@qvac/sdk 0.14.1 → 0.15.0

package/dist/examples/multi-model-demo.js

@@ -1,78 +1,78 @@
-import { completion, LLAMA_3_2_1B_INST_Q4_0, loadModel, QWEN3_1_7B_INST_Q4, unloadModel, } from "@qvac/sdk";
+import { completion, LLAMA_3_2_1B_INST_Q4_0, loadModel, QWEN3_1_7B_INST_Q4, unloadModel } from '@qvac/sdk';
 try {
     const alice = await loadModel({
         modelSrc: QWEN3_1_7B_INST_Q4,
         modelConfig: {
-            ctx_size: 4096,
-        },
+            ctx_size: 4096
+        }
     });
     const bob = await loadModel({
         modelSrc: LLAMA_3_2_1B_INST_Q4_0,
         modelConfig: {
-            ctx_size: 4096,
+            ctx_size: 4096
         },
         onProgress: (p) => {
             const mb = (n) => (n / 1e6).toFixed(1);
             const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
             process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
             if (p.percentage >= 100)
-                process.stderr.write("\n");
-        },
+                process.stderr.write('\n');
+        }
     });
     const aliceHistory = [
         {
-            role: "system",
-            content: "You answer questions about.",
+            role: 'system',
+            content: 'You answer questions about.'
         },
-        { role: "user", content: "What is Bitcoin?" },
+        { role: 'user', content: 'What is Bitcoin?' }
     ];
     const bobHistory = [
         {
-            role: "system",
-            content: "You ask questions about Bitcoin in one sentence.",
-        },
+            role: 'system',
+            content: 'You ask questions about Bitcoin in one sentence.'
+        }
     ];
-    console.log("Bob: ", "What is Bitcoin?");
+    console.log('Bob: ', 'What is Bitcoin?');
     const aliceResponse = completion({
         modelId: alice,
         history: [...aliceHistory],
-        stream: false,
+        stream: false
     });
     const aliceText = await aliceResponse.text;
-    aliceHistory.push({ role: "assistant", content: aliceText });
-    console.log("Alice: ", aliceText);
-    console.log("▸ Alice Stats: ", await aliceResponse.stats);
+    aliceHistory.push({ role: 'assistant', content: aliceText });
+    console.log('Alice: ', aliceText);
+    console.log('▸ Alice Stats: ', await aliceResponse.stats);
     const bobResponse = completion({
         modelId: bob,
-        history: [...bobHistory, { role: "user", content: aliceText }],
-        stream: false,
+        history: [...bobHistory, { role: 'user', content: aliceText }],
+        stream: false
     });
     const bobText = await bobResponse.text;
-    bobHistory.push({ role: "assistant", content: bobText });
-    console.log("Bob: ", bobText);
-    console.log("▸ Bob Stats: ", await bobResponse.stats);
+    bobHistory.push({ role: 'assistant', content: bobText });
+    console.log('Bob: ', bobText);
+    console.log('▸ Bob Stats: ', await bobResponse.stats);
     const aliceResponse2 = completion({
         modelId: alice,
-        history: [...aliceHistory, { role: "user", content: bobText }],
-        stream: false,
+        history: [...aliceHistory, { role: 'user', content: bobText }],
+        stream: false
     });
     const aliceText2 = await aliceResponse2.text;
-    aliceHistory.push({ role: "assistant", content: aliceText2 });
-    console.log("Alice: ", aliceText2);
-    console.log("▸ Alice Stats: ", await aliceResponse2.stats);
+    aliceHistory.push({ role: 'assistant', content: aliceText2 });
+    console.log('Alice: ', aliceText2);
+    console.log('▸ Alice Stats: ', await aliceResponse2.stats);
     const bobResponse2 = completion({
         modelId: bob,
-        history: [...bobHistory, { role: "user", content: aliceText2 }],
-        stream: false,
+        history: [...bobHistory, { role: 'user', content: aliceText2 }],
+        stream: false
     });
     const bobText2 = await bobResponse2.text;
-    bobHistory.push({ role: "assistant", content: bobText2 });
-    console.log("Bob: ", bobText2);
-    console.log("▸ Bob Stats: ", await bobResponse2.stats);
+    bobHistory.push({ role: 'assistant', content: bobText2 });
+    console.log('Bob: ', bobText2);
+    console.log('▸ Bob Stats: ', await bobResponse2.stats);
     await unloadModel({ modelId: alice, clearStorage: false });
     await unloadModel({ modelId: bob, clearStorage: false });
 }
 catch (error) {
-    console.error("✖", error);
+    console.error('✖', error);
     process.exit(1);
 }

