Christian De Simone
Christian is an AI Engineer with the MemorIA team, passionate about continuous learning and innovation. With extensive experience in developing cloud-native software using Kubernetes, he has hands-on expertise with major cloud providers such as AWS, Azure, and Scaleway. Christian is dedicated to continuous improvement, constantly refining his skills to deliver innovative, successful solutions. His work focuses on integrating AI technologies to create intelligent, scalable systems that drive impactful results.
💻 Software Development & AI Integration
🚀 Cloud-Native Solutions Development
🤖 AI-driven innovation and automation
💬 Collaborative and approachable—building strong connections with colleagues
Software & AI Engineer
Your company –Intré s.r.l. | MemorIA
Session
Have you ever wondered what it's like to have a virtual assistant that can answer questions about your documentation? In this talk, we'll share how we built an intelligent chatbot powered by OpenAI, Qdrant and Haystack to innovate user support and transform static documents into interactive resources.
In today's fast-paced digital environment, instant access to relevant information is no longer a luxury but a necessity. Imagine interacting with a document as if it were a knowledgeable expert, providing precise answers at your fingertips. We harnessed OpenAI Assistant, Qdrant, and Haystack to build a chatbot that not only responds to document-based queries but also pinpoints the exact page and context of the information, creating a seamless and engaging user experience.
Key Takeaways:
- Real-world use case: From scratch, we transformed a client's documentation into a live, interactive resource.
- Retrieval in Action: Learn how we integrated OpenAI's retrieval mode to quickly extract relevant information.
- Advanced data management: Discover how Qdrant and Haystack handle embedding persistence and similarity calculations for fast answers.
This will be a hands-on session where we'll dive into the code and show you how to replicate our solution.
Duration: 45-60 minutes.
This intervention has not previously been presented at other conferences.