qwen-embedder 0.1.1 → 0.1.2

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "qwen-embedder",
-  "version": "0.1.1",
+  "version": "0.1.2",
   "description": "Local text embedding with Qwen ONNX model via Transformers.js",
   "type": "module",
   "main": "./dist/index.js",

package/src/embedder.ts

@@ -78,7 +78,8 @@ export class Embedder {
     }
 
     const results: (number[] | undefined)[] = new Array(texts.length)
-    const uncached: number[] = []
+    const uncachedByText = new Map<string, number[]>()
+    const uncachedTexts: string[] = []
 
     for (let i = 0; i < texts.length; i++) {
       const t = texts[i]
@@ -87,23 +88,33 @@ export class Embedder {
       }
       const cached = this.cache.get(t)
       if (cached !== undefined) {
-        results[i] = cached
+        results[i] = cached.slice()
       } else {
-        uncached.push(i)
+        const existing = uncachedByText.get(t)
+        if (existing !== undefined) {
+          existing.push(i)
+        } else {
+          uncachedByText.set(t, [i])
+          uncachedTexts.push(t)
+        }
       }
     }
 
-    if (uncached.length === 0) {
+    if (uncachedTexts.length === 0) {
       return results as number[][]
     }
 
-    const uncachedTexts = uncached.map(i => texts[i])
     const inferred = await this.runInference(uncachedTexts)
 
-    for (let j = 0; j < uncached.length; j++) {
+    for (let j = 0; j < uncachedTexts.length; j++) {
+      const text = uncachedTexts[j]
       const vector = inferred[j]
-      this.setCache(uncachedTexts[j], vector)
-      results[uncached[j]] = vector
+      const stored = vector.slice()
+      this.setCache(text, stored)
+      const positions = uncachedByText.get(text) ?? []
+      for (const position of positions) {
+        results[position] = stored.slice()
+      }
     }
 
     return results as number[][]
@@ -135,12 +146,13 @@ export class Embedder {
   private setCache(key: string, value: number[]): void {
     if (this.maxCacheSize === 0) return
 
+    const stored = value.slice()
     if (this.cache.size >= this.maxCacheSize) {
       const oldest = this.cache.keys().next()
       if (!oldest.done) {
         this.cache.delete(oldest.value)
       }
     }
-    this.cache.set(key, value)
+    this.cache.set(key, stored)
   }
 }