- Видео 198
- Просмотров 125 373
OpenSource Connections
США
Добавлен 17 май 2019
We're OpenSource Connections, the search & AI specialists. We wrote the Manning book on Relevant Search! We help you own your search and empower your search teams with our expert consultancy and training. This channel contains videos from our own conference series, Haystack, held in the USA every April and Europe every October plus touring events, and other talks we've given. If you have a search & AI problem and want our help do contact us at www.opensourceconnections.com !
Optimizing Hybrid Search in OpenSearch
This notebook walkthrough covers how to find the ideal configuration set for hybrid search in your installation and how to approach this challenge more dynamically based on one example dataset.
Follow along with the repository: github.com/o19s/opensearch-hybrid-search-optimization
00:00:00 - Intro
00:01:15 - Prepare OpenSearch
00:07:37 - Index Data
00:12:56 - Create a Baseline
00:27:33 - Best Hybrid Search Configuration
00:43:11 - Query, Result, Judgement Analysis
00:51:44 - Individual Query Drill Down
01:03:21 - Dynamic Approach - Features & Models
01:33:29 - Evaluate Models
Follow along with the repository: github.com/o19s/opensearch-hybrid-search-optimization
00:00:00 - Intro
00:01:15 - Prepare OpenSearch
00:07:37 - Index Data
00:12:56 - Create a Baseline
00:27:33 - Best Hybrid Search Configuration
00:43:11 - Query, Result, Judgement Analysis
00:51:44 - Individual Query Drill Down
01:03:21 - Dynamic Approach - Features & Models
01:33:29 - Evaluate Models
Просмотров: 219
Видео
Haystack EU 2024 - Gregor Weber & Alexandra Klochko: Search & LLM:A GenZ Search App for 12m students
Просмотров 1022 месяца назад
In today’s rapidly evolving digital landscape, where information overload is the norm, creating a search experience that resonates with Gen Z demands more than just relevance-it requires, personalization and adaptability. At Knowunity, an Ed-Tech startup with over 12 million students, we’ve are leveraging Large Language Models to further develop our search. Our search team consist of 1 PM and 1...
Haystack EU 2024 - Pallavi Patil: Relevance Proof in Yelp Search: LLM-Powered Annotations
Просмотров 1532 месяца назад
In Yelp Search, we heavily rely on user reviews while choosing relevant search results, and we’ve also incorporated other relevant business information into our search system. Search result annotations are a key accompaniment to the results, as “review highlights” annotations can explain to the user why a business is relevant for their intent. We use LLM expansions to power these annotations us...
Haystack EU 2024 - Robertson Taylor:Train high quality embedding models for production vector search
Просмотров 1182 месяца назад
You are only as good as your embeddings - how to train high quality models for production vector search This talk covers practicalities of training embedding models for production (multi-modal) vector search. Topics will span data, training, and evaluation. More specifically the talk will cover: - How to optimize model training for business objectives by leveraging historic search-result intera...
Haystack EU 2024 - Hendrik Nehnes: Boosting LLM accuracy with Entity Resolution-based RAG
Просмотров 872 месяца назад
Enterprises are increasingly looking to run Large Language Models (LLMs) on private, internal data that LLMs have never seen and which must remain confidential. Retrieval Augmented Generation (RAG) enhances LLMs with data from specific, controlled sources. Typically, RAG uses vector databases, which excel at retrieving information from unstructured data. However, for structured data like custom...
Haystack EU 2024 - Lightning Talks
Просмотров 672 месяца назад
Lightning Talks featuring: Praveen Mohan - Demo on using LLM to extract filters for your queries Dainius Jocas - Adventures with ANN Daniel Wrigley - Leveraging User Behavior Insights - From Evaluation to Hybrid Search Optimization Evgeniya Sukhodolskaya - Any Embedding Model Can Become a Late Interaction Model Shantanu Ladwe - Test driven approach
Haystack EU 2024 - Roman Grebennikov: Nixiesearch:Lucene on S3 & building a serverless search engine
Просмотров 1942 месяца назад
Nixiesearch: running Lucene over S3, and why we are building our own serverless search engineIs your search cluster stuck in ‘status: red’ due to over-complicated maintenance? Are modern vector databases still falling short in solving your real-world search problems? You’re not alone. Companies like Uber, Doordash, Amazon, and Yelp have turned to running their search backends on Lucene over S3 ...
