Content-similarity search surface over the CLIP index (closes #50)

Adds lib.mldata search over the CLIP index (#49): forFile returns a file's stored payload; similar ranks nearest files by cosine on the CLIP embedding; searchByEmbedding ranks the index against a caller-supplied query vector. All RAM-only, reusing the packed Float32Array index and id list. No text encoder is bundled — the caller provides the query embedding.

Model: opus-4-8

src/library/index.ts

@@ -41,6 +41,7 @@ import {
     type PhotosAPI,
     type TimelineAPI,
 } from "./read.js";
+import { makeMLDataAPI, type MLDataAPI } from "./mlsearch.js";
 
 export {
     Album,
@@ -52,6 +53,7 @@ export {
     type TimelineGroup,
     type GroupBy,
 } from "./read.js";
+export { type MLDataAPI, type SimilarResult } from "./mlsearch.js";
 import type { CollectionsPage, FilesPage } from "../client.js";
 import { MLDATA_BATCH_SIZE, type MLData } from "../mldata-fetch.js";
 import type { Collection, EnteFile } from "../model/types.js";
@@ -138,6 +140,10 @@ export class Library {
     readonly albums: AlbumsAPI;
     readonly photos: PhotosAPI;
     readonly timeline: TimelineAPI;
+    // The content-similarity search surface over the CLIP index (issue #50).
+    // Present whether or not ML fetching is enabled; with no ML store it
+    // returns empty results.
+    readonly mldata: MLDataAPI;
 
     private readonly client: LibraryClient;
     private readonly store: MetadataStore;
@@ -146,7 +152,7 @@ export class Library {
     private readonly onProgress?: RefreshProgressCallback;
     private readonly pools: RequestPools;
     // The ML-data cache, present only when the client can fetch ML data.
-    private readonly mldata?: MLDataStore;
+    private readonly mlStore?: MLDataStore;
 
     private timer?: ReturnType<typeof setTimeout>;
     private refreshing = false;
@@ -188,7 +194,7 @@ export class Library {
         this.intervalMs = args.intervalMs;
         this.onProgress = args.onProgress;
         this.pools = args.pools;
-        this.mldata = args.mldata;
+        this.mlStore = args.mldata;
         this.lastRecords = this.deriveNow();
 
         // The read namespaces derive fresh from the store on each call, so they
@@ -197,6 +203,8 @@ export class Library {
         this.albums = makeAlbumsAPI(derive);
         this.photos = makePhotosAPI(derive);
         this.timeline = makeTimelineAPI(derive);
+        // Reads the ML store live so results grow as ML data is fetched.
+        this.mldata = makeMLDataAPI(() => this.mlStore);
     }
 
     // Load the cache and start the refresh loop. With an empty cache the first
@@ -293,7 +301,7 @@ export class Library {
         for (const c of collections) {
             files += this.store.listFiles(c.id).length;
         }
-        const ml = this.mldata?.stats();
+        const ml = this.mlStore?.stats();
         return {
             userID: this.store.userID,
             collections: collections.length,
@@ -448,7 +456,7 @@ export class Library {
     // advanced), through the metadata pool, and update the CLIP index. Guarded
     // so passes never overlap; a failure is reported, not thrown.
     private async runMLFetch(): Promise<void> {
-        const mldata = this.mldata;
+        const mldata = this.mlStore;
         // Bind so the call keeps the client as its receiver when invoked
         // through the pool below.
         const fetchMLData = this.client.fetchMLData?.bind(this.client);