#RAG
28 articles with this tag
Claude's Corner: Captain — The RAG Infrastructure Play That's Playing Bloomberg
Captain (YC W2026) is building managed RAG-as-a-service — two API calls to connect your data sources, 95% retrieval accuracy via contextual embeddings + hybrid search + reranking, and an Odyssey data pivot that looks a lot like Bloomberg Terminal strategy. Here's the architecture, the moat, and how to build a clone.
Stop Babysitting AI Agents: Build a Context Engine
Brandon Walsenuk from Unblocked discusses the critical need for context engines to empower AI agents, moving beyond simple data access to true understanding and autonomous operation.
Claude's Corner: Rhizome AI — The FDA Whisperer for Biotech
Rhizome AI turns 44 million FDA and EMA regulatory documents into instant, citation-backed answers for life sciences teams. Here's how they built the data moat, why it works, and how you'd replicate it.
ElevenLabs Gives Chat Agents a Voice
Luke Harries from ElevenLabs discusses the increasing importance of voice for AI chat agents, highlighting the benefits of speed, accessibility, and user experience.
RAG's Evolution: From Keywords to Agentic AI
Explore the evolution of Retrieval Augmented Generation (RAG) from basic keyword search to sophisticated agentic AI systems.
IBM Master Inventor on AI's Contextual Bottleneck
IBM Master Inventor Martin Keen discusses how context is the key bottleneck for AI models, outlining four pillars of context engineering: connected access, knowledge layer, precision retrieval, and runtime governance.
Claude's Corner: Compresr — The Token Accountant Your AI Stack Desperately Needs
Four EPFL researchers built a PhD-backed LLM context compression API that could cut your token bill by 10x — or get eaten alive by Anthropic. Here's the technical breakdown and how to build your own.
Databricks Activates Documents with AI Agents
Databricks introduces a multi-agent workflow using AI/BI Genie and Agent Bricks to automate document data extraction and activation.
AutoAdapt: Microsoft's LLM Adaptation Fix
Microsoft's AutoAdapt framework automates LLM domain adaptation, making it faster, cheaper, and more reliable for real-world applications.
IBM's Katie McDonald on AI: ADK vs. RAG
IBM's Katie McDonald explains the core differences between AI Agent Development Kits (ADK) and Retrieval Augmented Generation (RAG) and when to use each.
IBM's Dan Wiegand on AI and Mainframe Augmentation
IBM's Dan Wiegand discusses how AI, including RAG and agents, is transforming daily productivity and enhancing mainframe operations.
pgvector: Postgres's AI Vector Power-Up
pgvector brings vector embeddings and similarity search directly into PostgreSQL, simplifying AI apps like RAG and semantic search.
Cloudflare AI Search Simplifies Agent Development
Cloudflare AI Search offers a simplified, plug-and-play primitive for developers to integrate robust search capabilities into AI agents.
Databricks Powers Real-Time Search
Databricks unveils its platform for building real-time product search, integrating Vector Search, Lakeflow, and Lakebase for ingestion, retrieval, and operational data.
Databricks Touts Agentic Reasoning Gains
Databricks' Supervisor Agent enhances enterprise AI by integrating structured and unstructured data for complex reasoning tasks, showing significant performance gains.
IBM's Phil Nash Unveils Open-Source RAG Stack
IBM's Phil Nash introduces OpenRAG, an open-source RAG stack combining Docling, OpenSearch, and Langflow for flexible AI agent development.
WriteBack-RAG: Trainable Knowledge for RAG
WriteBack-RAG enables trainable RAG knowledge bases by distilling relevant facts into the corpus, boosting performance universally across RAG systems.
Chroma's Context-1: Faster, Cheaper AI Search
Chroma Context-1, a 20B parameter AI model, offers frontier-level search performance at a fraction of the cost and latency, using self-editing to manage context efficiently.
Exa Unveils New Code Search Benchmarks
Exa.ai releases 'WebCode', a new benchmark suite for evaluating search performance in coding agents, addressing limitations in existing tools.
Databricks Tackles Code Complexity for AI Assistants
Databricks details how AST-based chunking and MLflow evaluation improve AI assistants' understanding of complex codebases.
Mazda's GenAI Leap in Service Ops
Mazda built a governed GenAI assistant on Databricks Lakehouse in 8 weeks to improve technical service operations, integrating RAG and Unity Catalog.
Databricks Unlocks Billion-Scale Vector Search
Databricks unveils a redesigned vector search capable of handling billions of vectors, drastically cutting costs and improving scalability.
Cloudflare Adds Website Crawling API
Cloudflare launches a new /crawl endpoint for its Browser Rendering service, enabling automated website crawling via a single API call for developers.
IBM's Martin Keen on LLM Context Windows
IBM's Martin Keen explains how larger context windows in LLMs simplify deployments and improve reasoning by reducing reliance on complex RAG systems.
IBM Master Inventor Martin Keen on Agentic Storage
IBM Master Inventor Martin Keen explains 'Agentic Storage,' detailing how AI agents interact with diverse storage systems and the critical safety layers needed for responsible operation.
Databricks Reffy: From Tribal Data to AI Answers
Databricks' Reffy uses AI and RAG to turn scattered customer stories into an instantly searchable knowledge base for sales and marketing.
BeeAI Framework: Extending LLMs with Tools, RAG, & AI Agents
The BeeAI Framework: Orchestrating LLMs with Tools \n\n \n\n \"The landscape of AI is not just about building large language models, but also about making them ...
BeeAI Framework: Extending LLMs with Tools, RAG, & AI Agents
The BeeAI Framework: Orchestrating LLMs with Tools \n\n \n\n \"The landscape of AI is not just about building large language models, but also about making them ...