Everything tagged retrieval-augmented-generation, newest first. Tags come from the classifier reading each item's summary; 394 tags used 25 times or more have their own page.
Modern AI can be understood through a human analogy: the model is the brain, training is schooling, RAG adds trusted outside knowledge, and agents give the system hands and feet to act in the world, helping explain how generative AI works, why it can hallucinate, and how it becomes more useful.
U.S. CD revenue surged 58.6% in the first half of 2026, reversing a prior decline as renewed interest in retro technology and physical media drives a comeback.
The content explains four ways to give AI agents task-specific knowledge beyond training data—skills, MCP, RAG, and memory—using a web app 500 error as an example, and argues that simply stuffing context into the prompt is often ineffective compared with structured methods that provide procedures, tools, retrieval, or retained experience.
The content explains the “what versus why” problem in data systems, where structured SQL data and unstructured policy documents must be combined by an AI agent that reads questions, identifies needed sources, builds and runs queries, compiles results, and answers with grounded context.
The document discusses the limitations of retrieval augmented generation (RAG) for answering specific questions in structured documents and proposes an alternative method that preserves document structure, allowing models to navigate and reason through the document's tree structure for more accurate answers.
The progression of AI engineering projects ranges from simple language model APIs to advanced systems where AI agents autonomously build and manage enterprise-scale solutions, highlighting the increasing complexity and sophistication required at each level.
The content outlines a five-level progression of AI engineering projects, showing how beginners move from simple API-based chatbots to robust retrieval systems, tool-using agents, and eventually production-grade AI platforms, while emphasizing the skills, evaluation methods, and operational thinking needed to advance.
Long context and cache augmented generation (CAG) offer alternative methods to retrieval augmented generation (RAG) for providing large language models (LLMs) with external knowledge by utilizing expanded context windows and caching strategies, though each has its own advantages and challenges related to cost, latency, and performance.
The effectiveness of AI models is often hindered by a lack of context, making context engineering crucial for providing relevant, real-time data and governance to enhance AI performance and decision-making.
AI is increasingly integrated into daily life, enhancing productivity and decision-making, but challenges remain in ensuring accurate responses, especially for mainframe-related queries, which can be improved through retrieval-augmented generation.
Large language models (LLMs) are limited by their training cutoff and lack real-time or private data knowledge, requiring context injection via retrieval augmented generation (RAG) or long context methods to integrate relevant information.
Agentic storage is a system designed to provide AI agents with persistent memory by integrating with various storage systems through a standardized protocol, enabling them to retain work products beyond their temporary context window.
Retrieval Augmented Generation (RAG) enhances large language models by retrieving and embedding relevant external documents, including multimodal data, into input prompts for accurate query responses.
Despite advances in generative AI and larger context windows, Retrieval Augmented Generation (RAG) remains crucial for cost-effective, accurate responses, with OpenRAG offering an integrated open-source solution for efficient data ingestion, retrieval, and orchestration.
The evolution of business intelligence is shifting from static dashboards to conversational BI using large language models and retrieval augmented generation for more dynamic, context-aware insights.
This crash course teaches the integration of AI systems using Retrieval Augmented Generation (RAG) and Model Context Protocol (MCP) to build sophisticated applications, with hands-on labs and no prior AI knowledge required.
The Verscell AI SDK course teaches building a customer support AI agent using TypeScript, focusing on autonomous decision-making, real-time information retrieval, and integration with OpenAI to enhance customer support efficiency and personalization.
Agentic AI and Retrieval Augmented Generation (RAG) are popular AI concepts with varied applications, such as coding and enterprise support, but their effectiveness depends on specific contexts and use cases.
Retrieval Augmented Generation (RAG) systems rely on various retrieval strategies, such as sparse and dense retrieval, to effectively fetch and integrate relevant knowledge into language models, impacting the quality and relevance of AI-generated responses.
The course, led by Suman Debnath from Amazon, explores AI engineering advancements, focusing on embeddings, multimodal models, and retrieval augmented generation (RAG) with practical applications using Amazon Nova and Bedrock for enterprise solutions.
AI assistants leverage retrieval augmented generation and content-aware storage, using AI-optimized storage, data pipelines, vector databases, and accelerator chips to enhance inferencing accuracy by accessing and processing unstructured data.