package/dist/examples/ocr-fasttext.js

@@ -9,23 +9,23 @@
  * Pass a custom image path, or download the default image into examples/image/:
  *   https://github.com/tetherto/qvac/blob/main/packages/sdk/examples/image/basic_test.bmp
  */
-import { close, loadModel, ocr, OCR_LATIN, unloadModel, } from "@qvac/sdk";
-import path from "path";
-import { fileURLToPath } from "url";
+import { close, loadModel, ocr, OCR_LATIN, unloadModel } from '@qvac/sdk';
+import path from 'path';
+import { fileURLToPath } from 'url';
 const __dirname = path.dirname(fileURLToPath(import.meta.url));
-const imagePath = process.argv[2] || path.join(__dirname, "image/basic_test.bmp");
+const imagePath = process.argv[2] || path.join(__dirname, 'image/basic_test.bmp');
 try {
-    console.log("▸ Loading OCR model...");
+    console.log('▸ Loading OCR model...');
     const modelId = await loadModel({
         modelSrc: OCR_LATIN,
         modelConfig: {
-            langList: ["en"],
+            langList: ['en'],
             magRatio: 1.5,
             defaultRotationAngles: [90, 180, 270],
             contrastRetry: false,
             lowConfidenceThreshold: 0.5,
-            recognizerBatchSize: 1,
-        },
+            recognizerBatchSize: 1
+        }
     });
     console.log(`▸ Model loaded successfully! Model ID: ${modelId}`);
     console.log(`\n▸ Running OCR on: ${imagePath}`);
@@ -33,28 +33,28 @@ try {
         modelId,
         image: imagePath,
         options: {
-            paragraph: false,
-        },
+            paragraph: false
+        }
     });
     const result = await blocks;
-    console.log("\n▸ OCR Results:");
-    console.log("▸ ================================");
+    console.log('\n▸ OCR Results:');
+    console.log('▸ ================================');
     for (const block of result) {
         console.log(block.text);
         if (block.bbox) {
-            console.log(`▸ BBox: [${block.bbox.join(", ")}]`);
+            console.log(`▸ BBox: [${block.bbox.join(', ')}]`);
         }
         if (block.confidence !== undefined) {
             console.log(`▸ Confidence: ${block.confidence}`);
         }
     }
-    console.log("\n▸ ================================");
-    console.log("\n▸ Unloading model...");
+    console.log('\n▸ ================================');
+    console.log('\n▸ Unloading model...');
     await unloadModel({ modelId, clearStorage: false });
-    console.log("▸ Model unloaded successfully.");
+    console.log('▸ Model unloaded successfully.');
     process.exit(0);
 }
 catch (error) {
-    console.error("✖", error);
+    console.error('✖', error);
     await close();
 }

