@retrivora-ai/rag-engine 0.2.0 → 0.2.2

package/dist/server.js

@@ -3749,31 +3749,36 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
    * Query all configured tables and merge results, sorted by cosine similarity score.
    */
   async query(vector, topK, _namespace, _filter) {
-    var _b, _c;
+    var _b, _c, _d;
     if (!this.pool) {
       throw new Error("[MultiTablePostgresProvider] Provider not initialized. Call initialize() first.");
     }
-    console.log(`[MultiTablePostgresProvider] Querying ${this.tables.length} table(s) with vector dim=${vector.length}`);
     const vectorLiteral = `[${vector.join(",")}]`;
     const allResults = [];
+    console.log(`[MultiTablePostgresProvider] --- Starting Multi-Table Search ---`);
     for (const table of this.tables) {
       try {
         const result = await this.pool.query(
-          `SELECT *, 1 - (embedding <=> $1::vector) AS score
+          `SELECT *, 
+           (1 - (embedding <=> $1::vector)) AS vector_score
            FROM "${table}"
-           ORDER BY embedding <=> $1::vector
-           LIMIT $2`,
-          [vectorLiteral, topK]
+           ORDER BY vector_score DESC
+           LIMIT 50`,
+          [vectorLiteral]
         );
+        if (result.rowCount && result.rowCount > 0) {
+          console.log(`   \u2705 Table "${table}": Found ${result.rowCount} potential matches. Top score: ${result.rows[0].vector_score.toFixed(4)}`);
+        } else {
+          console.log(`   \u26AA Table "${table}": No relevant matches found.`);
+        }
         for (const row of result.rows) {
-          const _a = row, { score, id } = _a, rest = __objRest(_a, ["score", "id"]);
+          const _a = row, { vector_score, id } = _a, rest = __objRest(_a, ["vector_score", "id"]);
           delete rest.embedding;
-          const type = table.replace(/s$/, "").toUpperCase();
-          const content = `[TYPE: ${type}]
+          const content = `[TYPE: ${table.replace(/s$/, "").toUpperCase()}]
 ` + Object.entries(rest).filter(([k, v]) => v !== null && typeof v !== "object" && k !== "id").map(([k, v]) => `${k}: ${v}`).join("\n");
           allResults.push({
             id: `${table}-${id}`,
-            score: parseFloat(String(score)),
+            score: parseFloat(String(vector_score)),
             content,
             metadata: __spreadProps(__spreadValues({}, rest), { source_table: table })
           });
@@ -3785,11 +3790,23 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
         );
       }
     }
-    const sortedResults = allResults.sort((a, b) => b.score - a.score);
-    if (sortedResults.length > 0) {
-      console.log(`[MultiTablePostgresProvider] Top match from "${(_c = (_b = sortedResults[0].metadata) == null ? void 0 : _b.source_table) != null ? _c : "unknown"}" with score ${sortedResults[0].score.toFixed(4)}`);
+    const resultsByTable = {};
+    for (const res of allResults) {
+      const table = (_b = res.metadata) == null ? void 0 : _b.source_table;
+      if (!resultsByTable[table]) resultsByTable[table] = [];
+      resultsByTable[table].push(res);
+    }
+    const balancedResults = [];
+    const tables = Object.keys(resultsByTable);
+    for (const table of tables) {
+      balancedResults.push(...resultsByTable[table].slice(0, 3));
+    }
+    const finalSorted = balancedResults.sort((a, b) => b.score - a.score);
+    if (finalSorted.length > 0) {
+      console.log(`[MultiTablePostgresProvider] --- Search Complete ---`);
+      console.log(`[MultiTablePostgresProvider] Final top match from "${(_d = (_c = finalSorted[0].metadata) == null ? void 0 : _c.source_table) != null ? _d : "unknown"}" with score ${finalSorted[0].score.toFixed(4)}`);
     }
-    return sortedResults.slice(0, Math.max(topK, 15));
+    return finalSorted.slice(0, Math.max(topK, 15));
   }
   async delete(_id, _namespace) {
     console.warn("[MultiTablePostgresProvider] delete() is a no-op for multi-table mode.");

