Browsing Tag
rag
42 posts
Build a Simple RAG App with Telnyx AI Inference
RAG is one of those patterns that sounds more complicated than it has to be. At its core,…
Your RAG faithfulness check is measuring copy-paste, not faithfulness
I was building an eval harness for a retrieval-augmented generation pipeline, and the first faithfulness check I wrote…
Two Pre-Registered Benchmarks for Audit-Native RAG: RAB (EU AI Act 10/12/19) + LRB (Time-Travel Retrieval)
Most RAG demos answer “what’s the right chunk?” Very few can answer the two questions a regulator or…
How I benchmarked a 100% local RAG pipeline to 9/9 (zero API keys)
Most “chat with your documents” demos work in an afternoon. Then you hit the last 20%: retrieval that…
Extract Plain Text from Medium Posts for RAG and Search Indexes
Chunk clean article content for embeddings, summarization, and full-text search—skip nav, clap bars, and scripts. Extract Plain Text…
Why output-stage PII masking is the wrong protective surface for data exfiltration in RAG
“The output filter runs after the LLM has already seen the confidential data. By then, three classes of…
How to Evaluate Vector Databases in 2026
In 2026, a synthetic performance crisis challenges the vector database market. A GitHub search for “vector database benchmark”…
Knowledge Base Software for B2B Support: Architecture, API Design, and AI Readiness
Most teams don’t struggle to choose a knowledge base. They struggle to choose the right one for how…
Parametric Hubris: Empirical Evidence That Tool Availability Does Not Equal Tool Usage in Frontier Language Models
Parametric Hubris: Empirical Evidence That Tool Availability Does Not Equal Tool Usage in Frontier Language Models Frontier large…
Teaching Machines to Understand Documents with Docling
Docling Exploration Introduction In this experiment I have explored the Docling CLI and used it to parse a…