package/dist/examples/parallel-download.js

@@ -1,12 +1,12 @@
-import { LLAMA_3_2_1B_INST_Q4_0, WHISPER_TINY, VAD_SILERO_5_1_2, GTE_LARGE_FP16, downloadAsset, close, } from "@qvac/sdk";
+import { LLAMA_3_2_1B_INST_Q4_0, WHISPER_TINY, VAD_SILERO_5_1_2, GTE_LARGE_FP16, downloadAsset, close } from '@qvac/sdk';
 function now() {
     return Date.now();
 }
 const assets = [
-    { name: "Llama 3.2 1B", src: LLAMA_3_2_1B_INST_Q4_0 },
-    { name: "Whisper Tiny", src: WHISPER_TINY },
-    { name: "VAD Silero", src: VAD_SILERO_5_1_2 },
-    { name: "GTE Large FP16", src: GTE_LARGE_FP16 },
+    { name: 'Llama 3.2 1B', src: LLAMA_3_2_1B_INST_Q4_0 },
+    { name: 'Whisper Tiny', src: WHISPER_TINY },
+    { name: 'VAD Silero', src: VAD_SILERO_5_1_2 },
+    { name: 'GTE Large FP16', src: GTE_LARGE_FP16 }
 ];
 const timers = {};
 console.log(`\n▸ Parallel Download (${assets.length} assets)\n`);
@@ -26,7 +26,7 @@ try {
                     t.end = now();
                     console.log(`▸ [${asset.name}] done at ${((t.end - wallStart) / 1000).toFixed(1)}s`);
                 }
-            },
+            }
         });
     });
     const results = await Promise.allSettled(promises);
@@ -36,18 +36,16 @@ try {
         const asset = assets[i];
         const result = results[i];
         const t = timers[asset.name];
-        const status = result.status === "fulfilled" ? "OK" : "FAILED";
-        const reason = result.status === "rejected" ? ` — ${result.reason}` : "";
-        const timeToFirst = t.firstProgress != null
-            ? `${((t.firstProgress - t.start) / 1000).toFixed(1)}s`
-            : "N/A";
-        const total = t.end != null ? `${((t.end - t.start) / 1000).toFixed(1)}s` : "N/A";
+        const status = result.status === 'fulfilled' ? 'OK' : 'FAILED';
+        const reason = result.status === 'rejected' ? ` — ${result.reason}` : '';
+        const timeToFirst = t.firstProgress != null ? `${((t.firstProgress - t.start) / 1000).toFixed(1)}s` : 'N/A';
+        const total = t.end != null ? `${((t.end - t.start) / 1000).toFixed(1)}s` : 'N/A';
         console.log(`▸ ${status} ${asset.name}: first-progress=${timeToFirst}, total=${total}${reason}`);
     }
     console.log(`\n▸ Wall time: ${((wallEnd - wallStart) / 1000).toFixed(1)}s`);
     void close();
 }
 catch (error) {
-    console.error("✖", error);
+    console.error('✖', error);
     process.exit(1);
 }