Haystack EU 2024 - Stephen Batifol: Exploring Vector Search at Scale
Просмотров 812 месяца назад
Milvus is an open-source vector database built to power Gen AI solutions. 80% of the data in the world is unstructured data, and vector databases are the databases that help you get valuable insights from unstructured data. With this in mind, we built Milvus as a distributed system on top of other open-source solutions, including MinIO and Kafka, to support vector collections that exceed billio...
Haystack EU 2024 - Elzbieta Jakubowska: Women of Search Present: The Life of a Search System
Просмотров 612 месяца назад
In a tech landscape that would have been deemed science fiction just a few years ago, terms like ‘vector search’ and ‘LLMs’ have become as commonplace as ‘coffee’ and ‘good morning’ in our daily conversations. Being part of this rapidly evolving community is exhilarating, yet it often feels like everyone but you is already leveraging the latest technology. If your aim is to build the most intel...
Haystack EU 2024- Hajer Bouafif&Praveen Mohan Prasad:Unlock Product Search with ML & LLM Innovations
Просмотров 1652 месяца назад
In the realm of search, Machine Learning plays a pivotal role in enhancing the user experience throughout the entire lifecycle, from ingesting documents to delivering highly relevant results for user queries. This session will showcase various ML integrations tailored to optimize outcomes for user queries in a retail scenario, accompanied by a live demonstration. We will explore cutting-edge te...
Haystack EU 2024- Julien Meynet:Evaluating Marketplace Search: User Perception vs. Business Metrics
Просмотров 1342 месяца назад
Evaluating E-commerce and Marketplace Search: User Perception vs. Business Metrics Precision and recall have long been recognized as a fundamental trade-off in search. Especially in e-commerce and marketplaces, search optimization often involves finding the right balance between these two concepts. This talk will explore how user perception of search quality (UX metrics) and business performanc...
Haystack EU 2024 - Tetiana Torovets,Giulio Santo & Lucas Cardozo:A Multimodal Housing Search Chatbot
Просмотров 2652 месяца назад
Building a Multimodal LLM-Based Search Assistant Chatbot to Enhance Housing Search QuintoAndar Group is the largest housing platform in Latin America, leveraging cutting-edge AI technologies to streamline the housing search process, reducing paperwork and increasing accessibility. To elevate our users’ experience even further, we developed a groundbreaking search experience by adopting contrast...
Haystack EU 2024 - Jo Kristian Bergum:What You See Is What You Search: Vision Language Models & PDFs
Просмотров 8652 месяца назад
Extracting information from complex document formats like PDFs usually involves a multi-step process, including text extraction, OCR, layout analysis, chunking, and embedding. This extraction process is resource-intensive, and the quality can vary, resulting in poor retrieval quality (garbage-in, garbage-out). ColPali, a newly proposed retrieval model, presents a more efficient alternative usin...
Haystack EU 2024 -Marcin Gumkowski & Catarina Gonçalves:LTR Framework-how to train an army of models
Просмотров 1442 месяца назад
At OLX, we faced a significant challenge: the need to experiment with rankings across many countries and categories, totaling over 100. This situation became a bottleneck, hindering our Data Scientists from progressing in their work. Given our limited human resources, it was imperative to seek more automated solutions. We implemented LTR Framework, allowing our Data Scientists to adjust configu...
Haystack EU 2024 - Sean MacAvaney: Re-Thinking Re-Ranking
Просмотров 2742 месяца назад
Re-ranking systems often rely on a ‘cascading’ approach, where an initial set of documents is re-sorted to create a final result list. However, this method has a critical flaw: it can miss out on the most relevant documents by filtering them out too early, which reduces recall and hampers overall performance. In this talk, I will share an alternative to the cascading approach that brings in add...