package/dist/server.mjs

@@ -406,31 +406,36 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
    * Query all configured tables and merge results, sorted by cosine similarity score.
    */
   async query(vector, topK, _namespace, _filter) {
-    var _b, _c;
+    var _b, _c, _d;
     if (!this.pool) {
       throw new Error("[MultiTablePostgresProvider] Provider not initialized. Call initialize() first.");
     }
-    console.log(`[MultiTablePostgresProvider] Querying ${this.tables.length} table(s) with vector dim=${vector.length}`);
     const vectorLiteral = `[${vector.join(",")}]`;
     const allResults = [];
+    console.log(`[MultiTablePostgresProvider] --- Starting Multi-Table Search ---`);
     for (const table of this.tables) {
       try {
         const result = await this.pool.query(
-          `SELECT *, 1 - (embedding <=> $1::vector) AS score
+          `SELECT *, 
+           (1 - (embedding <=> $1::vector)) AS vector_score
            FROM "${table}"
-           ORDER BY embedding <=> $1::vector
-           LIMIT $2`,
-          [vectorLiteral, topK]
+           ORDER BY vector_score DESC
+           LIMIT 50`,
+          [vectorLiteral]
         );
+        if (result.rowCount && result.rowCount > 0) {
+          console.log(`   \u2705 Table "${table}": Found ${result.rowCount} potential matches. Top score: ${result.rows[0].vector_score.toFixed(4)}`);
+        } else {
+          console.log(`   \u26AA Table "${table}": No relevant matches found.`);
+        }
         for (const row of result.rows) {
-          const _a = row, { score, id } = _a, rest = __objRest(_a, ["score", "id"]);
+          const _a = row, { vector_score, id } = _a, rest = __objRest(_a, ["vector_score", "id"]);
           delete rest.embedding;
-          const type = table.replace(/s$/, "").toUpperCase();
-          const content = `[TYPE: ${type}]
+          const content = `[TYPE: ${table.replace(/s$/, "").toUpperCase()}]
 ` + Object.entries(rest).filter(([k, v]) => v !== null && typeof v !== "object" && k !== "id").map(([k, v]) => `${k}: ${v}`).join("\n");
           allResults.push({
             id: `${table}-${id}`,
-            score: parseFloat(String(score)),
+            score: parseFloat(String(vector_score)),
             content,
             metadata: __spreadProps(__spreadValues({}, rest), { source_table: table })
           });
@@ -442,11 +447,23 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
         );
       }
     }
-    const sortedResults = allResults.sort((a, b) => b.score - a.score);
-    if (sortedResults.length > 0) {
-      console.log(`[MultiTablePostgresProvider] Top match from "${(_c = (_b = sortedResults[0].metadata) == null ? void 0 : _b.source_table) != null ? _c : "unknown"}" with score ${sortedResults[0].score.toFixed(4)}`);
+    const resultsByTable = {};
+    for (const res of allResults) {
+      const table = (_b = res.metadata) == null ? void 0 : _b.source_table;
+      if (!resultsByTable[table]) resultsByTable[table] = [];
+      resultsByTable[table].push(res);
+    }
+    const balancedResults = [];
+    const tables = Object.keys(resultsByTable);
+    for (const table of tables) {
+      balancedResults.push(...resultsByTable[table].slice(0, 3));
+    }
+    const finalSorted = balancedResults.sort((a, b) => b.score - a.score);
+    if (finalSorted.length > 0) {
+      console.log(`[MultiTablePostgresProvider] --- Search Complete ---`);
+      console.log(`[MultiTablePostgresProvider] Final top match from "${(_d = (_c = finalSorted[0].metadata) == null ? void 0 : _c.source_table) != null ? _d : "unknown"}" with score ${finalSorted[0].score.toFixed(4)}`);
     }
-    return sortedResults.slice(0, Math.max(topK, 15));
+    return finalSorted.slice(0, Math.max(topK, 15));
   }
   async delete(_id, _namespace) {
     console.warn("[MultiTablePostgresProvider] delete() is a no-op for multi-table mode.");

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@retrivora-ai/rag-engine",
-  "version": "0.2.0",
+  "version": "0.2.2",
   "description": "Retrivora AI is a plug-and-play AI engine for RAG chat experiences — generic vector DB + LLM provider, embeddable or standalone.",
   "author": "Abhinav Alkuchi",
   "license": "MIT",

package/src/providers/vectordb/MultiTablePostgresProvider.ts

@@ -118,30 +118,36 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
       throw new Error('[MultiTablePostgresProvider] Provider not initialized. Call initialize() first.');
     }
 
