Chroma Vector Database: Retrieval for LLMs
Explore Chroma Vector Database's role in enhancing LLM retrieval capabilities with insights from industry experts Hammad Bashir and Liquan Pei.
Retrieval Augmented Generation (RAG) - Tutorial 4
Explore Retrieval Augmented Generation (RAG) techniques to enhance AI models' knowledge and responses using external data sources, improving accuracy and relevance in various applications.
Complete Session on Knowledge Graph and GraphDB with LangChain
Comprehensive exploration of Knowledge Graphs and GraphDB integration with LangChain, covering implementation techniques and practical applications for advanced data management and AI systems.
Streamlining Property Search Across Multiple Platforms Using AI and Machine Learning
Discover how machine learning and AI revolutionize real estate search by integrating multiple platforms, enhancing property discovery, and streamlining the house-hunting process through advanced metasearch capabilities.
Practical Strategies for Implementing Domain-Specific LLMs
Dive into practical strategies for implementing domain-specific large language models, covering RAG architecture, evaluation metrics, data preprocessing, and query optimization techniques.
Building Applications with RAG and LangChain on Google Cloud
Master building AI applications with RAG and LangChain on Google Cloud. Follow a hands-on demonstration of indexing data, creating a web interface, and deploying solutions for enhanced AI response accuracy.
LLMOps with MLflow - Document Classification Using Fine-Tuned LLM Models
Master end-to-end document classification using MLflow for LLM fine-tuning, inference, and deployment with Docker. Build robust APIs and implement CI pipelines for efficient machine learning operations.
Introduction to Retrieval Augmented Generation (RAG) - From Fundamentals to Implementation
Dive into RAG fundamentals and learn to implement AI-powered chatbots using vector databases, combining retrieval and generative models for enhanced information processing capabilities.
LLMOps MLflow - Document Classification with Fine-Tuning and Inference
Domina el fine-tuning de modelos LLM usando MLflow, desde la creación de clasificadores de documentos hasta la implementación con Docker y Azure DevOps para inferencia eficiente.
Delivering RAG at Scale with Azure AI Search - BRK104
Discover how AT&T built and implemented a large-scale RAG knowledge management platform using Azure AI Search, enabling hundreds of GenAI applications with quality measurement and diverse use cases.
Advanced RAG with LlamaIndex, Azure AI Search and Azure AI Foundry
Master advanced RAG fundamentals and build data-grounded AI applications using LlamaIndex and Azure AI Search. Learn retrieval strategies and practical implementation techniques.
Optimizing ColPali for Retrieval at Scale - From Theory to Practice
Discover how to optimize ColPali's multivector document retrieval system through efficient pooling techniques, achieving 12x faster search speeds while maintaining accuracy in RAG and Vision RAG applications.
Advanced Retrieval Augmented Generation (RAG) Techniques
Master advanced RAG implementation techniques, focusing on chunking strategies, embedding model selection, and metadata structuring for building more effective and business-valuable AI applications.
A Deep Dive into Vector Search Technology and Tools
Explore vector search technology through practical demonstrations of ClickHouse, OpenSearch, and PGVector, learning how AI models convert text to vectors for enhanced contextual search capabilities.
Building RAG Applications: Speaking with Unstructured Data Using LangChain - Part 1
Dive into building a RAG application using Langchain, multiple LLMs, and vector stores to enable interactive conversations with unstructured data through a Streamlit interface.
Vector Databases: A New Search Paradigm - OCX 2024
Explore how vector databases revolutionize information search through multidimensional data representation, with hands-on examples using Milvus, Weaviate, and Neo4J for enhanced data analysis.
Improving Gemini Responses with Google Search Access Integration
Discover how to enhance Gemini's responses by integrating Google search capabilities through AI Studio's platform, featuring practical demonstrations and implementation techniques.
Memolet - Reifying the Reuse of User-AI Conversational Memories
Explore innovative approaches to managing and reusing AI conversation histories through Memolet's framework for enhanced human-AI interactions and memory management.
Building RAG Applications from Scratch with NVIDIA NIM Microservices
Dive into building scalable RAG applications using NVIDIA NIM microservices, covering text embedding, reranking, and chatbot integration for high-performance AI deployment.
OpenSearch: Navigating Innovation and Community Collaboration for 2025 and Beyond
Discover how OpenSearch is evolving through community collaboration, focusing on search capabilities, observability, and AI integration while exploring development priorities and strategies for future growth.
Optimizing Hybrid Search in OpenSearch - A Configuration and Dynamic Approach Tutorial
Master hybrid search optimization techniques in OpenSearch through hands-on configuration, data indexing, baseline creation, and dynamic modeling approaches for improved search relevance.