2025-06-17 –, Kesselhaus
We present an extensible hybrid search solution using Elasticsearch, built on a multi-index architecture and allowing the integration of multiple embedding models. Our approach addresses the challenges of searching a vast and heterogeneous collection, using different chunking granularity and offering an alternative to reciprocal rank fusion.
Over the last few years we have been pushing to the limits our full-text search solution for the French Audiovisual Institute. However, some areas of our immense corpus are still inaccessible, either because the multimedia content lacks textual annotations, or because the automatic transcriptions are not self-sufficient for an efficient full-text search.
Semantic search appears as a natural complement, but the scalability of the implementation reveals specific challenges in capacity planning and chunking strategies to accommodate different embedding models.
Nevertheless, when it comes to merging the benefits of both text and vector search methods, the success of the hybrid search approach relies essentially on the reranking algorithm. To address this, we developed an alternative to the reciprocal rank fusion based on our needs, specifically tailored for a multi-index architecture and integrating multiple embedding sets.
In this talk, we share our experience in building an extensible hybrid search solution, covering everything from complex functional modeling to cluster architecture design. Attendees will gain practical insights into handling billions of vectors in real-world scenarios, such as within large graph data structures. Additionally, we will explore the challenges of hybrid reranking, discussing the limitations of standard fusion techniques and the rationale behind our novel approach.
While relevance evaluation is still ongoing, our modular architecture enables continuous iteration, ensuring the adaptability to the rapid evolution of embedding models and vector optimizations. This flexibility positions our solution to remain at the forefront of large-scale semantic search, balancing precision, scalability, and efficiency.
Search, Scale, Stories
Level:Intermediate
Radu provides consulting services as a Solutions Architect at Adelean. He handles projects around Elasticsearch and Adelean’s A2 search technology. He oversees the integration and evolution of search engines within large e-commerce platforms, marketplaces, or organizations' data lakes. Prior to joining Adelean, Radu acquired solid experience in web archiving, operating large-scale crawling systems in the context of several European research projects. He holds a PhD in Computer Science and an MSc in Distributed Systems.
Italian, adopted by France not long ago, I am a constant learner, dedicated to computer science and discovery—whether uncovering solutions or gaining insights.
Speaker at :
- ElasticON 2023 - Searching through large graphs using Elasticsearch
- Devoxx France 2023 - Cloning CHATGPT with ElasticSearch and HuggingFace
- 10th Meetup Search & Data - Construire une API conversationnelle au dessus d'un moteur de recherche
- Haystack US 2023 - Dive into NLP with the Elastic Stack
- VoxxedDays Luxembourg 2023 - Cloner ChatGPT avec Hugging Face et Elasticsearch
- DevoxxMorocco 2023 - Conversational Search - Unleashing the Power of Voice Search, Question Answering, and LLMs
- DevFest Toulouse 2023 - Cloner ChatGPT avec Hugging Face et Elasticsearch
- 11th Meetup Search & Data - Exploration of an Open Source Rag System
- Devoxx France 2024 - Mettre en place un RAG Open Source en 30 minutes
- Devoxx France 2024 - Construire son Assistant Intelligent avec Hugging Face et Elasticsearch
- OpensearchCon EU 2024 - Implementing an open-source RAG with OpenSearch
- VoxxedDays Luxembourg 2024 - Home Assistant sous surveillance
- Devoxx Morocco 2024 - A practical guide about prompt engineering
- 1st OpenSearch France UG - To the discovery of OpenSearch AI superpowers!
- Big Data Europe 2024 - Exploring Large Graphs at the Heart of the French National Audiovisual Institute
-ElasticON 2025 - Billion vectors baby
-Devoxx UK 2025 - Exploring Large Graphs at the Heart of the French National Audiovisual Institute
-OpensearchCon EU 2025 - Monitoring a smart home with Opensearch