Haystack EU 2024 - Aswath N Srinivasan:Leveraging User Behavior Insights to Enhance Search Relevance
Просмотров 1652 месяца назад
Haystack EU 2024 - Aswath N Srinivasan:Leveraging User Behavior Insights to Enhance Search Relevance
Haystack EU 2024 - Trey Grainger: Keynote: AI-Powered Search: Navigating the Evolving Lexicon of IR
Просмотров 3472 месяца назад
Haystack EU 2024 - Trey Grainger: Keynote: AI-Powered Search: Navigating the Evolving Lexicon of IR
Haystack US 2024 - Trey Grainger: Personalizing search using multimodal latent behavioral embeddings
Просмотров 3677 месяцев назад
Haystack US 2024 - Trey Grainger: Personalizing search using multimodal latent behavioral embeddings
Haystack US 2024 - Jeff Capobianco: Chat With Your Data - A Practical Guide to Production RAG Apps
Просмотров 3247 месяцев назад
Haystack US 2024 - Jeff Capobianco: Chat With Your Data - A Practical Guide to Production RAG Apps
Haystack US 2024 - Jeremy Hudson & René Kriegler: Evolution of Moody's Search & AI
Просмотров 2277 месяцев назад
Haystack US 2024 - Jeremy Hudson & René Kriegler: Evolution of Moody's Search & AI
Haystack US 2024 - Scott Stults: Measuring and Improving the R in RAG
Просмотров 1687 месяцев назад
Haystack US 2024 - Scott Stults: Measuring and Improving the R in RAG
Haystack US 2024 - Joelle Robinson: Revisiting the Basics: How Round Robin Improved Search Relevancy
Просмотров 1367 месяцев назад
Haystack US 2024 - Joelle Robinson: Revisiting the Basics: How Round Robin Improved Search Relevancy
Haystack US 2024 - Praveen Mohan Prasad & Hajer Bouafif: Expanding RAG with multimodal capabilities
Просмотров 1857 месяцев назад
Haystack US 2024 - Praveen Mohan Prasad & Hajer Bouafif: Expanding RAG with multimodal capabilities
Haystack US 2024- Kathleen DeRusso:Retro Relevance:Lessons Learned Balancing Keyword&Semantic Search
Просмотров 4127 месяцев назад
Haystack US 2024- Kathleen DeRusso:Retro Relevance:Lessons Learned Balancing Keyword&Semantic Search
Haystack US 2024 - Eric Pugh & Stavros Macrakis: Your Search Engine Needs a Memory!
Просмотров 2597 месяцев назад
Haystack US 2024 - Eric Pugh & Stavros Macrakis: Your Search Engine Needs a Memory!
Haystack US 2024 - Colin Harman: Why RAG Projects Fail, and How to Make Yours Succeed
Просмотров 3697 месяцев назад
Haystack US 2024 - Colin Harman: Why RAG Projects Fail, and How to Make Yours Succeed
Haystack US 2024 - Audrey Lorberfeld: Women of Search present Comparing AI-Augmented IR Strategies
Просмотров 1597 месяцев назад
Haystack US 2024 - Audrey Lorberfeld: Women of Search present Comparing AI-Augmented IR Strategies
Haystack US 2024-Paul-Louis Nech:Zucchini/Cucumber? Benchmarking Embeddings, Similar Image Retrieval
Просмотров 1137 месяцев назад
Haystack US 2024-Paul-Louis Nech:Zucchini/Cucumber? Benchmarking Embeddings, Similar Image Retrieval
Haystack US 2024 - Ali Rokni: Search Query Understanding with LLMs: From Ideation to Production
Просмотров 5197 месяцев назад
Haystack US 2024 - Ali Rokni: Search Query Understanding with LLMs: From Ideation to Production