package/dist/examples/plugins.js

@@ -10,27 +10,27 @@
  *   3. Embeddings        -> fails (plugin not selected)
  *
  */
-import { bundleSdk } from "../commands/index.js";
-import { existsSync, rmSync } from "fs";
-import path from "path";
+import { bundleSdk } from '../commands/index.js';
+import { existsSync, rmSync } from 'fs';
+import path from 'path';
 const configDir = import.meta.dirname ?? process.cwd();
 const configPath = `${configDir}/config/plugins/plugins.config.json`;
-const projectRoot = path.resolve(configDir, "..");
-const qvacOutputDir = path.join(projectRoot, "qvac");
+const projectRoot = path.resolve(configDir, '..');
+const qvacOutputDir = path.join(projectRoot, 'qvac');
 // ─── Generate the worker bundle from the plugins config ─────────────────────
 console.log(`▸ Config: ${configPath}`);
 console.log(`▸ This example will generate a worker bundle in ${qvacOutputDir} and delete it on exit.`);
-console.log("▸ If you have an existing qvac/ folder with bundled files, they will be overwritten and removed.\n");
-console.log("▸ Generating worker bundle from plugins config...\n");
+console.log('▸ If you have an existing qvac/ folder with bundled files, they will be overwritten and removed.\n');
+console.log('▸ Generating worker bundle from plugins config...\n');
 try {
     await bundleSdk({ projectRoot, configPath, quiet: true });
 }
 catch (error) {
-    console.error("✖ Failed to generate worker bundle.");
-    console.error("✖", error);
+    console.error('✖ Failed to generate worker bundle.');
+    console.error('✖', error);
     process.exit(1);
 }
-console.log("");
+console.log('');
 // Cleanup generated qvac/ folder on exit
 function cleanup() {
     if (existsSync(qvacOutputDir)) {
@@ -38,12 +38,12 @@ function cleanup() {
         console.log(`\n▸ Cleaned up ${qvacOutputDir}`);
     }
 }
-process.on("exit", cleanup);
+process.on('exit', cleanup);
 // Point config before importing the SDK.
 // In a real app, place qvac.config.json (or .js/.ts) in your project root (auto-discovered).
-process.env["QVAC_CONFIG_PATH"] = configPath;
-const { completion, translate, embed, loadModel, unloadModel, LLAMA_3_2_1B_INST_Q4_0, BERGAMOT_EN_ES, GTE_LARGE_FP16, } = await import("@qvac/sdk");
-console.log("▸ 1. LLM Completion (llamacpp-completion plugin)");
+process.env['QVAC_CONFIG_PATH'] = configPath;
+const { completion, translate, embed, loadModel, unloadModel, LLAMA_3_2_1B_INST_Q4_0, BERGAMOT_EN_ES, GTE_LARGE_FP16 } = await import('@qvac/sdk');
+console.log('▸ 1. LLM Completion (llamacpp-completion plugin)');
 try {
     const llmModelId = await loadModel({
         modelSrc: LLAMA_3_2_1B_INST_Q4_0,
@@ -53,82 +53,82 @@ try {
             const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
             process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
             if (p.percentage >= 100)
-                process.stderr.write("\n");
-        },
+                process.stderr.write('\n');
+        }
     });
     console.log(`▸ Model loaded: ${llmModelId}`);
-    const question = "What is 2 + 2? Answer in one word.";
+    const question = 'What is 2 + 2? Answer in one word.';
     console.log(`▸ Question: ${question}`);
     const result = completion({
         modelId: llmModelId,
-        history: [{ role: "user", content: question }],
-        stream: true,
+        history: [{ role: 'user', content: question }],
+        stream: true
     });
-    console.log("▸ Response:");
+    console.log('▸ Response:');
     for await (const token of result.tokenStream) {
         process.stdout.write(token);
     }
-    console.log("");
+    console.log('');
     await unloadModel({ modelId: llmModelId });
-    console.log("▸ LLM unloaded\n");
+    console.log('▸ LLM unloaded\n');
 }
 catch (error) {
-    console.error("✖ LLM failed:", error);
+    console.error('✖ LLM failed:', error);
     process.exit(1);
 }
-console.log("▸ 2. Translation (nmtcpp-translation plugin)");
+console.log('▸ 2. Translation (nmtcpp-translation plugin)');
 try {
     const nmtModelId = await loadModel({
         modelSrc: BERGAMOT_EN_ES,
         modelConfig: {
-            engine: "Bergamot",
-            from: "en",
-            to: "es",
+            engine: 'Bergamot',
+            from: 'en',
+            to: 'es'
         },
         onProgress: (p) => {
             const mb = (n) => (n / 1e6).toFixed(1);
             const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
             process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
             if (p.percentage >= 100)
-                process.stderr.write("\n");
-        },
+                process.stderr.write('\n');
+        }
     });
     console.log(`▸ Model loaded: ${nmtModelId}`);
-    const text = "Hello, how are you?";
+    const text = 'Hello, how are you?';
     const result = translate({
         modelId: nmtModelId,
         text,
-        modelType: "nmtcpp-translation",
-        stream: false,
+        modelType: 'nmtcpp-translation',
+        stream: false
     });
     const translated = await result.text;
     console.log(`"${text}" -> "${translated}"`);
     await unloadModel({ modelId: nmtModelId });
-    console.log("▸ NMT unloaded\n");
+    console.log('▸ NMT unloaded\n');
 }
 catch (error) {
-    console.error("✖ Translation failed:", error);
+    console.error('✖ Translation failed:', error);
     process.exit(1);
 }
-console.log("▸ 3. Embeddings (llamacpp-embedding plugin NOT in config)");
-console.log("▸ Attempting to load an embeddings model...\n");
+console.log('▸ 3. Embeddings (llamacpp-embedding plugin NOT in config)');
+console.log('▸ Attempting to load an embeddings model...\n');
 try {
     const embedModelId = await loadModel({
-        modelSrc: GTE_LARGE_FP16,
+        modelSrc: GTE_LARGE_FP16
     });
-    await embed({ modelId: embedModelId, text: "test" });
-    console.error("✖ Unexpected: embed succeeded without the plugin!");
+    await embed({ modelId: embedModelId, text: 'test' });
+    console.error('✖ Unexpected: embed succeeded without the plugin!');
     process.exit(1);
 }
 catch (error) {
     const message = error instanceof Error ? error.message : String(error);
-    if (message.includes("Plugin not found")) {
-        console.log("▸ Expected PLUGIN_NOT_FOUND error:");
+    if (message.includes('Plugin not found')) {
+        console.log('▸ Expected PLUGIN_NOT_FOUND error:');
         console.log(`▸ ${message}\n`);
     }
     else {
-        console.error("✖ Unexpected error:", error);
+        console.error('✖ Unexpected error:', error);
         process.exit(1);
     }
 }
-console.log("▸ Done! Only the selected plugins were available.");
+console.log('▸ Done! Only the selected plugins were available.');

