

Corrado De Bari
Developer Evangelist, Microservices & AI, Oracle Database
Fiumicino, Italy
Actions
Developer Evangelist in MAA Platform Engineering team at Oracle, with more than 25 years of experience in Information Technology, he is currently focused on AI Microservices platform development with the Oracle Database. In Oracle Italy since 2010, he joined Technology Sales Consulting team, working on Italian large and medium accounts on OCI, AI/ML, DataLakes and BPM/SOA platforms. Formerly Sales Engineer at Sun Microsystems, as well as Java & Software Ambassador for Italy, starting his career as architect in Telecom Italia Mobile. He holds the CEFRIEL Master in Information Technology and a bachelor's degree in Computer Science.
Links
Area of Expertise
Topics
Unlock the Power of Vector Embeddings: from Vector Store to Chatbots
The rise of generative AI has increased the demand for more context-aware applications, particularly in Retrieval-Augmented Generation (RAG) for chatbot development. Vector embeddings are essential for enabling efficient search and retrieval of unstructured data. We’ll explore how a vector store can boost RAG and how developers can harness them using SQL, Python, and Java through frameworks like LangChain or Spring AI. We’ll highlight the importance of vector embeddings in improving chatbot responses and optimizing knowledge retrieval, with practical code examples and a low-code platform.
Accepted @ HrOUG 2025 and AI Coding Summit
Java for Generative AI: Why not?
Generative AI and its applications are no longer just a prerogative of data scientists using Python but, with Java and Spring Boot skills, it could be approached through the new "Spring AI" framework.
We will see step-by-step how we can implement a Spring Boot application based on Retrieval Augmented Generation (RAG) using a knowledge base stored in a VectorDB and MCP Agents for structured data, leveraging public, hybrid or on-premises LLMs, showing tips&tricks in ingestion, choosing the LLMs models and prompt engineering. An assisted approach, where most of the moving parts will be tested before being implemented will be also shown, to quickly generate code reflecting the tested configurations and use it as a baseline for an AI Microservice. The transition phase to production, through a Backend platform, will not be overlooked.
Accepted @ JavaCro'25
From Prototype to Production: Mastering Enterprise Chatbots with an Open Source Tool
With the explosion of interest in Generative Ai, organizations everywhere are embarking on projects to create enterprise ChatBots using techniques like Retrieval Augmented Generation and Agents, but we've all seen high profile failures. How can you avoid brand embarrassment and make sure your ChatBot or AI Conversational Agent is accurate providing organizations' info? Rapid experimentation, iteration and optimization are the key success factors. In this sessions we learn how you can use an open source GenAI sandbox to find the right LLM, the best parameters setting, the right way to create embeddings from your corpus, and how to evaluate performance and ultimately generate code you can deploy confidently into production. Build a true enterprise quality chatbot backend avoiding risks that can scale on a large knowledge base stored on a Vector DB.
Accepted @ HrOUG 2025
The Oracle AI Microservices Sandbox for RAG rapid prototyping
Although we are inundated with articles and tutorials promising GenAI-based chatbots in just five minutes or so, the reality of developing a reliable agent is much more challenging. Some predict that 30% of projects will be abandoned due to the difficulty of translating proofs of concept and substantial investments into tangible benefits. To help prevent this, an open-source rapid prototyping platform called "Oracle AI Microservices Sandbox" has been released. This platform enables zero-code development of knowledge bases using Oracle DB 23c AI and its Similarity Search capabilities, allowing users to select any LLM for vector embedding and chat completion, whether on-premises or in the cloud, starting from template-based prompt engineering. The hyperparameters related to the LLM and the knowledge base processing can be tested either individually or in bulk, facilitated by the generation of Q&A test datasets to determine accuracy rates. Successfully tested configurations, along with the generated knowledge base, can be published and exported as AI microservices using Spring AI or LangChain, accessible through OpenAI API-compatible REST endpoints.
