Tag

Embeddings

3 articles tagged with “Embeddings”

The Paralon capybara reading a glowing document through a magnifying glass, one line red among green ones

Sep 23, 20267 min read

Catch RAG Hallucinations Sentence by Sentence with an NLI Classifier: 74 Planted Errors, 93% Caught, $0.013

A RAG pipeline on one API key: embeddings for retrieval, a 27B chat model for the answer, and OpenJev over /v1/classify to check every sentence of the answer against the passages it came from. We planted 74 wrong sentences in 148 answers so recall is exact: 93.2% caught at a 0.7 threshold, 4.6% of clean sentences flagged, 49 seconds and 1.3 cents for 463 sentences. The 27B used as a judge caught the same 69 for 2.4× the money and 3× the time. Script included.

Read

The Paralon capybara feeding a stack of glowing cards onto a conveyor belt into a small machine

Guides & Tutorials

Sep 16, 20268 min read

Batch API for Open Models: Half-Price Chat, Embeddings and Responses Jobs with the OpenAI SDK

Paralon's Batch API takes a JSONL file of requests and returns a file of results, at 50% of the token price, through the same /v1/files and /v1/batches calls as OpenAI's. We ran it with the official Python SDK: 300 support tickets classified with zero failures, 100 embeddings and 20 Responses API drafts, billed at exactly half the live price, while live requests kept their normal latency.

Read

The Paralon capybara holding a magnifying lens up to a floating cloud of glowing connected dots

Guides & Tutorials

Sep 14, 202612 min read

Semantic Search with an Open Embeddings API: 990 Tickets, 5 Languages, and Where Keyword Search Still Wins

We indexed 990 support tickets with a 384-dimension open embedding model over an OpenAI-compatible /v1/embeddings endpoint and searched them 1,290 ways, scored against known intents and a TF-IDF keyword baseline. Same-language, keyword search was better. Across languages it collapsed to chance while embeddings held 47 to 58% precision. Adding a 27B reranker over the top ten lifted every language by 17 to 37 points for $0.09 per thousand queries. The whole index cost a tenth of a cent.

Read