From 3e39d3bbd527982dc482359046f208081f9d6f60 Mon Sep 17 00:00:00 2001
From: Shinwoo PARK <shinwoo.park@psw.kr>
Date: Mon, 11 May 2026 12:19:58 +0900
Subject: [PATCH] docs: document LLM extractor adapter usage

---
 README.md | 23 +++++++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/README.md b/README.md
index 092a073..a9188ef 100644
--- a/README.md
+++ b/README.md
@@ -113,6 +113,29 @@ await db.ingestStatement('Bun makes TypeScript tooling fast.', {
 });
 ```
 
+## LLM-backed extraction
+
+You can bridge any text-generating model into IdentityDB by wrapping it with `LlmFactExtractor`.
+
+```ts
+import { LlmFactExtractor } from 'identitydb';
+
+const extractor = new LlmFactExtractor({
+  model: {
+    async generateText(prompt) {
+      return callYourFavoriteLlm(prompt);
+    },
+  },
+  instructions: 'Prefer technology, product, and time topics over generic nouns.',
+});
+
+await db.ingestStatement('I have worked with Bun and TypeScript since 2025.', {
+  extractor,
+});
+```
+
+The adapter expects the model to return JSON and will validate the structured response before IdentityDB writes a fact.
+
 ## Development
 
 ```bash