» Tag
rag
29 postsPixelRAG: Retrieval-Augmented Generation Without Text Parsing
PixelRAG retrieves and reads web pages as screenshots instead of parsed text, outperforming text-based RAG across a 30-million-image Wikipedia datastore with notable efficiency gains.
Anatomy of a Full Self-Hosted RAG Stack, End to End
A self-hosted RAG pipeline in full: Docling parsing, dual dense/sparse indexing, RRF hybrid search, knowledge graphs, token budgeting, and parallel ingestion.
Amazon Bedrock Managed Knowledge Base: What Changes for Developers
AWS's Amazon Bedrock Managed Knowledge Base automates RAG ingestion, parsing, and retrieval — key quota limits and userContext security to know.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.compdfmuse: A Deterministic PDF Parser That Failed on Real Resumes
pdfmuse's deterministic PDF parser looked solid until real resumes exposed a silent 10% failure rate from unhandled form XObjects.
How RAG Hallucinations Poison Your Vector Database
A fintech RAG pipeline poisoned its own vector store via silent hallucinations; here's how deterministic validation fixed the problem.
Why PDF Ingestion, Not the LLM, Broke a Banking RAG Chatbot
How PDF extraction, broken tables, OCR, and chunking issues nearly derailed a production banking RAG chatbot pipeline.
Testing LLMs Like Software: A Promptfoo Deep Dive for QA
A production-level guide to testing LLM systems with Promptfoo: versioned evals, deterministic checks, judge-model bias, and provider benchmarking.
AI Agent Memory Is Just a Smarter Filing Cabinet
Today's AI agent 'memory' is retrieval in disguise—it can't tell if past answers were right. Real memory needs judgment that learns from outcomes.
Token Drift Explained: Why AI Agents Get Slower and Pricier
A breakdown of token drift in LLM agents: why session costs grow quadratically and how context budgets keep long-running agents efficient.
Study: Perplexity Grounds 'Best Software' Answers in 215,128 SEO Pages
Perplexity's sonar models cite 215,128 AI-generated 'best software' pages from a network built to be read by machines, not humans.