@qvac/sdk 0.13.5 → 0.14.1

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);
 }

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

@@ -2,13 +2,17 @@ import { loadModel, unloadModel, embed, GTE_LARGE_FP16, ragChunk, ragSaveEmbeddi
 try {
     // Get query from command line or use default
     const query = process.argv[2] || "machine learning algorithms";
-    console.log("🔧 RAG Pipeline Example (Segregated Flow)\n");
-    console.log(`🔍 Query: "${query}"`);
+    console.log("▸ RAG Pipeline Example (Segregated Flow)");
+    console.log(`▸ Query: "${query}"`);
     const workspace = "pipeline-example";
     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 = [
@@ -21,7 +25,7 @@ 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("\n📝 Step 1: Chunking documents...");
+    console.log("▸ Step 1: Chunking documents...");
     const chunks = await ragChunk({
         documents: samples,
         chunkOpts: {
@@ -29,8 +33,8 @@ try {
             chunkOverlap: 20,
         },
     });
-    console.log(`   Created ${chunks.length} chunks`);
-    console.log("\n🧠 Step 2: Generating embeddings (batch)...");
+    console.log(`▸ Created ${chunks.length} chunks`);
+    console.log("▸ Step 2: Generating embeddings (batch)...");
     const texts = chunks.map((chunk) => chunk.content);
     const { embedding: embeddings } = await embed({ modelId, text: texts });
     const embeddedDocs = chunks.map((chunk, i) => ({
@@ -39,35 +43,33 @@ try {
         embedding: embeddings[i],
         embeddingModelId: modelId,
     }));
-    console.log(`   Generated ${embeddedDocs.length} embeddings`);
-    console.log("\n💾 Step 3: Saving to vector database...");
+    console.log(`▸ Generated ${embeddedDocs.length} embeddings`);
+    console.log("▸ Step 3: Saving to vector database...");
     const saveResult = await ragSaveEmbeddings({
         workspace,
         documents: embeddedDocs,
     });
     const saved = saveResult.filter((r) => r.status === "fulfilled").length;
-    console.log(`   Saved ${saved}/${saveResult.length} documents`);
-    console.log("\n🔎 Step 4: Searching...");
+    console.log(`▸ Saved ${saved}/${saveResult.length} documents`);
+    console.log("▸ Step 4: Searching...");
     const results = await ragSearch({
         workspace,
         modelId,
         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(`   ${result.content}`);
-        console.log("=".repeat(100));
         console.log();
     });
     // Cleanup: close and delete workspace
     await ragCloseWorkspace({ workspace, deleteOnClose: true });
-    console.log(`🗑️  Deleted '${workspace}' workspace`);
+    console.log(`▸ Deleted '${workspace}' workspace`);
     await unloadModel({ modelId });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