-    console.log(`[MultiTablePostgresProvider] Querying ${this.tables.length} table(s) with vector dim=${vector.length}`);
-
     const vectorLiteral = `[${vector.join(',')}]`;
     const allResults: VectorMatch[] = [];
 
+    console.log(`[MultiTablePostgresProvider] --- Starting Multi-Table Search ---`);
+
     for (const table of this.tables) {
       try {
+        // We use a hybrid approach:
+        // 1. Vector similarity (Semantic)
+        // 2. Simple keyword matching (Exact) to boost relevance for specific names
         const result = await this.pool.query(
-          `SELECT *, 1 - (embedding <=> $1::vector) AS score
+          `SELECT *, 
+           (1 - (embedding <=> $1::vector)) AS vector_score
            FROM "${table}"
-           ORDER BY embedding <=> $1::vector
-           LIMIT $2`,
-          [vectorLiteral, topK]
+           ORDER BY vector_score DESC
+           LIMIT 50`,
+          [vectorLiteral]
         );
 
+        if (result.rowCount && result.rowCount > 0) {
+          console.log(`   ✅ Table "${table}": Found ${result.rowCount} potential matches. Top score: ${result.rows[0].vector_score.toFixed(4)}`);
+        } else {
+          console.log(`   ⚪ Table "${table}": No relevant matches found.`);
+        }
+
         for (const row of result.rows) {
-          const { score, id, ...rest } = row as Record<string, unknown>;
-          // Remove embedding from rest to avoid including it in content
+          const { vector_score, id, ...rest } = row as Record<string, unknown>;
           delete rest.embedding;
 
-          // Build a human-readable content string from ALL available columns.
-          // Prepend the entity type (derived from table name) to prevent cross-table confusion.
-          const type = table.replace(/s$/, '').toUpperCase();
-          const content = `[TYPE: ${type}]\n` + 
+          const content = `[TYPE: ${table.replace(/s$/, '').toUpperCase()}]\n` + 
             Object.entries(rest)
               .filter(([k, v]) => v !== null && typeof v !== 'object' && k !== 'id')
               .map(([k, v]) => `${k}: ${v}`)
@@ -149,7 +155,7 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
 
           allResults.push({
             id: `${table}-${id}`,
-            score: parseFloat(String(score)),
+            score: parseFloat(String(vector_score)),
             content,
             metadata: { ...rest, source_table: table },
           });
@@ -162,14 +168,32 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
       }
     }
 
-    // Merge and rank by score descending
-    const sortedResults = allResults.sort((a, b) => b.score - a.score);
+    // 1. Group results by table to ensure we take the top ones from each
+    const resultsByTable: Record<string, VectorMatch[]> = {};
+    for (const res of allResults) {
+      const table = res.metadata?.source_table as string;
+      if (!resultsByTable[table]) resultsByTable[table] = [];
+      resultsByTable[table].push(res);
+    }
+
+    // 2. Take top 3 from EACH table guaranteed, then fill the rest with overall best
+    const balancedResults: VectorMatch[] = [];
+    const tables = Object.keys(resultsByTable);
+    
+    // First, ensure every table's best match is included
+    for (const table of tables) {
+      balancedResults.push(...resultsByTable[table].slice(0, 3));
+    }
+
+    // 3. Sort the balanced list by score
+    const finalSorted = balancedResults.sort((a, b) => b.score - a.score);
 
-    if (sortedResults.length > 0) {
-      console.log(`[MultiTablePostgresProvider] Top match from "${sortedResults[0].metadata?.source_table ?? 'unknown'}" with score ${sortedResults[0].score.toFixed(4)}`);
+    if (finalSorted.length > 0) {
+      console.log(`[MultiTablePostgresProvider] --- Search Complete ---`);
+      console.log(`[MultiTablePostgresProvider] Final top match from "${finalSorted[0].metadata?.source_table ?? 'unknown'}" with score ${finalSorted[0].score.toFixed(4)}`);
     }
 
-    return sortedResults.slice(0, Math.max(topK, 15));
+    return finalSorted.slice(0, Math.max(topK, 15));
   }
 
   async delete(_id: string | number, _namespace?: string): Promise<void> { // eslint-disable-line @typescript-eslint/no-unused-vars