@qvac/sdk 0.13.4 → 0.14.0

package/dist/examples/ocr-fasttext.js

@@ -9,19 +9,17 @@
  * 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_RECOGNIZER_1, unloadModel, } from "@qvac/sdk";
+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");
 try {
-    console.log("🚀 Loading OCR model...");
+    console.log("▸ Loading OCR model...");
     const modelId = await loadModel({
-        modelSrc: OCR_LATIN_RECOGNIZER_1,
+        modelSrc: OCR_LATIN,
         modelConfig: {
             langList: ["en"],
-            useGPU: true,
-            timeout: 30000,
             magRatio: 1.5,
             defaultRotationAngles: [90, 180, 270],
             contrastRetry: false,
@@ -29,8 +27,8 @@ try {
             recognizerBatchSize: 1,
         },
     });
-    console.log(`✅ Model loaded successfully! Model ID: ${modelId}`);
-    console.log(`\n🔍 Running OCR on: ${imagePath}`);
+    console.log(`▸ Model loaded successfully! Model ID: ${modelId}`);
+    console.log(`\n▸ Running OCR on: ${imagePath}`);
     const { blocks } = ocr({
         modelId,
         image: imagePath,
@@ -39,24 +37,24 @@ try {
         },
     });
     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(`\n📄 Text: ${block.text}`);
+        console.log(block.text);
         if (block.bbox) {
-            console.log(`   📍 BBox: [${block.bbox.join(", ")}]`);
+            console.log(`▸ BBox: [${block.bbox.join(", ")}]`);
         }
         if (block.confidence !== undefined) {
-            console.log(`   ✓ Confidence: ${block.confidence}`);
+            console.log(`▸ 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 during OCR processing:", error);
+    console.error("✖", error);
     await close();
 }

package/dist/examples/parallel-download.js

@@ -9,7 +9,7 @@ const assets = [
     { name: "GTE Large FP16", src: GTE_LARGE_FP16 },
 ];
 const timers = {};
-console.log(`\n=== Parallel Download (${assets.length} assets) ===\n`);
+console.log(`\n▸ Parallel Download (${assets.length} assets)\n`);
 const wallStart = now();
 try {
     const promises = assets.map((asset) => {
@@ -20,18 +20,18 @@ try {
                 const t = timers[asset.name];
                 if (t.firstProgress == null) {
                     t.firstProgress = now();
-                    console.log(`[${asset.name}] first progress at ${((t.firstProgress - wallStart) / 1000).toFixed(1)}s — ${progress.percentage}%`);
+                    console.log(`▸ [${asset.name}] first progress at ${((t.firstProgress - wallStart) / 1000).toFixed(1)}s — ${progress.percentage}%`);
                 }
                 if (progress.percentage === 100 && t.end == null) {
                     t.end = now();
-                    console.log(`[${asset.name}] done at ${((t.end - wallStart) / 1000).toFixed(1)}s`);
+                    console.log(`▸ [${asset.name}] done at ${((t.end - wallStart) / 1000).toFixed(1)}s`);
                 }
             },
         });
     });
     const results = await Promise.allSettled(promises);
     const wallEnd = now();
-    console.log(`\n=== Results ===\n`);
+    console.log(`\n▸ Results\n`);
     for (let i = 0; i < assets.length; i++) {
         const asset = assets[i];
         const result = results[i];
@@ -42,12 +42,12 @@ try {
             ? `${((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(`▸ ${status} ${asset.name}: first-progress=${timeToFirst}, total=${total}${reason}`);
     }
-    console.log(`\nWall time: ${((wallEnd - wallStart) / 1000).toFixed(1)}s`);
+    console.log(`\n▸ Wall time: ${((wallEnd - wallStart) / 1000).toFixed(1)}s`);
     void close();
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/plugins.js