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

@@ -1,12 +1,17 @@
 import { loadModel, unloadModel, GTE_LARGE_FP16, ragIngest, ragSearch, ragDeleteEmbeddings, ragListWorkspaces, ragCloseWorkspace, ragReindex, } from "@qvac/sdk";
 try {
-    console.log("🚀 RAG Workspaces with Chunking Example\n");
+    console.log("▸ RAG Workspaces with Chunking Example");
     // Load model
     const modelId = await loadModel({
         modelSrc: GTE_LARGE_FP16,
-        onProgress: (p) => process.stdout.write(`\rLoading: ${Math.round(p.percentage * 100)}%`),
+        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");
     // Medical articles (will be chunked)
     const medicalArticles = [
         `COVID-19: A Comprehensive Overview
@@ -68,7 +73,7 @@ try {
         "Deep learning neural networks enable breakthroughs in computer vision and natural language processing.",
     ];
     // Ingest medical articles with chunking
-    console.log("📚 Ingesting medical articles with chunking...");
+    console.log("▸ Ingesting medical articles with chunking...");
     const medicalResult = await ragIngest({
         modelId,
         workspace: "medical",
@@ -81,16 +86,16 @@ try {
             splitStrategy: "token",
         },
     });
-    console.log(`✅ Created ${medicalResult.processed.length} chunks from medical articles`);
+    console.log(`▸ Created ${medicalResult.processed.length} chunks from medical articles`);
     // Ingest tech docs without chunking
-    console.log("\n📚 Ingesting tech documents...");
+    console.log("\n▸ Ingesting tech documents...");
     const techResult = await ragIngest({
         modelId,
         workspace: "technology",
         documents: techDocs,
         chunk: false,
     });
-    console.log(`✅ Ingested ${techResult.processed.length} tech documents`);
+    console.log(`▸ Ingested ${techResult.processed.length} tech documents`);
     // Test searches
     const searches = [
         { workspace: "medical", query: "COVID symptoms fever", label: "Medical" },
@@ -98,20 +103,20 @@ try {
         { workspace: "technology", query: "neural networks", label: "Tech" },
         { workspace: "technology", query: "COVID", label: "Tech (isolation test)" },
     ];
-    console.log("\n🔍 Running searches:");
+    console.log("\n▸ Running searches:");
     for (const { workspace, query, label } of searches) {
         const results = await ragSearch({ modelId, workspace, query, topK: 1 });
         console.log(`\n${label}: "${query}"`);
         if (results.length > 0 && results[0]) {
-            console.log(`  ✓ Score: ${results[0].score.toFixed(3)}`);
-            console.log(`  ✓ Match: ${results[0].content.substring(0, 80)}...`);
+            console.log(`  Score: ${results[0].score.toFixed(3)}`);
+            console.log(`  Match: ${results[0].content.substring(0, 80)}...`);
         }
         else {
-            console.log(`  ✗ No results (workspace isolation working correctly)`);
+            console.log(`  ▸ No results (workspace isolation working correctly)`);
         }
     }
     // Test a third workspace
-    console.log("\n📁 Testing 'general' workspace...");
+    console.log("\n▸ Testing 'general' workspace...");
     await ragIngest({
         modelId,
         workspace: "general",
@@ -123,20 +128,19 @@ try {
         workspace: "general",
         query: "general workspace",
     });
-    console.log(`General workspace: ${generalSearch?.[0]?.content === "General workspace content for testing" ? "✅ Working" : "❌ Failed"}`);
+    console.log(`▸ General workspace: ${generalSearch?.[0]?.content === "General workspace content for testing" ? "Working" : "Failed"}`);
     // Reindexing - regenerate embeddings for an existing workspace
-    console.log("\n🔄 Reindexing medical workspace...");
+    console.log("\n▸ Reindexing medical workspace...");
     const reindexResult = await ragReindex({
         workspace: "medical",
         modelId,
         onProgress: (stage, current, total) => {
-            const pct = total > 0 ? Math.round((current / total) * 100) : 0;
-            console.log(`   [${stage}] ${current}/${total} (${pct}%)`);
+            console.log(`▸ ${stage} ${current}/${total}`);
         },
     });
-    console.log(`${reindexResult.reindexed ? "✅ Reindex completed" : "⚠️  Reindex returned false"} for medical workspace`);
+    console.log(`▸ ${reindexResult.reindexed ? "Reindex completed" : "Reindex returned false"} for medical workspace`);
     if (reindexResult.details) {
-        console.log("   Details:", reindexResult.details);
+        console.log("▸ Details:", reindexResult.details);
     }
     // Verify reindexed data still works
     const reindexVerify = await ragSearch({
@@ -145,7 +149,7 @@ try {
         query: "COVID symptoms",
         topK: 1,
     });
-    console.log(`   Verification search: ${reindexVerify.length > 0 ? "✅ Working" : "❌ Failed"}`);
+    console.log(`▸ Verification search: ${reindexVerify.length > 0 ? "Working" : "Failed"}`);
     // Cleanup example
     const firstChunk = medicalResult.processed.find((p) => p.status === "fulfilled" && p.id);
     if (firstChunk?.id) {
@@ -153,25 +157,25 @@ try {
             workspace: "medical",
             ids: [firstChunk.id],
         });
-        console.log("\n🗑️  Deleted one medical chunk");
+        console.log("\n▸ Deleted one medical chunk");
     }
     // List all workspaces
-    console.log("\n📂 Listing workspaces...");
+    console.log("\n▸ Listing workspaces...");
     const workspaces = await ragListWorkspaces();
     workspaces.forEach((ws) => {
-        console.log(`  • ${ws.name} (${ws.open ? "open" : "closed"})`);
+        console.log(`▸ ${ws.name} (${ws.open ? "open" : "closed"})`);
     });
     // Close and delete all workspaces created in this example
-    console.log("\n🗑️  Closing and deleting workspaces...");
+    console.log("\n▸ Closing and deleting workspaces...");
     await ragCloseWorkspace({ workspace: "medical", deleteOnClose: true });
-    console.log("Deleted 'medical' workspace");
+    console.log("▸ Deleted 'medical' workspace");
     await ragCloseWorkspace({ workspace: "technology", deleteOnClose: true });
-    console.log("Deleted 'technology' workspace");
+    console.log("▸ Deleted 'technology' workspace");
     await ragCloseWorkspace({ workspace: "general", deleteOnClose: true });
-    console.log("Deleted 'general' workspace");
+    console.log("▸ Deleted 'general' workspace");
     await unloadModel({ modelId });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

