» Tag
ocr
8 postsWhy 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.
Cutting Claude API Costs 84% by Separating Vision and Reasoning
An OCR pipeline routed page images to Haiku and reasoning to Sonnet instead of Opus, cutting Claude API costs by 84%. Includes the model-routing math and a real JSON parsing bug.
Teaching AI to Read Compliance Papers, Not to Decide
A two-stage AI pipeline reads SMS compliance documents field by field, while a deterministic rule engine — never the model — makes every approve, reject or review decision.
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.comXberg v1 Released: Advanced Content Intelligence Framework
Xberg v1 is a new version of the content intelligence framework handling various data types.
What 1,000 Invoices a Month Really Cost: Five Document-AI APIs
A side-by-side look at AWS, Google, Azure, LlamaParse and Veryfi pricing pages reveals hidden minimums and failed-attempt billing behind the real cost of 1,000 invoices a month.
Evals Before Prompts: Building an LLM OCR for KYC
Exploring LLMs for KYC document verification, achieving 92% accuracy and cost reduction.
Creating a Bulk Business Card Registration Feature with OCR
Explore the development of an OCR feature for automatic registration of business cards.
Searchable Map of NYC Grocery Chains' Weekly Circulars
Explore a searchable map of weekly circulars from NYC grocery stores. Quickly find advertised products nearby.