@retrivora-ai/rag-engine 1.8.9 → 1.9.0

package/dist/server.mjs

@@ -353,12 +353,10 @@ var init_MultiTablePostgresProvider = __esm({
           embedding   VECTOR(${this.dimensions})
         )
       `);
-          const metric = this.config.distanceMetric || "cosine";
-          const indexOps = metric === "euclidean" ? "vector_l2_ops" : metric === "dotproduct" ? "vector_ip_ops" : "vector_cosine_ops";
           await client.query(`
         CREATE INDEX IF NOT EXISTS ${this.uploadTable}_embedding_idx
         ON ${this.uploadTable}
-        USING hnsw (embedding ${indexOps})
+        USING hnsw (embedding vector_cosine_ops)
       `);
           const res = await client.query(`
         SELECT table_name 
@@ -420,12 +418,10 @@ var init_MultiTablePostgresProvider = __esm({
           )
         `;
             await client.query(createTableSql);
-            const metric = this.config.distanceMetric || "cosine";
-            const indexOps = metric === "euclidean" ? "vector_l2_ops" : metric === "dotproduct" ? "vector_ip_ops" : "vector_cosine_ops";
             await client.query(`
           CREATE INDEX IF NOT EXISTS "${tableName}_embedding_idx"
           ON "${tableName}"
-          USING hnsw (embedding ${indexOps})
+          USING hnsw (embedding vector_cosine_ops)
         `);
             if (!this.tables.includes(tableName)) {
               this.tables.push(tableName);
@@ -507,8 +503,6 @@ var init_MultiTablePostgresProvider = __esm({
           try {
             let sqlQuery = "";
             let params = [];
-            const metric = this.config.distanceMetric || "cosine";
-            const scoreExpr = metric === "euclidean" ? `1 / (1 + (embedding <-> $1::vector))` : metric === "dotproduct" ? `(embedding <#> $1::vector) * -1` : `1 - (embedding <=> $1::vector)`;
             if (queryText) {
               const hasEntityHints = entityHints.length > 0;
               const exactNameScoreExpr = hasEntityHints ? `+ (
@@ -521,9 +515,9 @@ var init_MultiTablePostgresProvider = __esm({
                ) * 3.0` : "";
               sqlQuery = `
             SELECT *, 
-             (${scoreExpr}) AS vector_score,
+             (1 - (embedding <=> $1::vector)) AS vector_score,
              COALESCE(ts_rank(to_tsvector('english', (to_jsonb(t) - 'embedding')::text), to_tsquery('english', $2)), 0) AS keyword_score,
-             ((${scoreExpr}) + (COALESCE(ts_rank(to_tsvector('english', (to_jsonb(t) - 'embedding')::text), to_tsquery('english', $2)), 0) * 2.0) ${exactNameScoreExpr}) AS hybrid_score
+             ((1 - (embedding <=> $1::vector)) + (COALESCE(ts_rank(to_tsvector('english', (to_jsonb(t) - 'embedding')::text), to_tsquery('english', $2)), 0) * 2.0) ${exactNameScoreExpr}) AS hybrid_score
             FROM "${table}" t
             ORDER BY hybrid_score DESC
             LIMIT 50
@@ -532,7 +526,7 @@ var init_MultiTablePostgresProvider = __esm({
             } else {
               sqlQuery = `
             SELECT *, 
-             (${scoreExpr}) AS hybrid_score
+             (1 - (embedding <=> $1::vector)) AS hybrid_score
             FROM "${table}" t
             ORDER BY hybrid_score DESC
             LIMIT 50
@@ -1006,13 +1000,11 @@ var init_QdrantProvider = __esm({
           if (axios4.isAxiosError(err) && ((_a = err.response) == null ? void 0 : _a.status) === 404) {
             const opts = this.config.options;
             const dimensionsForCreate = opts.dimensions || 1536;
-            const metric = this.config.distanceMetric || "cosine";
-            const distance = metric === "euclidean" ? "Euclid" : metric === "dotproduct" ? "Dot" : "Cosine";
             console.log(`[QdrantProvider] \u23F3 Creating collection "${this.indexName}" (dimensions: ${dimensionsForCreate})...`);
             await this.http.put(`/collections/${this.indexName}`, {
               vectors: {
                 size: dimensionsForCreate,
-                distance
+                distance: "Cosine"