@@ -18,16 +18,16 @@ const configPath = `${configDir}/config/plugins/plugins.config.json`;
 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(`▸ 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");
 try {
     await bundleSdk({ projectRoot, configPath, quiet: true });
 }
 catch (error) {
-    console.error("❌ Failed to generate worker bundle.");
-    console.error("❌ Error:", error);
+    console.error("✖ Failed to generate worker bundle.");
+    console.error("✖", error);
     process.exit(1);
 }
 console.log("");
@@ -35,7 +35,7 @@ console.log("");
 function cleanup() {
     if (existsSync(qvacOutputDir)) {
         rmSync(qvacOutputDir, { recursive: true, force: true });
-        console.log(`\n🧹 Cleaned up ${qvacOutputDir}`);
+        console.log(`\n▸ Cleaned up ${qvacOutputDir}`);
     }
 }
 process.on("exit", cleanup);
@@ -43,34 +43,40 @@ process.on("exit", cleanup);
 // 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)");
+console.log("▸ 1. LLM Completion (llamacpp-completion plugin)");
 try {
     const llmModelId = await loadModel({
         modelSrc: LLAMA_3_2_1B_INST_Q4_0,
         modelConfig: { ctx_size: 2048 },
-        onProgress: (p) => console.log(`   Loading LLM: ${p.percentage.toFixed(1)}%`),
+        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");
+        },
     });
-    console.log(`   Model loaded: ${llmModelId}`);
+    console.log(`▸ Model loaded: ${llmModelId}`);
     const question = "What is 2 + 2? Answer in one word.";
-    console.log(`   Question: ${question}`);
+    console.log(`▸ Question: ${question}`);
     const result = completion({
         modelId: llmModelId,
         history: [{ role: "user", content: question }],
         stream: true,
     });
-    process.stdout.write("   Response: ");
+    console.log("▸ Response:");
     for await (const token of result.tokenStream) {
         process.stdout.write(token);
     }
-    console.log("\n");
+    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,
@@ -79,9 +85,15 @@ try {
             from: "en",
             to: "es",
         },
-        onProgress: (p) => console.log(`   Loading NMT: ${p.percentage.toFixed(1)}%`),
+        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");
+        },
     });
-    console.log(`   Model loaded: ${nmtModelId}`);
+    console.log(`▸ Model loaded: ${nmtModelId}`);
     const text = "Hello, how are you?";
     const result = translate({
         modelId: nmtModelId,
@@ -90,33 +102,33 @@ try {
         stream: false,
     });
     const translated = await result.text;
-    console.log(`   "${text}" -> "${translated}"\n`);
+    console.log(`"${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,
     });
     await embed({ modelId: embedModelId, text: "test" });
-    console.error("   ❌ Unexpected: embed succeeded without the plugin!");
+    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:");
-        console.log(`   ${message}\n`);
+        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

@@ -5,13 +5,19 @@ try {
         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) => console.log(`  ${p.percentage.toFixed(1)}%`),
+        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");
+        },
     });
-    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." }],
@@ -23,12 +29,12 @@ 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");
     if (loadModelEvent) {
@@ -58,15 +64,15 @@ try {
         ];
         console.log("  Available ops:", ops.join(", "));
     }
-    console.log("\n=== Profiler JSON (structure) ===");
+    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("\nProfiler disabled:", !profiler.isEnabled());
+    console.log("\n▸ Profiler disabled:", !profiler.isEnabled());
 }
 catch (error) {
-    console.error("Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

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

@@ -1,29 +1,35 @@
 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) => console.log(`  ${p.percentage.toFixed(1)}%`),
+        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");
+        },
     });
-    console.log("Model loaded:", modelId);
-    console.log("\n=== Embed with per-call 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 ===");
+    console.log("▸ Embedding dimensions:", embedding1.length);
+    console.log("\n▸ Embed without profiling");
     const { embedding: embedding2 } = await embed({
         modelId,
         text: "This call is not profiled",
     });
-    console.log("Embedding dimensions:", embedding2.length);
-    console.log("\n=== Embed with profiling explicitly disabled ===");
+    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:", 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:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/quickstart.bare.d.ts

@@ -0,0 +1,2 @@
+export {};
+//# sourceMappingURL=quickstart.bare.d.ts.map

package/dist/examples/quickstart.bare.js

@@ -0,0 +1,18 @@
+// 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";
+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 result = completion({ modelId, history, stream: true });
+for await (const token of result.tokenStream) {
+    process.stdout.write(token);
+}
+await unloadModel({ modelId, autoClose: true });

package/dist/examples/quickstart.js

@@ -1,10 +1,17 @@
+// 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";
 try {
     // Load a model into memory
     const modelId = await loadModel({
         modelSrc: LLAMA_3_2_1B_INST_Q4_0,
-        onProgress: (progress) => {
-            console.log(progress);
+        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");
         },
     });
     // You can use the loaded model multiple times
@@ -22,6 +29,6 @@ try {
     await unloadModel({ modelId });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/rag/rag-chromadb.js

@@ -3,7 +3,7 @@ import { embed, loadModel, unloadModel, GTE_LARGE_FP16 } from "@qvac/sdk";
 import { ChromaClient } from "chromadb";
 // Setup instructions for ChromaDB server
 const CHROMADB_SETUP_INSTRUCTIONS = `
-🚀 To run this example, you need a ChromaDB server running locally.
+▸ To run this example, you need a ChromaDB server running locally.
 
