From 735ab367c4d7973d434d8a7f414d9d5f8faeb618 Mon Sep 17 00:00:00 2001 From: Cayman Roden Date: Mon, 16 Nov 2026 23:38:10 +0000 Subject: [PATCH] docs: state DocExtract is client work at the top of the README Co-Authored-By: Claude Opus 5.5 --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 11a471a..2b1ae74 100644 --- a/README.md +++ b/README.md @@ -1,5 +1,7 @@ # DocExtract: document extraction with an eval gate in CI +> **Client work.** I built DocExtract under a paid engagement for a client I can't name. This repository is the version I can share publicly. An authorized walkthrough is available on request. + DocExtract turns invoices, receipts, statements and other PDFs or scans into validated structured records you can search. Every pull request that touches prompts or the extractor re-scores a committed set of extraction outputs, and the check fails if the score falls below a floor or drops from baseline. This offline check scores frozen predictions; it does not rerun the extractor or detect prompt/model regressions. Those require a live evaluation. Under the hood: FastAPI, a two-pass Claude extraction pipeline, pgvector, and agentic RAG for questions over stored documents. @@ -201,8 +203,6 @@ The ADRs live in [docs/adr/](docs/adr/). The key ones: - There are two separate judges. The in-app judge (Gemini 2.5 Flash, Claude Haiku fallback) is off by default (`llm_judge_enabled = False` in `app/config.py`). The CI judge (`scripts/eval_llm_judge.py`) runs only in the paid live job, which skips without an API key, and uses its default provider (Anthropic) because the workflow passes no `--provider`. - The two-pass figures in [ADR-0003](docs/adr/0003-two-pass-extraction.md) (trigger rate, improvement, added latency) have no committed run artifact and are not cited as results here. -**Provenance:** built under a paid client engagement; an authorized walkthrough is available on request. - ## Roadmap