package/dist/examples/profiling/basic.js

@@ -1,11 +1,11 @@
-import { completion, loadModel, unloadModel, LLAMA_3_2_1B_INST_Q4_0, profiler, } from "@qvac/sdk";
+import { completion, loadModel, unloadModel, LLAMA_3_2_1B_INST_Q4_0, profiler } from '@qvac/sdk';
 try {
     // Enable profiling globally
     profiler.enable({
-        mode: "verbose",
-        includeServerBreakdown: true,
+        mode: 'verbose',
+        includeServerBreakdown: true
     });
-    console.log("▸ Profiler enabled:", profiler.isEnabled());
+    console.log('▸ Profiler enabled:', profiler.isEnabled());
     const modelId = await loadModel({
         modelSrc: LLAMA_3_2_1B_INST_Q4_0,
         onProgress: (p) => {
@@ -13,15 +13,15 @@ try {
             const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
             process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
             if (p.percentage >= 100)
-                process.stderr.write("\n");
-        },
+                process.stderr.write('\n');
+        }
     });
-    console.log("▸ Model loaded:", modelId);
-    console.log("\n▸ Running completion...");
+    console.log('▸ Model loaded:', modelId);
+    console.log('\n▸ Running completion...');
     const result = completion({
         modelId,
-        history: [{ role: "user", content: "Say hello in one sentence." }],
-        stream: true,
+        history: [{ role: 'user', content: 'Say hello in one sentence.' }],
+        stream: true
     });
     for await (const token of result.tokenStream) {
         process.stdout.write(token);
@@ -29,50 +29,48 @@ try {
     console.log();
     await unloadModel({ modelId });
     // Export profiling data
-    console.log("\n▸ Profiler Summary");
+    console.log('\n▸ Profiler Summary');
     console.log(profiler.exportSummary());
-    console.log("\n▸ Profiler Table");
+    console.log('\n▸ Profiler Table');
     console.log(profiler.exportTable());
     const json = profiler.exportJSON();
-    console.log("\n▸ Load Model Metrics");
+    console.log('\n▸ Load Model Metrics');
     // Filter for operation-level event (kind: "handler"), not RPC phase events
-    const loadModelEvent = json.recentEvents?.find((e) => e.op === "loadModel" && e.kind === "handler");
+    const loadModelEvent = json.recentEvents?.find((e) => e.op === 'loadModel' && e.kind === 'handler');
     if (loadModelEvent) {
         const tags = loadModelEvent.tags ?? {};
         const gauges = loadModelEvent.gauges ?? {};
-        console.log("  sourceType:", tags["sourceType"] ?? "(not set)");
-        console.log("  cacheHit:", tags["cacheHit"] ?? "(not set)");
-        console.log("  totalLoadTime:", gauges["totalLoadTime"], "ms");
-        console.log("  modelInitializationTime:", gauges["modelInitializationTime"], "ms");
-        if (tags["cacheHit"] !== "true") {
-            console.log("  downloadTime:", gauges["downloadTime"] ?? "(cached)", "ms");
-            console.log("  totalBytesDownloaded:", gauges["totalBytesDownloaded"] ?? "(cached)");
-            console.log("  downloadSpeedBps:", gauges["downloadSpeedBps"] ?? "(cached)");
+        console.log('  sourceType:', tags['sourceType'] ?? '(not set)');
+        console.log('  cacheHit:', tags['cacheHit'] ?? '(not set)');
+        console.log('  totalLoadTime:', gauges['totalLoadTime'], 'ms');
+        console.log('  modelInitializationTime:', gauges['modelInitializationTime'], 'ms');
+        if (tags['cacheHit'] !== 'true') {
+            console.log('  downloadTime:', gauges['downloadTime'] ?? '(cached)', 'ms');
+            console.log('  totalBytesDownloaded:', gauges['totalBytesDownloaded'] ?? '(cached)');
+            console.log('  downloadSpeedBps:', gauges['downloadSpeedBps'] ?? '(cached)');
         }
         else {
-            console.log("  (download metrics omitted - cache hit)");
+            console.log('  (download metrics omitted - cache hit)');
         }
-        if (gauges["checksumValidationTime"] !== undefined) {
-            console.log("  checksumValidationTime:", gauges["checksumValidationTime"], "ms");
+        if (gauges['checksumValidationTime'] !== undefined) {
+            console.log('  checksumValidationTime:', gauges['checksumValidationTime'], 'ms');
         }
     }
     else {
-        console.log("  (no loadModel handler event captured)");
+        console.log('  (no loadModel handler event captured)');
         // Debug: show what ops are available
-        const ops = [
-            ...new Set(json.recentEvents?.map((e) => `${e.op}:${e.kind}`) ?? []),
-        ];
-        console.log("  Available ops:", ops.join(", "));
+        const ops = [...new Set(json.recentEvents?.map((e) => `${e.op}:${e.kind}`) ?? [])];
+        console.log('  Available ops:', ops.join(', '));
     }
-    console.log("\n▸ Profiler JSON (structure)");
-    console.log("  aggregates:", Object.keys(json.aggregates).length, "metrics");
-    console.log("  recentEvents:", json.recentEvents?.length ?? 0, "events");
-    console.log("  config:", json.config);
+    console.log('\n▸ Profiler JSON (structure)');
+    console.log('  aggregates:', Object.keys(json.aggregates).length, 'metrics');
+    console.log('  recentEvents:', json.recentEvents?.length ?? 0, 'events');
+    console.log('  config:', json.config);
     // Disable profiling
     profiler.disable();
-    console.log("\n▸ Profiler disabled:", !profiler.isEnabled());
+    console.log('\n▸ Profiler disabled:', !profiler.isEnabled());
 }
 catch (error) {
-    console.error("✖", error);
+    console.error('✖', error);
     process.exit(1);
 }