 Setup options:
 
@@ -21,12 +21,12 @@ async function initializeChromaClient() {
     const client = new ChromaClient({ host: "localhost", port: 8000 });
     try {
         await client.heartbeat();
-        console.log("✅ Connected to ChromaDB server");
+        console.log("▸ Connected to ChromaDB server");
         return client;
     }
     catch {
-        console.error("❌ Failed to connect to ChromaDB server");
-        console.error("Please ensure the server is running on localhost:8000");
+        console.error("✖ Failed to connect to ChromaDB server");
+        console.error("▸ Please ensure the server is running on localhost:8000");
         console.error(CHROMADB_SETUP_INSTRUCTIONS);
         process.exit(1);
     }
@@ -34,11 +34,17 @@ async function initializeChromaClient() {
 try {
     // Get query from command line or use default
     const query = process.argv[2] || "machine learning algorithms";
-    console.log(`🔍 Query: "${query}"`);
+    console.log(`▸ Query: "${query}"`);
     const client = await initializeChromaClient();
     const modelId = await loadModel({
         modelSrc: GTE_LARGE_FP16,
-        onProgress: (p) => console.log(`Loading model... ${Math.round(p.percentage)}%`),
+        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");
+        },
     });
     // Sample corpus
     const samples = [
@@ -81,14 +87,14 @@ try {
         await client.deleteCollection({ name: collectionName });
     }
     catch (e) {
-        console.warn(`Collection didn't exist, no need to delete: ${String(e)}`);
+        console.warn(`▸ Collection didn't exist, no need to delete: ${String(e)}`);
     }
     const collection = await client.createCollection({
         name: collectionName,
         embeddingFunction: null,
     });
     // Embed and add documents (we're bringing our own embeddings)
-    console.log("📚 Embedding documents...");
+    console.log("▸ Embedding documents...");
     const ids = [];
     const documents = [];
     const embeddings = [];
@@ -102,7 +108,7 @@ try {
         documents,
         embeddings,
     });
-    console.log("🔎 Searching for similar documents...");
+    console.log("▸ Searching for similar documents...");
     const { embedding: queryEmbedding } = await embed({ modelId, text: query });
     // Query top 3 by vector similarity and include distances
     const res = await collection.query({
@@ -110,19 +116,17 @@ try {
         nResults: 3,
         include: ["documents", "distances"],
     });
-    console.log("\n📋 Top 3 most similar documents:");
+    console.log("▸ Top 3 most similar documents:");
     const docs = res.documents?.[0] ?? [];
     const dists = res.distances?.[0] ?? [];
     for (let i = 0; i < docs.length; i++) {
-        console.log("=".repeat(50) + " Top result:");
-        console.log(`\n${i + 1}. (Score: ${dists[i]?.toFixed(4)})`);
+        console.log(`${i + 1}. (Score: ${dists[i]?.toFixed(4)})`);
         console.log(`   ${docs[i]}`);
-        console.log("=".repeat(100));
         console.log();
     }
     await unloadModel({ modelId });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/rag/rag-hyperdb/cancellation.js

