@retrivora-ai/rag-engine 0.1.9 → 0.2.0

package/dist/server.d.mts

@@ -705,7 +705,7 @@ declare class MultiTablePostgresProvider extends BaseVectorProvider {
     private pool;
     private readonly dimensions;
     private readonly connectionString;
-    private readonly tables;
+    private tables;
     constructor(config: VectorDBConfig);
     initialize(): Promise<void>;
     /**

package/dist/server.d.ts

@@ -705,7 +705,7 @@ declare class MultiTablePostgresProvider extends BaseVectorProvider {
     private pool;
     private readonly dimensions;
     private readonly connectionString;
-    private readonly tables;
+    private tables;
     constructor(config: VectorDBConfig);
     initialize(): Promise<void>;
     /**

package/dist/server.js

@@ -3699,10 +3699,34 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
   async initialize() {
     this.pool = new import_pg2.Pool({ connectionString: this.connectionString });
     const client = await this.pool.connect();
-    client.release();
-    console.log(
-      `[MultiTablePostgresProvider] Connected. Searching across ${this.tables.length} table(s): ${this.tables.join(", ")}`
-    );
+    try {
+      const res = await client.query(`
+        SELECT table_name 
+        FROM information_schema.columns 
+        WHERE column_name = 'embedding' 
+        AND table_schema = 'public'
+      `);
+      const discoveredTables = res.rows.map((r) => r.table_name);
+      if (this.tables.length === 0) {
+        this.tables = discoveredTables;
+      } else {
+        const staticTables = [...this.tables];
+        this.tables = staticTables.filter((t) => discoveredTables.includes(t));
+        if (this.tables.length < staticTables.length) {
+          const missing = staticTables.filter((t) => !discoveredTables.includes(t));
+          console.warn(`[MultiTablePostgresProvider] Some configured tables were skipped (missing 'embedding' column): ${missing.join(", ")}`);
+        }
+      }
+      if (this.tables.length === 0) {
+        console.warn('[MultiTablePostgresProvider] No tables with "embedding" columns found in the database.');
+      } else {
+        console.log(
+          `[MultiTablePostgresProvider] Connected. Searching across ${this.tables.length} table(s): ${this.tables.join(", ")}`
+        );
+      }
+    } finally {
+      client.release();
+    }
   }
   /**
    * Upsert is not supported for MultiTablePostgresProvider as it's designed for 
@@ -3744,7 +3768,9 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
         for (const row of result.rows) {
           const _a = row, { score, id } = _a, rest = __objRest(_a, ["score", "id"]);
           delete rest.embedding;
-          const content = Object.entries(rest).filter(([k, v]) => v !== null && typeof v !== "object" && k !== "id").map(([k, v]) => `${k}: ${v}`).join("\n");
+          const type = table.replace(/s$/, "").toUpperCase();
+          const content = `[TYPE: ${type}]
+` + Object.entries(rest).filter(([k, v]) => v !== null && typeof v !== "object" && k !== "id").map(([k, v]) => `${k}: ${v}`).join("\n");
           allResults.push({
             id: `${table}-${id}`,
             score: parseFloat(String(score)),
@@ -3763,7 +3789,7 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
     if (sortedResults.length > 0) {
       console.log(`[MultiTablePostgresProvider] Top match from "${(_c = (_b = sortedResults[0].metadata) == null ? void 0 : _b.source_table) != null ? _c : "unknown"}" with score ${sortedResults[0].score.toFixed(4)}`);
     }
-    return sortedResults.slice(0, topK);
+    return sortedResults.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

@@ -356,10 +356,34 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
   async initialize() {
     this.pool = new Pool({ connectionString: this.connectionString });
     const client = await this.pool.connect();
-    client.release();
-    console.log(
-      `[MultiTablePostgresProvider] Connected. Searching across ${this.tables.length} table(s): ${this.tables.join(", ")}`
-    );
+    try {
+      const res = await client.query(`
+        SELECT table_name 
+        FROM information_schema.columns 
+        WHERE column_name = 'embedding' 
+        AND table_schema = 'public'
+      `);
+      const discoveredTables = res.rows.map((r) => r.table_name);
+      if (this.tables.length === 0) {
+        this.tables = discoveredTables;
+      } else {
+        const staticTables = [...this.tables];
+        this.tables = staticTables.filter((t) => discoveredTables.includes(t));
+        if (this.tables.length < staticTables.length) {
+          const missing = staticTables.filter((t) => !discoveredTables.includes(t));
+          console.warn(`[MultiTablePostgresProvider] Some configured tables were skipped (missing 'embedding' column): ${missing.join(", ")}`);
+        }
+      }
+      if (this.tables.length === 0) {
+        console.warn('[MultiTablePostgresProvider] No tables with "embedding" columns found in the database.');
+      } else {
+        console.log(
+          `[MultiTablePostgresProvider] Connected. Searching across ${this.tables.length} table(s): ${this.tables.join(", ")}`
+        );
+      }
+    } finally {
+      client.release();
+    }
   }
   /**
    * Upsert is not supported for MultiTablePostgresProvider as it's designed for 
@@ -401,7 +425,9 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
         for (const row of result.rows) {
           const _a = row, { score, id } = _a, rest = __objRest(_a, ["score", "id"]);
           delete rest.embedding;
-          const content = Object.entries(rest).filter(([k, v]) => v !== null && typeof v !== "object" && k !== "id").map(([k, v]) => `${k}: ${v}`).join("\n");
+          const type = table.replace(/s$/, "").toUpperCase();
+          const content = `[TYPE: ${type}]
+` + Object.entries(rest).filter(([k, v]) => v !== null && typeof v !== "object" && k !== "id").map(([k, v]) => `${k}: ${v}`).join("\n");
           allResults.push({
             id: `${table}-${id}`,
             score: parseFloat(String(score)),
@@ -420,7 +446,7 @@ var MultiTablePostgresProvider = class extends BaseVectorProvider {
     if (sortedResults.length > 0) {
       console.log(`[MultiTablePostgresProvider] Top match from "${(_c = (_b = sortedResults[0].metadata) == null ? void 0 : _b.source_table) != null ? _c : "unknown"}" with score ${sortedResults[0].score.toFixed(4)}`);
     }
-    return sortedResults.slice(0, topK);
+    return sortedResults.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": "0.1.9",
+  "version": "0.2.0",
   "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