package/dist/examples/profiling/per-call.js

@@ -1,7 +1,7 @@
-import { embed, loadModel, unloadModel, GTE_LARGE_FP16, profiler, } from "@qvac/sdk";
+import { embed, loadModel, unloadModel, GTE_LARGE_FP16, profiler } from '@qvac/sdk';
 try {
     profiler.disable();
-    console.log("▸ Profiler globally enabled:", profiler.isEnabled());
+    console.log('▸ Profiler globally enabled:', profiler.isEnabled());
     const modelId = await loadModel({
         modelSrc: GTE_LARGE_FP16,
         onProgress: (p) => {
@@ -9,27 +9,27 @@ try {
             const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
             process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
             if (p.percentage >= 100)
-                process.stderr.write("\n");
-        },
+                process.stderr.write('\n');
+        }
     });
-    console.log("▸ Model loaded:", modelId);
-    console.log("\n▸ Embed with per-call profiling");
-    const { embedding: embedding1 } = await embed({ modelId, text: "Profile this specific call" }, { profiling: { enabled: true, includeServerBreakdown: true } });
-    console.log("▸ Embedding dimensions:", embedding1.length);
-    console.log("\n▸ Embed without profiling");
+    console.log('▸ Model loaded:', modelId);
+    console.log('\n▸ Embed with per-call profiling');
+    const { embedding: embedding1 } = await embed({ modelId, text: 'Profile this specific call' }, { profiling: { enabled: true, includeServerBreakdown: true } });
+    console.log('▸ Embedding dimensions:', embedding1.length);
+    console.log('\n▸ Embed without profiling');
     const { embedding: embedding2 } = await embed({
         modelId,
-        text: "This call is not profiled",
+        text: 'This call is not profiled'
     });
-    console.log("▸ Embedding dimensions:", embedding2.length);
-    console.log("\n▸ Embed with profiling explicitly disabled");
-    const { embedding: embedding3 } = await embed({ modelId, text: "Profiling explicitly disabled for this call" }, { profiling: { enabled: false } });
-    console.log("▸ Embedding dimensions:", embedding3.length);
+    console.log('▸ Embedding dimensions:', embedding2.length);
+    console.log('\n▸ Embed with profiling explicitly disabled');
+    const { embedding: embedding3 } = await embed({ modelId, text: 'Profiling explicitly disabled for this call' }, { profiling: { enabled: false } });
+    console.log('▸ Embedding dimensions:', embedding3.length);
     await unloadModel({ modelId });
-    console.log("\n▸ Profiler Summary (per-call data only)");
+    console.log('\n▸ Profiler Summary (per-call data only)');
     console.log(profiler.exportSummary());
 }
 catch (error) {
-    console.error("✖", error);
+    console.error('✖', error);
     process.exit(1);
 }

