OpenSource Connections Courses

Supercharging Search in OpenSearch - Harnessing User Behavior Insights for Continuous Improvement

Discover how to capture user behavior insights beyond basic search results to continuously improve OpenSearch systems and enhance user experience through data-driven optimization.

• YouTube
• 49 minutes
• Self-Paced
• Free Video

How Great Product Managers Build for Impact

Discover how search product managers can build strategic roadmaps that balance tactical demands with long-term vision while keeping stakeholders aligned and teams focused on impact.

• YouTube
• 47 minutes
• Self-Paced
• Free Video

Commoditizing Inference - Your Query Language Should Speak AI

Explore how AI inference becomes a query-native primitive in Elasticsearch, covering semantic retrieval, re-ranking, and new ES|QL primitives with practical examples.

• YouTube
• 46 minutes
• Self-Paced
• Free Video

From BM25 to Mixture-of-Encoders - Evaluations for Next-Gen Search and Retrieval Systems

Explore advanced retrieval systems comparing BM25, vector, hybrid models, and mixture-of-encoders for multi-attribute search with real-world evaluation metrics.

• YouTube
• 48 minutes
• Self-Paced
• Free Video

Harnessing AI to Strengthen Trustworthy Information

Discover how AI combats misinformation through search, intelligent assistants, and RAG systems to empower journalists with fact-checking tools and rebuild trust in news.

• YouTube
• 47 minutes
• Self-Paced
• Free Video

AI Agents - From Hype to Reality

Explore AI agents through three expert perspectives: investment hype, user needs vs promises, and technical limitations to build practical solutions over possibilities.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Future-Proofing E-commerce Search Architecture for Conversational Commerce

Discover how to transform e-commerce search with federated architecture, improving latency by triple digits while cutting costs 20% and boosting conversions for better customer experience.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Beyond Keywords - Measuring Multimodal Search Quality

Discover how to evaluate multimodal search systems using embedding models to measure semantic relevance across text and images, with practical open-source tools for optimization.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

Billion-Scale Hybrid Retrieval in a Single Query

Discover a revolutionary approach to billion-scale hybrid retrieval that unifies dense & sparse vectors, keywords, and filters in a single distributed query without separate indexes.

• YouTube
• 41 minutes
• Self-Paced
• Free Video

Agentic Search Tuning - Faster and Better

Discover how LLM-based agents automate search engine tuning through interleaved A/B testing, making optimization faster and more accurate than manual methods.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

AI-Fueled Automation and the New Value Story of Search

Discover how AI-fueled automation transforms search value propositions, unlocking ROI for long-tail use cases and agentic users in this keynote on modern search relevance strategies.

• YouTube
• 44 minutes
• Self-Paced
• Free Video

Hybrid Image Search at Scale - Lessons in Accuracy, Latency, and Cost

Discover how to build scalable hybrid image search systems combining visual embeddings, LLM-based lexical search, and knowledge graphs for 10M+ products at industrial scale.

• YouTube
• 45 minutes
• Self-Paced
• Free Video

Hybrid Search Lessons Learned - Designing Systems for RAG and Conventional Search

Discover practical strategies for implementing hybrid search systems that serve both RAG and conventional search, including query design, latency control, and enterprise rollout challenges.

• YouTube
• 46 minutes
• Self-Paced
• Free Video

Improving Relevance in RAG - Lessons from LiveRAG Challenge

Discover practical strategies for enhancing retrieval relevance in RAG systems through real-world SIGIR LiveRAG challenge insights and synthetic data generation techniques.

• YouTube
• 40 minutes
• Self-Paced
• Free Video

Smart Recall - Enhance Local LLM Conversations with Embedding-Aware Context Retrieval

Discover how to build embedding-aware context retrieval systems that enhance local LLM memory using Python, semantic similarity, and efficient recall mechanisms for coherent conversations.

• YouTube
• 41 minutes
• Self-Paced
• Free Video