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

@@ -4,12 +4,16 @@ import * as a from "apache-arrow";
 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 db = await lancedb.connect(".rag-lancedb");
     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 = [
@@ -56,10 +60,10 @@ try {
         await db.dropTable("documents");
     }
     catch (e) {
-        console.warn(`Table doesn't exist, no need to drop: ${String(e)}`);
+        console.warn(`▸ Table doesn't exist, no need to drop: ${String(e)}`);
     }
     const documentsTable = await db.createEmptyTable("documents", schema);
-    console.log("📚 Embedding documents...");
+    console.log("▸ Embedding documents...");
     const documents = [];
     for (const sample of samples) {
         const { embedding } = await embed({ modelId, text: sample.text });
@@ -71,13 +75,13 @@ try {
         documents.push(record);
     }
     await documentsTable.add(documents);
-    console.log("🔎 Searching for similar documents...");
+    console.log("▸ Searching for similar documents...");
     const { embedding: queryEmbedding } = await embed({ modelId, text: query });
     const results = (await documentsTable
         .vectorSearch(queryEmbedding)
         .limit(1)
         .toArray());
-    console.log("\n📋 Top 3 most similar documents:");
+    console.log("\n▸ Top 3 most similar documents:");
     results.forEach((result, index) => {
         console.log("=".repeat(50) + " Top result:");
         console.log(`\n${index + 1}. (Score: ${result._distance?.toFixed(4)})`);
@@ -88,6 +92,6 @@ try {
     await unloadModel({ modelId });
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }

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

@@ -3,14 +3,18 @@ import sqlite3InitModule from "@sqliteai/sqlite-wasm";
 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}"`);
     // Initialize SQLite with vector extension
     const sqlite3 = await sqlite3InitModule();
     const db = new sqlite3.oo1.DB(":memory:", "c");
     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}` : `${line}\n`);
+            if (p.percentage >= 100)
+                process.stderr.write("\n");
         },
     });
     const samples = [
@@ -55,7 +59,7 @@ try {
     embedding BLOB NOT NULL
   )
 `);
-    console.log("📚 Embedding documents...");
+    console.log("▸ Embedding documents...");
     for (const sample of samples) {
         const { embedding } = await embed({ modelId, text: sample.text });
         db.exec({
@@ -70,7 +74,7 @@ try {
     // [Optional] Preload quantized vectors in memory for optimal performance
     db.exec(`SELECT vector_quantize_preload('documents', 'embedding')`);
     // Search for similar documents
-    console.log("🔎 Searching for similar documents...");
+    console.log("▸ Searching for similar documents...");
     const { embedding: queryEmbedding } = await embed({ modelId, text: query });
     const results = [];
     // Perform vector search
@@ -88,7 +92,7 @@ try {
             results.push(typedRow);
         },
     });
-    console.log("\n📋 Top 3 most similar documents:");
+    console.log("\n▸ Top 3 most similar documents:");
     results.forEach((result, index) => {
         console.log("=".repeat(50) + " Top result:");
         console.log(`\n${index + 1}. [ID: ${result.id}] (Score: ${result.distance.toFixed(4)})`);
@@ -100,6 +104,6 @@ try {
     db.close();
 }
 catch (error) {
-    console.error("❌ Error:", error);
+    console.error("✖", error);
     process.exit(1);
 }