Test keywords in place of the CLIP embedding in a file's JSON

clipKeywords takes a file's ML data and whether it is a video, and gives the
titles of the Discover categories of Ente's photos app that its CLIP embedding
falls in, highest score first. The tests cover the rule with made-up vectors
and Ente's real categories with the CLIP embedding of a public-domain photo of
a sunset. The backup and backup-metadata tests now expect keywords in a file's
JSON and no CLIP embedding in its mlData. These tests fail until the
implementation lands.

Model: opus-5-5

test/cli/backup-end-to-end.test.ts

@@ -86,10 +86,17 @@ const DAY = "2024/2024-03/2024-03-01";
 const TOAST = new TextEncoder().encode("a few seconds of the wedding toast");
 
 // Ente's ML data for beach.jpg: a face it found, and the photo's CLIP
-// embedding.
+// embedding, here that of a photo of a sunset (see clip-keywords.test.ts).
 const ML_DATA = {
     face: { faces: [{ faceID: "100_1", score: 0.98 }] },
-    clip: { embedding: [0.5, 0.6, 0.7] },
+    clip: {
+        embedding: JSON.parse(
+            readFileSync(
+                new URL("../clip-keywords-sunset.json", import.meta.url),
+                "utf-8",
+            ),
+        ).embedding,
+    },
 };
 
 // Each file's ID, its owner, its original as uploaded, and the metadata its
@@ -486,7 +493,10 @@ describe("the first backup of the account", () => {
             },
             updationTime: TAKEN,
         });
-        expect(beach.mlData).toEqual(ML_DATA);
+        // The JSON holds the ML data without its CLIP embedding, and the
+        // keywords the embedding gives in its place.
+        expect(beach.mlData).toEqual({ face: ML_DATA.face });
+        expect(beach.keywords).toEqual(["Sunset"]);
         expect(beach.imageMetadata.exif.Make.description).toBe("Canon");
         expect(beach.imageMetadata.exif.Model.description).toBe("EOS R5");
 
@@ -497,6 +507,7 @@ describe("the first backup of the account", () => {
             metadata: { title: "toast.mp4", fileType: "video" },
         });
         expect(toast).not.toHaveProperty("mlData");
+        expect(toast).not.toHaveProperty("keywords");
         expect(toast).not.toHaveProperty("imageMetadata");
         expect(toast).not.toHaveProperty("imageMetadataError");
 

test/cli/backup.test.ts

@@ -946,9 +946,19 @@ describe("the backup lock", () => {
     });
 });
 
-// Also serves ML data: file 100 has `ML_PAYLOAD`, the other two have none.
-// While `mlError` is set, every ML data request fails with it.
-const ML_PAYLOAD = { face: { faces: [] }, clip: { embedding: [0.5, 0.25] } };
+// Also serves ML data: file 100 has `ML_PAYLOAD`, whose CLIP embedding is that
+// of a photo of a sunset (see clip-keywords.test.ts), and the other two have
+// none. While `mlError` is set, every ML data request fails with it.
+const SUNSET_EMBEDDING: number[] = JSON.parse(
+    readFileSync(
+        new URL("../clip-keywords-sunset.json", import.meta.url),
+        "utf-8",
+    ),
+).embedding;
+const ML_PAYLOAD = {
+    face: { faces: [] },
+    clip: { embedding: SUNSET_EMBEDDING },
+};
 
 class MLClient extends MockClient {
     mlError?: string;
@@ -968,16 +978,20 @@ const fileJSON = (outDir: string, fileID: number): Record<string, unknown> =>
     JSON.parse(readFileSync(saved(outDir, `${fileID}.json`), "utf-8"));
 
 describe("ML data in each file's JSON", () => {
-    it("writes a file's ML data, and no ML field for a file that has none", async () => {
+    // The JSON holds the ML data without its CLIP embedding, and in its place
+    // the keywords the embedding gives.
+    it("writes a file's ML data and keywords, and no ML field for a file that has none", async () => {
         const lib = await openLibrary(stubSource(), new MLClient());
         const outDir = join(root, "backup");
 
         const result = await lib.backup({ downloadDirectory: outDir });
 
         expect(result.failed).toBe(0);
-        expect(fileJSON(outDir, 100).mlData).toEqual(ML_PAYLOAD);
+        expect(fileJSON(outDir, 100).mlData).toEqual({ face: { faces: [] } });
+        expect(fileJSON(outDir, 100).keywords).toEqual(["Sunset"]);
         expect(fileJSON(outDir, 101)).not.toHaveProperty("mlData");
         expect(fileJSON(outDir, 101)).not.toHaveProperty("mlDataError");
+        expect(fileJSON(outDir, 101)).not.toHaveProperty("keywords");
         await lib.close();
     });
 