@@ -15,7 +15,7 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
   private pool!: Pool;
   private readonly dimensions: number;
   private readonly connectionString: string;
-  private readonly tables: string[];
+  private tables: string[];
 
   constructor(config: VectorDBConfig) {
     super(config);
@@ -31,7 +31,7 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
       (opts.tables as string | string[]) ??
       process.env.VECTOR_DB_TABLES ??
       '';
-    
+
     this.tables = typeof rawTables === 'string'
       ? rawTables.split(',').map((t) => t.trim()).filter(Boolean)
       : rawTables;
@@ -46,12 +46,43 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
 
   async initialize(): Promise<void> {
     this.pool = new Pool({ connectionString: this.connectionString });
-    // Verify connectivity
+    
+    // Dynamically discover all tables that have an 'embedding' column
     const client: PoolClient = await this.pool.connect();
-    client.release();
-    console.log(
-      `[MultiTablePostgresProvider] Connected. Searching across ${this.tables.length} table(s): ${this.tables.join(', ')}`
-    );
+    try {
+      const res = await client.query(`
+        SELECT table_name 
+        FROM information_schema.columns 
+        WHERE column_name = 'embedding' 
+        AND table_schema = 'public'
+      `);
+      
+      const discoveredTables = res.rows.map(r => r.table_name);
+      
+      if (this.tables.length === 0) {
+        // No static tables configured, use everything discovered
+        this.tables = discoveredTables;
+      } else {
+        // Filter configured tables to ensure they actually exist with embeddings
+        const staticTables = [...this.tables];
+        this.tables = staticTables.filter(t => discoveredTables.includes(t));
+        
+        if (this.tables.length < staticTables.length) {
+          const missing = staticTables.filter(t => !discoveredTables.includes(t));
+          console.warn(`[MultiTablePostgresProvider] Some configured tables were skipped (missing 'embedding' column): ${missing.join(', ')}`);
+        }
+      }
+
+      if (this.tables.length === 0) {
+        console.warn('[MultiTablePostgresProvider] No tables with "embedding" columns found in the database.');
+      } else {
+        console.log(
+          `[MultiTablePostgresProvider] Connected. Searching across ${this.tables.length} table(s): ${this.tables.join(', ')}`
+        );
+      }
+    } finally {
+      client.release();
+    }
   }
 
   /**
@@ -108,11 +139,13 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
           delete rest.embedding;
 
           // Build a human-readable content string from ALL available columns.
-          // This ensures the LLM sees the name, website, description, etc. together.
-          const content = Object.entries(rest)
-            .filter(([k, v]) => v !== null && typeof v !== 'object' && k !== 'id')
-            .map(([k, v]) => `${k}: ${v}`)
-            .join('\n');
+          // Prepend the entity type (derived from table name) to prevent cross-table confusion.
+          const type = table.replace(/s$/, '').toUpperCase();
+          const content = `[TYPE: ${type}]\n` + 
+            Object.entries(rest)
+              .filter(([k, v]) => v !== null && typeof v !== 'object' && k !== 'id')
+              .map(([k, v]) => `${k}: ${v}`)
+              .join('\n');
 
           allResults.push({
             id: `${table}-${id}`,
@@ -131,12 +164,12 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
 
     // Merge and rank by score descending
     const sortedResults = allResults.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)}`);
     }
 
-    return sortedResults.slice(0, topK);
+    return sortedResults.slice(0, Math.max(topK, 15));
   }
 
   async delete(_id: string | number, _namespace?: string): Promise<void> { // eslint-disable-line @typescript-eslint/no-unused-vars