@@ -15,19 +15,23 @@ function generateDocuments(count) {
     });
 }
 try {
-    console.log("RAG Cancellation Example\n");
+    console.log("▸ RAG Cancellation Example");
     // Load embedding model
-    console.log("Loading embedding model...");
+    console.log("▸ Loading embedding model...");
     const modelId = await loadModel({
         modelSrc: GTE_LARGE_FP16,
-        onProgress: (progress) => {
-            process.stdout.write(`\r   ${progress.percentage.toFixed(1)}%`);
+        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");
         },
     });
-    console.log("\n✅ Model loaded\n");
+    console.log("▸ Model loaded");
     // Generate documents
     const documents = generateDocuments(200);
-    console.log(`📄 Processing ${documents.length} documents...\n`);
+    console.log(`▸ Processing ${documents.length} documents...`);
     let progressCount = 0;
     let cancelled = false;
     // Capture the decorated promise so we can cancel by `requestId` (the
@@ -40,10 +44,9 @@ try {
         progressInterval: 50,
         onProgress: (stage, current, total) => {
             progressCount++;
-            const pct = total > 0 ? Math.round((current / total) * 100) : 0;
-            console.log(`   [${stage}] ${current}/${total} (${pct}%)`);
+            console.log(`▸ ${stage} ${current}/${total}`);
             if (!cancelled && stage === "embedding" && current > 10) {
-                console.log("\n🛑 Triggering cancellation...\n");
+                console.log("▸ Triggering cancellation...");
                 cancelled = true;
                 void cancel({ requestId: ingest.requestId });
             }
@@ -51,15 +54,15 @@ try {
     });
     try {
         await ingest;
-        console.log("\n⚠️  Ingest completed (cancellation didn't interrupt in time)");
+        console.log("▸ Ingest completed (cancellation didn't interrupt in time)");
     }
     catch (error) {
         const msg = error instanceof Error ? error.message : String(error);
         const wasCancelled = msg.toLowerCase().includes("cancel") ||
             msg.toLowerCase().includes("abort");
         if (wasCancelled) {
-            console.log("✅ Operation cancelled successfully!");
-            console.log(`   Progress updates received: ${progressCount}`);
+            console.log("▸ Operation cancelled successfully!");
+            console.log(`▸ Progress updates received: ${progressCount}`);
         }
         else {
             throw error;
@@ -68,10 +71,10 @@ try {
     // Cleanup (workspace may not exist if cancelled early)
     await ragCloseWorkspace({ workspace: WORKSPACE, deleteOnClose: true }).catch(() => { });
     await unloadModel({ modelId });
-    console.log("✅ Done");
+    console.log("▸ Done");
     process.exit(0);
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

package/dist/examples/rag/rag-hyperdb/ingest.js

@@ -3,11 +3,15 @@ try {
     // Get query from command line or use default
     const query = process.argv[2] || "machine learning algorithms";
     const workspace = "ingest-example";
-    console.log(`🔍 Query: "${query}"`);
+    console.log(`▸ Query: "${query}"`);
     const modelId = await loadModel({
         modelSrc: GTE_LARGE_FP16,
-        onProgress: (progress) => {
-            console.log(`Loading model... ${progress.percentage.toFixed(1)}%`);
+        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");
         },
     });
     const samples = [
@@ -20,35 +24,33 @@ try {
         "Cloud computing delivers computing services over the internet, allowing users to access resources like storage, processing power, and applications on-demand from anywhere.",
         "Cybersecurity protects digital systems, networks, and data from malicious attacks, unauthorized access, and various forms of cyber threats through multiple layers of defense.",
     ];
-    console.log("📚 Ingesting documents...");
+    console.log("▸ Ingesting documents...");
     const result = await ragIngest({
         modelId,
         workspace,
         documents: samples,
         chunk: false,
     });
-    console.log(`✅ Ingested ${result.processed.length} documents`);
-    console.log("🔎 Searching for similar documents...");
+    console.log(`▸ Ingested ${result.processed.length} documents`);
+    console.log("▸ Searching for similar documents...");
     const results = await ragSearch({
         modelId,
         workspace,
         query,
         topK: 3,
     });
-    console.log("\n📋 Top 3 most similar documents:");
+    console.log("▸ Top 3 most similar documents:");
     results.forEach((result, index) => {
-        console.log("=".repeat(50) + " Top result:");
-        console.log(`\n${index + 1}. (Score: ${result.score})`);
+        console.log(`${index + 1}. (Score: ${result.score})`);
         console.log(`   ${result.content}`);
-        console.log("=".repeat(100));
         console.log();
     });
     // Cleanup: close and delete workspace
     await ragCloseWorkspace({ workspace, deleteOnClose: true });
-    console.log(`\n🗑️  Deleted '${workspace}' workspace`);
+    console.log(`▸ Deleted '${workspace}' workspace`);
     await unloadModel({ modelId });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }