How we moved from a fragile loop-based payout system to a reliable, idempotent, and traceable architecture. On paper, payouts sound simple: Customer places an order Platform collects payment Platform pays the seller That's it. Until you try to do it at scale. In any marketplace or fintech system, money flows across multiple parties: Sellers / vendors Delivery partners Platform fees Discounts, vouc
Fixed-length chunking requires no external services, yet semantic chunking absolutely needs an Embedding API — why? The core idea of semantic chunking is to split text at semantic boundaries. Determining whether "two pieces of text belong to the same topic" requires converting text into vectors and computing similarity — that's exactly what the Embedding API does. Dimension Fixed-Length / Recur
I still remember where i was when the email came in. December 25th. Christmas morning. Phone in hand while having breakfast, and there is an email from our client's CTO. No greetings, Just "We're terminating the contract. Our legal team will be in touch" We lost a 120K a year contract. On a Christmas morning because of a date calculation bug that none of us, not a person on a team of 5 experienced
Why Does Switching Embedding Models Make Such a Huge Difference? In the first four articles, we built the RAG pipeline, tuned parameters, and mastered chunking strategies. But there's one question we haven't dived into: After your documents are chunked, how do they become vectors? This process is called Embedding. It transforms human-readable text into machine-computable vectors. The choice of E