package/dist/examples/quickstart.bare.js

@@ -1,16 +1,14 @@
 // The Bare quickstart. Bare has no `process` global and does not spawn a worker,
 // so two setup steps come first: install bare-process as the `process` global,
 // then register the plugins this example uses via `plugins([...])`.
-import bareProcess from "bare-process";
-import { plugins, LLAMA_3_2_1B_INST_Q4_0 } from "@qvac/sdk";
-import { llmPlugin } from "@qvac/sdk/llamacpp-completion/plugin.js";
+import bareProcess from 'bare-process';
+import { plugins, LLAMA_3_2_1B_INST_Q4_0 } from '@qvac/sdk';
+import { llmPlugin } from '@qvac/sdk/llamacpp-completion/plugin.js';
 globalThis.process = bareProcess;
 const { loadModel, completion, unloadModel } = plugins([llmPlugin]);
 // From here it is the same as the Node quickstart.
 const modelId = await loadModel({ modelSrc: LLAMA_3_2_1B_INST_Q4_0 });
-const history = [
-    { role: "user", content: "Explain quantum computing in one sentence" },
-];
+const history = [{ role: 'user', content: 'Explain quantum computing in one sentence' }];
 const result = completion({ modelId, history, stream: true });
 for await (const token of result.tokenStream) {
     process.stdout.write(token);

package/dist/examples/quickstart.js

@@ -1,7 +1,7 @@
 // The SDK prints no logs by default. To see its client and server logs, run with
 // QVAC_CONFIG_PATH pointing at a config that sets "loggerConsoleOutput": true
 // (see the Quickstart docs).
-import { loadModel, LLAMA_3_2_1B_INST_Q4_0, completion, unloadModel, } from "@qvac/sdk";
+import { loadModel, LLAMA_3_2_1B_INST_Q4_0, completion, unloadModel } from '@qvac/sdk';
 try {
     // Load a model into memory
     const modelId = await loadModel({
@@ -11,15 +11,15 @@ try {
             const line = `▸ Downloading ${p.percentage.toFixed(0)}% (${mb(p.downloaded)}/${mb(p.total)} MB)`;
             process.stderr.write(process.stderr.isTTY ? `\r${line}` : `${line}\n`);
             if (p.percentage >= 100)
-                process.stderr.write("\n");
-        },
+                process.stderr.write('\n');
+        }
     });
     // You can use the loaded model multiple times
     const history = [
         {
-            role: "user",
-            content: "Explain quantum computing in one sentence",
-        },
+            role: 'user',
+            content: 'Explain quantum computing in one sentence'
+        }
     ];
     const result = completion({ modelId, history, stream: true });
     for await (const token of result.tokenStream) {
@@ -29,6 +29,6 @@ try {
     await unloadModel({ modelId });
 }
 catch (error) {
-    console.error("✖", error);
+    console.error('✖', error);
     process.exit(1);
 }