Valentina Alto
AI and Intelligent Apps Technical Architect
Dubai, United Arab Emirates
Actions
I'm a Technical Architect specialized in AI and Intelligent Apps working in Microsoft and currently based in Dubai, UAE. Over the past years I gained tech sales experience focusing on data and AI workloads within the manufacturing and pharmaceutical industry in Microsoft Italy. I've been working on customers' digital transformations, designing cloud architecture and modern data platforms, including IoT, real-time analytics, Machine Learning, AI Services, and Generative AI. I'm also a tech author, contributing articles on machine learning, AI, and statistics, and I recently published two books on Generative AI and Large Language Models.
Area of Expertise
Topics
Introducing GraphRAG: from retrieval augmented generation to graph-based knowledge embeddings
In the realm of LLM-powered applications, Retrieval Augmented Generation (RAG) consolidated as established itself as a leading framework. It is based on the idea of retrieving relevant context from custom knowledge base via embeddings, that are vector representation of texts.
Over the last months, we witnessed the rise of numerous variants of traditional RAG, and one of the most prominent is GraphRAG, based on graph-like organization of the knowledge base.
In this session, we explore the idea behind GraphRAG with a hands-on implementation with LangChain.
Design and build powerful LLM Agents
When it comes to GenerativeAI-powered applications, one of the most trending framework is that of Agent, which can be defined as highly-specialized entities that can achieve user's goal by panning and interacting with the surrounding ecosystem.
In this session, we are going to explore the main components that features AI Agents, such as LLMs, Prompts, Memory and Tools. We will also see architectural best practices to build robust and enterprise-scale agents, focusing on emerging trends like semantic caching and GraphRag.
Build LLM-powered Application with LangChain
In this session, we will cover the main components of LangChain, a popular AI orchestrator which make it easier to embed LLMs into your applications. We will focus on components like memory, prompt engineering, plug-ins and chains.
We will then see an hands-on implementation leveraging OpenAI's models.
Building LangChain Agents with Azure OpenAI models and Cognitive Services
Large Language Models have proved to be extremely powerful, but what if you want to integrate them into your applications and let them interact with external tools?
LangChain is a lightweight python-based framework meant to orchestrate LLMs within applications to build intelligent agents and copilots.
In this session, we will see how to build an Agent powered by Azure OpenAI models and enriched by Azure Cognitive Services, all orchestrated by LangChain.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top