Optimization of Retrieval-Augmented Generation (RAG) for eCommerce: Personalized Responses with API Integration and Dynamic Queries [ukr]
Like
3
Talk presentation
A practical case study exploring how fine-tuning RAG reduces the risk of AI hallucinations and improves response accuracy by combining knowledge from a database with dynamic API requests
Oleksandr Marholin
ConnectiveOne, CTO
- Over 10 years of experience in IT
- Launched the AI-based product FaceIdentification.pro, which optimizes online identification processes, facial recognition in databases, KYC, Liveness Detection, and document recognition.
- At the service IT company Evergreen, contributed to the creation of over 100 projects from concept to implementation.
- At the Conversational AI platform ConnectiveOne, built the technical team from scratch, implemented agile development practices, and improved SDLC processes.
- Graduated from the Faculty of Cybernetics at Taras Shevchenko National University of Kyiv, where he also taught. Mentors young developers.
- Enthusiast of craft beer, runs an Instagram blog as a horse character: @konski_makedonski, supports the Ukrainian Armed Forces
- LinkedIn, Facebook