AI agents autonomously achieve goals by maintaining state, breaking down complex tasks, and iteratively planning and executing actions, with applications in IoT, retrieval augmented generation, and multi-agent workflows to optimize processes like agriculture and content creation.
ZeroEntropy offers retrieval-augmented generation (RAG) via an API and has secured investment from Initialized, a16z Scout, and numerous angel investors.
AI assistants are revolutionizing work by using content-aware storage and Retrieval Augmented Generation to leverage untapped enterprise data, enhancing inferencing with real-time insights for improved decision-making and operational efficiency.
The conversation humorously highlights the limitations and potential inaccuracies of AI, emphasizing the need for techniques like Retrieval Augmented Generation (RAG) and selecting appropriate models to improve AI's accuracy in providing reliable information.
Retrieval-augmented fine tuning (RAF) combines retrieval augmented generation (RAG) and fine-tuning to enhance large language models' (LLM) performance in domain-specific tasks by training models to effectively use external documents for generating answers.
Douwe Kiela discusses the evolution and challenges of retrieval-augmented generation (RAG), emphasizing personalization, synthetic data, and the integration of structured and unstructured data in AI models.
Data lakehouses blend the strengths of data lakes and warehouses, enabling organizations to unify, manage, and leverage their data for accurate, high-performance AI applications using methods like retrieval augmented generation (RAG).
The modern equivalent of Googling oneself is querying chatbots, with improved responses achievable through retrieval augmented generation, fine-tuning, and prompt engineering, each offering unique benefits for enhancing large language model outputs.
Ryan and Amr Awadallah discuss advancements in retrieval-augmented generation, the importance of fact-checking, and Vectara's Mockingbird model's approach to reducing AI hallucinations.
Augmented generation techniques like retrieval-augmented generation (RAG) and cache-augmented generation (CAG) enhance large language models by providing external knowledge, with RAG using a searchable database and CAG preloading all knowledge into the context window.
Open-source AI empowers developers with flexible, cost-effective tools for building scalable applications, managing data, and leveraging community-driven models, while navigating challenges in maintenance and expertise.
Indirect prompt injection involves embedding hidden instructions in data sources accessed by large language models, leading to unpredictable and potentially harmful outputs without a clear solution.
Erica demonstrates using LangChain for retrieval augmented generation (RAG) in Python to provide large language models with up-to-date information from a knowledge base for accurate responses.
Enterprises are using AI, including large language models and retrieval augmented generation, to improve employee productivity by integrating data from multiple silos.
Web developers can build AI applications using large language models through user interfaces, APIs, and frameworks, employing techniques like basic prompting, retrieval augmented generation, and AI agents to retrieve relevant answers efficiently.
BA's World 2024 conference introduced groundbreaking AI technologies like IR, Myota, Free Canvas, and Zadu AI glasses, enhancing text-to-image generation, no-code app creation, content creation, and everyday AI utility.
The content discusses strategies for optimizing customer experience in an electronics store by using context optimization, prompt engineering, retrieval augmented generation, and fine-tuning large language models.
Retrieval augmented generation (RAG) enhances large language model responses by using vector databases for context, with agenetic RAG employing LLMs as decision-making agents to improve data relevance and accuracy.
Ben Popper and Keith Babo discuss evolving API security in the GenAI era, emphasizing governance, data protection, and the role of API gateways.
OpenAI's new 01 models excel in complex reasoning, integrating retrieval augmented generation for enhanced accuracy and structured outputs.
Using watsonx flows engine simplifies deploying RAG solutions at scale by handling complex tasks like tokenization, retrieval, and authentication.
Retrieval Augmented Generation (RAG) enhances large language models by combining queries with external data for more accurate, source-cited outputs.
Retrieval-augmented generation (RAG) is an effective method for specializing LLMs with your data, requiring more than combining pretrained models.
This course, created by Paulo, teaches the basics and advanced techniques of Retrieval Augmented Generation (RAG) for integrating personal data with large language models.
The RAGlow framework, an advanced open-source AI engine for retrieval augmented generation, has received significant updates enhancing integrations, workflows, and data handling.
Ben and Eira discuss with LlamaIndex's CEO Jerry Lu and VC Jerry Chen about simplifying LLM app development and its challenges.
Generative AI and large language models, through techniques like Retrieval Augmented Generation (RAG), can assist NOC engineers by efficiently retrieving and summarizing relevant data, generating trouble tickets, and classifying issues to streamline problem-solving processes.
