Solving LLM Data Problems with Vector Databases - Part 2
Explore vector databases' role in LLM apps, focusing on solving data issues and democratizing access to this technology for efficient billion-scale vector search.
Fine-Tune T5 for Document Classification - Part 1: Creating Dataset with Web Scraping
Personalize Flan-T5 for document classification by creating a custom dataset using web scraping techniques with DuckDuckGo.
Towards Neuro-Symbolic AI with Knowledge Graphs and Large Language Models
Explore the fusion of neuro-symbolic AI, knowledge graphs, and large language models. Learn how combining these approaches can enhance AI systems' factual understanding and decision-making capabilities.
Retrieval Augmented Generation (RAG) for LLM-Powered Apps
Explore retrieval augmented generation (RAG) for enhancing LLM-powered applications, gaining insights into its importance and practical implementation.
Enterprise Jargon and RAG Systems - Effective Tactics for Improved Performance
Discover effective tactics to enhance RAG and retrieval systems for handling enterprise jargon, improving LLM-powered tools and applications for businesses.
Why Retrieval Augmented Generation (RAG) is Overrated
Explore the limitations of Retrieval Augmented Generation (RAG), including hallucinations, complexity, and cost. Learn practical approaches to make RAG more effective in AI applications.
Co-design Hardware and Algorithm for Vector Search
Explore hardware-algorithm co-design for efficient vector search on FPGAs, enhancing performance in large-scale information retrieval and machine learning systems.
Question Answering over Documents with RAG - Lecture 6.4
Explore Retrieval-Augmented Generation (RAG) to enhance LLMs with external data, improving accuracy and relevance in corporate settings. Learn to set up and query a RAG system using sample employee data.
Developing Local AI Copilots with LangChain, NVIDIA NIM, and FAISS - LLM App Development
Learn to build a local AI copilot using LangChain, NVIDIA NIM, and FAISS. Covers document processing, vector storage, inference with Llama 3, and LangChain orchestration for responsive LLM applications.
Introduction to Retrieval-Augmented Generation (RAG) - Lecture 6.1
Explore Retrieval-Augmented Generation (RAG) for precise document-based Q&A using LLMs and LangChain. Learn about retrieval, augmentation, and generation phases to enhance model accuracy.
Retrieval-Augmented Generation: Enhancing AI Models - Lecture 7
Explore Retrieval-Augmented Generation (RAG): theory, components, and practical implementation. Enhance AI models' capabilities with this comprehensive overview for beginners and enthusiasts alike.
Build a Q&A App with RAG Using Gemini Pro and LangChain
Learn to create an intelligent Q&A app using Retrieval-Augmented Generation, Gemini Pro, and LangChain. Master advanced retrieval techniques to enhance chatbot performance and build a powerful AI-driven application.
Annotating and Spotting in Mathematical Corpora - Concepts and Tools
Explore techniques for annotating and spotting mathematical concepts in large text corpora, enhancing research and analysis in mathematical fields.
RAG from Scratch with Llama 3.1 - Building a Custom Data Chatbot
Hands-on tutorial for building a RAG system from scratch using Llama 3.1, Groq API, Sqlite-vec, and FastEmbed. Learn to create a chatbot with custom data without external libraries.
Building the World's Largest RAG for Knowledge Management at CVS Health
Explore CVS Health's innovative approach to building a large-scale RAG system for unified knowledge management, addressing challenges and strategies for implementing enterprise-wide information access.
RAG from the Ground Up with Python and Ollama - Building a Document Interaction System
Build a RAG system with Python and Ollama: parse documents, create embeddings, implement relevance scoring, and enable LLM interaction with your own datasets.
Vector Databases 101 - How Do They Work?
Explore vector databases' functionality, applications, and architecture. Learn about similarity search, indexing techniques, and real-world use cases in machine learning and AI.
Discovering Research Ideas Using Semantic Vectors and Machine Learning
Explore semantic vectors and machine learning for research idea discovery, enhancing content discoverability across disciplines using UNSILO's innovative approach to concept extraction and semantic mapping.
Wings Stay On or Replacing On Site Search at Wikipedia
Explore Wikipedia's search engine overhaul, focusing on user satisfaction and high-volume traffic handling. Learn about the challenges and solutions in improving search functionality for one of the world's most visited websites.
Retrieval, Search and Knowledge in the Age of LLMs and Vector Databases
Explore vector embeddings' impact on information compression, search, and knowledge retrieval. Learn how enterprises can leverage this technology to enhance customer understanding and interaction.
Embeddings - What They Are and Why They Matter
Discover how embeddings work in machine learning, from basic concepts to practical applications in semantic search and content relationships, with hands-on examples and implementation techniques.