OpenSource Connections Courses

Building Relevance Formulas with LLMs for E-commerce Search

Explore building conversational e-commerce search using LLMs to create relevance formulas that balance user preferences like price, reliability, and personal taste through tensor-based scoring.

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

Behind the Hype - Managing Billion-Scale Embeddings

Discover real-world strategies for managing billion-scale vector databases in Elasticsearch and OpenSearch, moving beyond semantic search hype to tackle scalability and performance challenges.

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

Automatic FAQ - Building a Multi-Agent System to Extract Insights from User Discussions

Discover how to build multi-agent systems that automatically extract insights from user discussions across Discord, GitHub, and other platforms using open-source tools like Milvus and LangChain.

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

Beyond RAG - From Search to Analytics on Unstructured Data with Aryn

Explore advanced AI analytics on unstructured data using Aryn, moving beyond RAG to perform complex semantic analysis at scale with visual AI models and LLMs.

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

AI and LLM Strategies and Application at Mercari Search

Explore how Mercari re-architected their search system using AI and LLMs, covering end-to-end architecture, successful applications, and business ROI considerations for e-commerce.

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

Relevance Proof in Yelp Search - LLM-Powered Annotations

Discover how Yelp enhances search results using LLM-powered annotations, focusing on review highlights and business information to improve user experience and search relevance at scale.

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

Building a GenZ Search Application with LLMs - Search and AI Integration for Student Learning

Discover how Knowunity leverages LLMs to enhance search functionality for Gen Z students, from AI-powered content summarization to intelligent question generation and knowledge graph construction.

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

Training High Quality Embedding Models for Production Vector Search

Master practical techniques for training and optimizing embedding models for production-ready vector search, covering data quality, loss functions, and efficient updating strategies.

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

Boosting LLM Accuracy with Entity Resolution-based RAG

Discover how Entity Resolution enhances RAG systems for LLMs, improving accuracy when handling structured enterprise data like customer records through real-time unified data processing.

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

Nixiesearch - Building a Serverless Search Engine with Lucene on S3

Explore how Nixiesearch leverages Lucene over S3 to create a simplified, serverless search engine with built-in AI capabilities, including RAG and text+image embeddings for modern search solutions.

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

Exploring Vector Search at Scale with Milvus - Building Billion-Scale Solutions

Explore vector search at billion-scale through Milvus, understanding distributed systems architecture, indexing strategies, and scalability solutions for unstructured data processing.

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

Unlocking Product Search with Machine Learning and LLM Innovations

Explore cutting-edge ML and LLM techniques to revolutionize product search, from query understanding to result re-ranking. Discover how to optimize retrieval quality using innovative approaches in a retail scenario.

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

Building a Multimodal LLM-Based Search Assistant Chatbot for Housing Search - Haystack EU 2024

Explore the development of a multimodal LLM-based chatbot for enhanced housing search, featuring contrastive vision-language models and innovative AI technologies to streamline user experiences in real estate.

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

Evaluating Marketplace Search: User Perception vs. Business Metrics

Explore the balance between precision and recall in e-commerce search, examining user perception, business metrics, and modern techniques like vector search. Learn strategies to optimize search relevance and user experience.

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

Vision Language Models and PDFs: What You See Is What You Search - Haystack EU 2024

Explore ColPali, a novel retrieval model using Vision Language Models to embed entire PDF pages, improving retrieval quality and simplifying extraction processes for complex document formats.

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