Accepted @ Analytics and Data Summit 2025
Text-to-SQL: chat with a DB exploiting the Generative AI
The endeavor to translate natural language queries into SQL has been a long-standing objective within the realm of computational linguistics and database management. Recent advancements in Generative Artificial Intelligence mark a pivotal moment in this journey. Current benchmarks have showcased that Large Language Models (LLMs) extend their utility beyond mere code generation to embrace specialized tasks such as Text-to-SQL conversion. This seminar aims to explore the cutting-edge developments in this field, highlighting effective methodologies based on frameworks that transcend the traditional tools and languages commonly associated with data science, like Spring Boot and the innovative "Spring AI" APIs, showing how these modern frameworks can facilitate equally the development of a bridge between natural language processing and database interaction.
Accepted @ Spring I/O 2024
Java meets Generative AI: build a knowledge management system with Spring AI
Generative AI and its applications are no longer just a prerogative of data scientists using Python, but with Java and SpringBoot skills it could be approached through "Spring AI" API.
We will see step-by-step how we can implement a Spring Boot application based on Retrieval Augmented Generation (RAG) with: cloud, hybrid or on-premises LLM models, using a knowledge base stored in a VectorDB, showing tips&trics in ingestion, choosing the LLMs models and prompt engineering. The transition phase to production, through a Backend platform, will not be overlooked.
Accepted @ MakeIT 2024 / JCON OpenBlend Slovenia 2024
UNLOCK THE POWER OF VECTOR EMBEDDINGS: FROM VECTOR STORE TO CHATBOTS
VECTOR STORE TO CHATBOTS
Abstract: The rise of generative AI has increased the demand for more context-aware applications, particularly in Retrieval-Augmented Generation (RAG) for chatbot development. Vector embeddings are essential for enabling efficient search and retrieval of unstructured data. We’ll explore how a vector store can boost RAG and how developers can harness them using SQL, Python, and Java through frameworks like LangChain or Spring AI. We’ll highlight the importance of vector embeddings in improving chatbot responses and optimizing knowledge retrieval, with practical code examples and a low-code platform.
AI Coding Summit - 19 June 2025 - Bucharest, Romania
ORACLE PLATFORMS FOR SUPPORTING MICROSERVICES DEVELOPMENT: TXEVENTQ, MICROTX, AND THE ORACLE BACKEND
In the context of the development of cloud-native and microservice-oriented applications, Oracle offers solutions to simplify integration, management of distributed transactions and interaction with the backend. TXEventQ represents, for example, an innovative messaging service integrated into the database, also designed to replace and integrate technologies such as Kafka, simplifying the architecture and improving operational efficiency. MicroTX, on the other hand, introduces a layer dedicated to the management of distributed transactions between microservices with SAGA pattern, optimized for the cloud-native environment. Finally, Oracle Backend for Microservices and AI allows developers to build microservices in Spring Boot, a platform that significantly reduces the complexity in developing, testing and managing reliable, secure and scalable enterprise microservices integrated with the Oracle Database.
Software Architecture Summit - 20 June 2025 - Bucharest, Romania
Build Smarter Knowledge Management Systems with AI Technology
Knowledge management systems are critical for today’s information-based workers, providing frontline insight and guidance when questions arise. However, building one can be daunting, and using them can cause frustration if questions are misunderstood when queries don’t match the database entries. Generative AI can help, and in this example we’ll use Java and vector database capabilities to create a system that’s more user-friendly. If users find the system more conversational and accessible, they’ll use it more often—that’s our goal!Now, Java developers can harness the capabilities of Oracle Cloud Infrastructure (OCI) Generative AI to build better knowledge management systems.This demo will guide you through the process of leveraging Java, Spring Boot, and the innovative Spring AI APIs to create next-generation applications.
Devoxx Belgium 2024 - 10 October 2024 - Antwerp, Belgium
Analytics and Data Summit 2025 Sessionize Event
AnDOUC TechCasts User group Sessionize Event

Corrado De Bari
Developer Evangelist, Microservices & AI, Oracle Database
Fiumicino, Italy
Links
Actions
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