Tag: RAG
Posts with this tag
- TREC RAG 2026: When RAG Evaluation Becomes an Agent Workflow
A concise entry point to TREC RAG 2026, ClimbMix-400b, and RAGDoll, with a bridge to a technical guide for building a replayable enterprise RAG evaluation harness.
- TREC RAG 2026 Technical Deep Dive: From Evidence Lineage to a Replayable RAG Evaluation Harness
A practical design for an enterprise RAG evaluation harness based on TREC RAG 2026 and RAGDoll: data models, execution stages, citation support, agent traces, judge calibration, and production gates.
- Google Cloud Releases OKF v0.2: A Complete Breakdown of the Open Knowledge Format Upgrade for AI Agents
An in-depth comparative analysis of Google Cloud's Open Knowledge Format (OKF) v0.2 vs v0.1. Explore Attested Computation, provenance credibility signals, structured verified mappings, and staleness lifecycle controls designed to eliminate hallucinations in enterprise AI agents.
- Enterprise RAG Guide: Retrieval Architecture, Evaluation, and Production Delivery
A practical framework for enterprise RAG data pipelines, hybrid search, reranking, GraphRAG, agentic RAG, evaluation, access governance, failure diagnosis, and operations.
- LangChain OpenWiki: The Automated Code Documentation Manager Tailored for AI Agents
An in-depth exploration of LangChain's latest open-source tool, OpenWiki. From the underlying Git Diffs tracking mechanism to the brand-new 'OpenWiki Brains' proactive memory, comprehensively analyzing how to build an exclusive codebase documentation system that reduces Token consumption for AI Coding Agents.
- GraphRAG In-Depth Analysis: How to Build Smarter AI Retrieval Workflows Using Knowledge Graphs?
Explore the highlights of Cassie Shum's talk at QCon AI. Learn from the ground up how GraphRAG solves enterprise RAG pain points through Global Context, Multi-hop Reasoning, and Cypher queries, with practical architectural implementations.
- PixelRAG: Web Screenshots Beat Text Retrieval! An In-Depth Analysis of a Million-Pixel Native RAG System
Unpacking the PixelRAG system proposed by UC Berkeley and other institutions. An analysis of its custom Chromium rendering, GPU-accelerated preprocessing, LoRA dual-tower visual embedding, and Text Warmup training recipe. Also, learn how to implement it as a web visual reading skill for Claude Code.
- Google Cloud Launches Open Knowledge Format (OKF): An Open Standard for AI Agents to Understand Enterprise Knowledge
An in-depth analysis of the Open Knowledge Format (OKF) specification introduced by Google Cloud. Exploring how it standardizes the traditional LLM-wiki model, breaks down enterprise knowledge silos through concise Markdown, YAML frontmatter, and interconnected structures, and provides a portable, highly interoperable knowledge foundation for AI Agents.
- Parallel.ai Popular Science: Agent Harness is the Entire Lifecycle Beyond the Model
Deep dive into Parallel's long article: From intent capture, tool execution, context compilation to verification and persistence, clarifying the differences between Harness, orchestrator, and framework, and comparing with Anthropic / LangChain examples.
- Agentic RAG: When Vector Search Meets Agentic Reasoning
A summary of my core insights from the report 'RAG 2026: When Vector Search Meets Agentic Reasoning': why pure vector RAG gets stuck in context blindness, why the direction for 2026 is coarse vector filtering plus deep agentic reading, and how enterprises can implement a verifiable, governable hybrid architecture.
For speaking invitations, internal engineering sessions, or architecture exchange, see the topics and public work I can bring into the conversation.
Speaking & contact