Generative AI for Search
Explore the powerful role of generative AI in search, focusing on NLP and Vision. Discover key challenges and promising directions through anecdotes and organizing principles.
The Missing Link - Taxonomists and Taxonomy Governance
Explore the crucial role of taxonomists and governance in effective taxonomy management. Gain insights into best practices for organizing and structuring information.
Using Vector Databases with LLMs - Part One
Explore vector databases for LLMs, enhancing audio and visual data processing, recognition, and search capabilities.
Using Vector Databases with LLMs - Part Two
Explore advanced vector database applications for LLMs, enhancing audio/visual recognition and search capabilities.
Mobilize Document Insights with Generative AI
Harness generative AI to revolutionize document processing, extracting insights and improving accuracy with minimal ML training for faster, more efficient workflows.
Getting Started with OpenSearch and OpenSearch Dashboards
Learn to set up and use OpenSearch for powerful search and analytics. Master cluster configuration, dashboard creation, and best practices for effective data visualization and management.
Retrieval-Augmented Generation (RAG) - Explained
Explore RAG (Retrieval-Augmented Generation) to mitigate AI hallucinations. Learn key concepts, implementation details, and advanced techniques through multiple passes and quizzes.
Using Vector Databases: Practical Advice for Production - LLMs in Prod Conference
Explore vector databases for LLMs in production. Learn design patterns, context retrieval, feature injection, and common pitfalls. Gain practical insights for efficient deployment and management.
Embeddings and Retrieval for LLMs: Techniques and Challenges
Explore embedding-based retrieval for AI apps, including key limitations and mitigation techniques. Learn about Chroma, an open-source embedding database for LLM applications.
RAG Has Been Oversimplified - Exploring Complexities in Retrieval Augmented Generation
Explore the complexities of Retrieval Augmented Generation (RAG) beyond its oversimplified portrayal. Gain insights into practical challenges and nuanced considerations for developers working with RAG systems.
Information Retrieval and Relevance: Vector Embeddings for Semantic Search
Explore vector embeddings for semantic search, learning techniques to create meaningful representations and apply them in information retrieval systems. Gain insights from an experienced technologist.
Fine-Tuning Foundation Models for Document Classification with Azure ML - LLama2
Fine-tune LLM for document classification using Azure ML Studio's Python SDK. Learn to adapt Llama2, Mistral, or other models for text classification tasks.
Neo4J Knowledge Graph: Topic Extraction with Langchain and Phi3 - Part 1
Explore topic extraction for knowledge graphs using Neo4J, Langchain, and Microsoft Phi3. Learn to enrich movie databases with themes from TMDB.org overviews.
Contextual Search with Vector Search: Exploring Open Source Tools
Explore vector search technology for smarter contextual searches. Learn to implement movie recommendation systems using ClickHouse, OpenSearch, and PGVector. Discover AI models and APIs for efficient data inference.
Documentation and AI: A Match Made in Heaven or Hell?
Explore the impact of AI on software documentation, weighing pros and cons of LLMs in tech writing. Learn best practices for AI-assisted documentation and share experiences.
Truth-Seeker: Using LLM Agents to Build and Verify Knowledge Bases
Explore how LLM agents construct and validate knowledge bases, enhancing data quality for improved AI training and information retrieval.
Building a Distributed Search Engine for Logs
Explore efficient architecture for building a distributed search engine to handle terabytes of logs, inspired by Snowflake's compute-storage separation approach.
Live Coding a Quick and Easy Semantic Search with Qdrant from Scratch - Rust Implementation
Build a simple semantic search using Qdrant's Rust API in a live coding session. Learn implementation techniques and enjoy Rust-related humor along the way.
Build More Capable LLMs with Retrieval Augmented Generation
Enhance LLM capabilities using retrieval-augmented generation to access knowledge bases and deliver fact-based answers, overcoming training data limitations.
Improved Retrieval Augmented Generation with ALL-SORT - Advanced Techniques
Explore advanced retrieval augmented generation techniques using ALL-SORT for improved LLM-assisted information retrieval, with practical demonstrations and performance evaluations.
RAG with Verified Citations - Advanced Inference Techniques
Explore advanced RAG techniques with verified citations, including BM25 and cosine similarity methods. Learn to implement and leverage one-click document RAG for improved accuracy.