A file's JSON holds keywords in place of its CLIP embedding (closes #218)

quak backup and quak backup-metadata write each file's ML data without its
CLIP embedding, and keywords in its place: the titles of the Discover
categories of Ente's photos app that the file falls in, by the app's rule.
src/clip-keywords.ts applies the rule. src/clip-keyword-vectors.ts holds the
16 categories from Ente's discover.json with the text embedding Ente's CLIP
text model gives each query. bin/clip-keyword-vectors writes that file and the
test fixture in a digest-pinned Python image, with every download pinned by
sha256; it runs by hand only. quak gains no dependency.

Model: opus-5-5

src/clip-keywords.ts

@@ -0,0 +1,59 @@
+// Keywords for a file from its CLIP embedding.
+//
+// Ente stores no keywords. A file's ML data holds a CLIP embedding, the 512
+// numbers Ente's image model gave the photo, and Ente's photos app sorts files
+// into the categories of its Discover section with it: a file falls in a
+// category when the cosine similarity of its CLIP embedding and the text
+// embedding of the category's query is at least the category's `minScore`,
+// unless the file is a video and the category leaves out videos. A file's
+// keywords are the titles of the categories it falls in. The categories and
+// their text embeddings are in `clip-keyword-vectors.ts`.
+
+import { DISCOVER_CATEGORIES } from "./clip-keyword-vectors.js";
+import type { MLData } from "./mldata-fetch.js";
+
+// How many numbers a CLIP embedding from Ente's image model has.
+const EMBEDDING_LENGTH = 512;
+
+const length = (vector: number[]): number => Math.hypot(...vector);
+
+const cosineSimilarity = (a: number[], b: number[]): number => {
+    let dot = 0;
+    a.forEach((value, i) => {
+        dot += value * (b[i] ?? 0);
+    });
+    return dot / (length(a) * length(b));
+};
+
+// The titles of the Discover categories a file falls in, highest score first,
+// or undefined when its ML data has no CLIP embedding of 512 finite numbers
+// that are not all zero. Tests pass their own `categories`.
+export const clipKeywords = (
+    mlData: MLData,
+    isVideo: boolean,
+    categories = DISCOVER_CATEGORIES,
+): string[] | undefined => {
+    const clip = mlData.clip;
+    if (typeof clip !== "object" || clip === null) return undefined;
+    const embedding = (clip as { embedding?: unknown }).embedding;
+    if (
+        !Array.isArray(embedding) ||
+        embedding.length !== EMBEDDING_LENGTH ||
+        !embedding.every((v) => typeof v === "number" && Number.isFinite(v)) ||
+        length(embedding) === 0
+    ) {
+        return undefined;
+    }
+
+    const matches: { title: string; score: number }[] = [];
+    for (const category of categories) {
+        if (isVideo && !category.showVideo) continue;
+        const score = cosineSimilarity(embedding, category.textEmbedding);
+        if (score >= category.minScore) {
+            matches.push({ title: category.title, score });
+        }
+    }
+    return matches
+        .sort((a, b) => b.score - a.score)
+        .map((match) => match.title);
+};