From 82d856a21dadd3b97859a75c80cb0332d9f9d08c Mon Sep 17 00:00:00 2001
From: ImBenji <benjamin.watt@imbenji.net>
Date: Thu, 16 Apr 2026 22:45:58 +0100
Subject: [PATCH] first commit

---
 README.md | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)
 create mode 100644 README.md

diff --git a/README.md b/README.md
new file mode 100644
index 0000000..0b1727a
--- /dev/null
+++ b/README.md
@@ -0,0 +1,33 @@
+# duriin_api
+
+Node.js Fastify server that ingests news articles from RSS, SEC EDGAR 8-K filings, Alpha Vantage News Sentiment, Finnhub company news, and GDELT into a local SQLite archive.
+
+## Setup
+
+1. Install dependencies:
+   ```bash
+   npm install
+   ```
+2. Edit `config.json` with your API keys, including `openRouter.apiKey`, tickers, RSS feeds, and schedules.
+3. Start the server:
+   ```bash
+   npm start
+   ```
+
+## API
+
+- `GET /articles?q=&source=&from=&to=&limit=&offset=`
+- `GET /articles?similar_to={id}&limit=`
+- `GET /articles?topic={query}&limit=`
+- `GET /articles/:id`
+- `GET /status`
+
+## Notes
+
+- SQLite archive file defaults to `./archive.sqlite`.
+- Deduplication is enforced on `url` and normalized title.
+- Article body extraction runs asynchronously after insertion, with hourly retries for rows still missing content.
+- Main article images are stored as ultra-compressed base64 WebP.
+- Embeddings are generated asynchronously with OpenRouter `perplexity/pplx-embed-v1-0.6b` and indexed in `sqlite-vec` for similarity search.
+- Topic search caches normalized query embeddings in SQLite and falls back to OpenRouter on cache miss.
+- SEC requests use the configured `User-Agent`.