Transforming the Search Industry with LLMs Using Source Frontier
Explore how Source Frontier technology enhances LLMs' capabilities by combining traditional search engine strengths with AI-powered content generation for more accurate and validated information retrieval.
From Tables to Answers: Building QA Systems for In-Document Searches
Discover how to build effective Question Answering systems for tabular data in PDF documents, from data preparation to modeling implementation, with practical insights and real-world applications.
Measuring Hallucinations in RAG - Retrieval Augmented Generation
Explore techniques to measure and mitigate hallucinations in Retrieval-Augmented Generation (RAG) systems, with practical examples and insights on improving LLM-based applications.
Billions of Records in MySQL: Lessons Learned
Explore strategies for managing billions of MySQL records, covering optimization, storage engines, schema design, and backup techniques for large-scale databases.
Content Deduplication: Vectors vs Keywords - Haystack On Tour, Kraków Feb 2023
Explore content deduplication techniques, comparing keyword-based and vector-based approaches for educational user-generated content at Brainly.
Searching in the Real World: Voice Search UX Lessons - Haystack On Tour Kraków 2023
Explore voice search challenges and UX lessons from commercial applications, focusing on user intent and effective implementation strategies.
Machine Learning for E-commerce Product Discovery - Finding a Needle in a Haystack
Explore machine learning techniques for efficient e-commerce product discovery, addressing challenges and leveraging NLP, image recognition, and knowledge graphs.
Text Embeddings, Classification, and Semantic Search with Python Code
Explore text embeddings for classification and semantic search with Python. Learn to transform text into computable vectors for powerful NLP applications.
Conquer RAG Retrieval Errors: 5-Step Tuning Process in Snorkel Flow
Optimize RAG retrieval with a 5-step tuning process in Snorkel Flow. Learn to identify errors, improve document chunking, and enhance embedding models for better accuracy and performance.
Best Practices and Tips for Fine-Tuning Representation Models
Discover techniques to enhance generative applications through representation model fine-tuning. Learn data quality strategies, augmentation methods, and optimization tips for RAG-based pipelines.
RAG Optimization: A Practical Overview for Improving Retrieval Augmented Generation
Discover practical techniques for optimizing RAG systems, from document chunking to embedding models and data enrichment, to enhance LLM performance and reliability.
Documentation for Using Open Source Design Templates
Learn best practices for creating and documenting open source design templates, focusing on UX research scalability and community collaboration in OpenSearch.
Tutorial de Bases de Datos Vectoriales, LangChain y ChatGPT
Aprende a integrar bases de datos vectoriales, LangChain y ChatGPT para crear aplicaciones de IA avanzadas y eficientes.
Building Google-Like Search Experiences on a Budget
Discover smart, budget-friendly approaches to create Google-like search experiences. Gain insights on structuring search results for optimal user satisfaction and problem-solving.
Retrieve, Augment, Generate then Measure - How to Build Open Source AI
Explore open-source AI development through the Retrieve, Augment, Generate, and Measure framework. Learn practical techniques for building AI systems using freely available tools and resources.
Harnessing the Power of Generative AI to Deliver Next-Gen Search Experiences
Explore how generative AI and semantic search revolutionize search engines, enabling deep understanding of user queries and AI-driven experiences. Learn about Enterprise Search tools for advanced question-answering capabilities.
Redefining Vector Search for Generative AI Application Development
Explore cutting-edge vector search algorithms for generative AI apps, leveraging Google's decade of research for enterprise-scale solutions.
Create a Contextual Chatbot with LLM and Vector Database in 10 Minutes
Learn to build a contextual chatbot using LLM and vector database, exploring embedding, search, and answer generation with Langchain.
Building Recommender Systems with Large Language Models
Explore recent approaches to building recommender systems using LLMs, focusing on language understanding and generation templates for various recommendation tasks.
Introduction to QA Bots with RAGs and LLMs
Explore QA systems using LLMs and RAGs, learning to create powerful question-answering bots on custom datasets.
Navigating via Retrieval Evaluation to Demystify LLM Wonderland
Explore retrieval evaluation's crucial role in LLM applications, focusing on its impact on response quality. Delve into the link between retrieval accuracy and answer quality, emphasizing thorough evaluation methods.