@@ -993,7 +1007,7 @@ describe("ML data in each file's JSON", () => {
         const result = await lib.backup({ downloadDirectory: outDir });
 
         // File 100's ML data was cached by the first run and is kept.
-        expect(fileJSON(outDir, 100).mlData).toEqual(ML_PAYLOAD);
+        expect(fileJSON(outDir, 100).mlData).toEqual({ face: { faces: [] } });
         expect(fileJSON(outDir, 100)).not.toHaveProperty("mlDataError");
         for (const fileID of [101, 200]) {
             expect(fileJSON(outDir, fileID).mlDataError).toBe(
@@ -1026,7 +1040,7 @@ describe("ML data in each file's JSON", () => {
 
         expect(result.failed).toBe(0);
         expect(result.skipped).toBe(3);
-        expect(fileJSON(outDir, 100).mlData).toEqual(ML_PAYLOAD);
+        expect(fileJSON(outDir, 100).mlData).toEqual({ face: { faces: [] } });
         for (const fileID of [100, 101, 200]) {
             expect(fileJSON(outDir, fileID)).not.toHaveProperty("mlDataError");
         }

test/cli/metadata-backup.test.ts

@@ -66,6 +66,15 @@ vi.mock("../../src/mldata-fetch.js", async (importOriginal) => ({
 const TEST_EMAIL = "metabackup@example.com";
 const TEST_PASSWORD = "metapass";
 
+// The CLIP embedding of a photo of a sunset (see clip-keywords.test.ts), which
+// the ML data of beach.jpg holds.
+const SUNSET_EMBEDDING: number[] = JSON.parse(
+    readFileSync(
+        new URL("../clip-keywords-sunset.json", import.meta.url),
+        "utf-8",
+    ),
+).embedding;
+
 let mock: MetaMockState;
 let testDir: string;
 
@@ -230,7 +239,7 @@ const buildMetaMock = async (): Promise<MetaMockState> => {
         clip: {
             version: 1,
             client: "test",
-            embedding: [0.5, 0.6, 0.7],
+            embedding: SUNSET_EMBEDDING,
         },
     });
     const gzipped = gzipSync(Buffer.from(mlPayload));
@@ -432,7 +441,9 @@ describe("quak backup-metadata", () => {
         expect(account.email).toBe(TEST_EMAIL);
     });
 
-    it("fetches and decrypts ML data by default", async () => {
+    // The CLIP embedding is left out of the ML data, and the keywords it gives
+    // are written in its place.
+    it("fetches and decrypts ML data by default, with keywords for the CLIP embedding", async () => {
         const outDir = join(testDir, "ml-data");
         await runBackup(outDir);
 
@@ -452,8 +463,8 @@ describe("quak backup-metadata", () => {
         expect(fileMeta.mlData.face.faces[0].faceID).toBe("face-abc");
         expect(fileMeta.mlData.face.faces[0].score).toBeCloseTo(0.98);
         expect(fileMeta.mlData.face.faces[0].detection.box.x).toBeCloseTo(0.1);
-        expect(fileMeta.mlData.clip).toBeDefined();
-        expect(fileMeta.mlData.clip.embedding).toEqual([0.5, 0.6, 0.7]);
+        expect(fileMeta.mlData).not.toHaveProperty("clip");
+        expect(fileMeta.keywords).toEqual(["Sunset"]);
     });
 
     it("extracts EXIF from downloaded files when --exif is set", async () => {
@@ -541,7 +552,7 @@ describe("quak backup-metadata when a file's ML data cannot be read", () => {
                 "utf-8",
             ),
         );
-        expect(ok.mlData.clip.embedding).toEqual([0.5, 0.6, 0.7]);
+        expect(ok.keywords).toEqual(["Sunset"]);
         expect(ok.mlDataError).toBeUndefined();
 
         const failed = JSON.parse(
@@ -599,7 +610,7 @@ describe("quak backup-metadata when a file's ML data cannot be read", () => {
                 "utf-8",
             ),
         );
-        expect(ok.mlData.clip.embedding).toEqual([0.5, 0.6, 0.7]);
+        expect(ok.keywords).toEqual(["Sunset"]);
     });
 
     it("exits 0 when every ML data request succeeds", async () => {