               }
             });
             console.log(`[QdrantProvider] \u2705 Created collection "${this.indexName}"`);
@@ -1190,12 +1182,9 @@ var init_ChromaDBProvider = __esm({
           console.log(`[ChromaDBProvider] \u2705 Collection "${this.indexName}" found (id: ${this.collectionId})`);
         } catch (err) {
           if (axios5.isAxiosError(err) && ((_a = err.response) == null ? void 0 : _a.status) === 404) {
-            const metric = this.config.distanceMetric || "cosine";
-            const space = metric === "euclidean" ? "l2" : metric === "dotproduct" ? "ip" : "cosine";
             console.log(`[ChromaDBProvider] \u23F3 Collection "${this.indexName}" not found. Creating...`);
             const { data } = await this.http.post("/api/v1/collections", {
-              name: this.indexName,
-              metadata: { "hnsw:space": space }
+              name: this.indexName
             });
             this.collectionId = data.id;
             console.log(`[ChromaDBProvider] \u2705 Created collection "${this.indexName}" (id: ${this.collectionId})`);
@@ -4184,20 +4173,18 @@ var UITransformer = class {
     }
     const isStockRequest = this.isStockQuery(userQuery);
     const filteredData = isStockRequest ? retrievedData.filter((item) => this.determineStockStatus(item)) : retrievedData;
-    const groupByField = this.determineGroupByField(userQuery, filteredData);
-    const categories = this.detectCategories(filteredData, groupByField);
+    const categories = this.detectCategories(filteredData);
     const hasProducts = filteredData.some((item) => this.isProductData(item));
     const isTimeSeries = filteredData.some((item) => this.isTimeSeriesData(item));
     const isTrendQuery = this.isTrendQuery(userQuery);
     if (isTrendQuery && isTimeSeries) {
       return this.transformToLineChart(filteredData);
     }
-    const explicitChartRequest = this.isExplicitChartQuery(userQuery);
-    if (hasProducts && !explicitChartRequest && !this.shouldShowCategoryChart(userQuery)) {
+    if (hasProducts && !this.shouldShowCategoryChart(userQuery, categories)) {
       return this.transformToProductCarousel(filteredData, config, trainedSchema);
     }
-    if (explicitChartRequest || categories.length > 1 && this.shouldShowCategoryChart(userQuery)) {
-      return this.transformToPieChart(filteredData, groupByField);
+    if (categories.length > 1 && this.shouldShowCategoryChart(userQuery, categories)) {
+      return this.transformToPieChart(filteredData);
     }
     if (hasProducts) {
       return this.transformToProductCarousel(filteredData, config, trainedSchema);
@@ -4222,12 +4209,11 @@ var UITransformer = class {
   /**
    * Transform data to pie chart format
    */
-  static transformToPieChart(data, groupByField) {
-    let categories = this.detectCategories(data, groupByField);
-    if (categories.length === 0) categories = ["All Data"];
-    const categoryData = this.aggregateByCategory(data, categories, groupByField);
+  static transformToPieChart(data) {
+    const categories = this.detectCategories(data);
+    const categoryData = this.aggregateByCategory(data, categories);
     const pieData = Object.entries(categoryData).map(([label, count]) => {
-      const { inStockCount, outOfStockCount } = this.calculateStockCounts(label, data, groupByField);
+      const { inStockCount, outOfStockCount } = this.calculateStockCounts(label, data);
       return {
         label,
         value: count,
@@ -4237,7 +4223,7 @@ var UITransformer = class {
     });
     return {
       type: "pie_chart",
-      title: `Distribution by ${groupByField.charAt(0).toUpperCase() + groupByField.slice(1)}`,
+      title: "Distribution by Category",
       description: `Showing breakdown across ${categories.length} categories`,
       data: pieData
     };
@@ -4460,11 +4446,10 @@ var UITransformer = class {
     });
     return hasTimeKeyword || hasValidDateValue;
   }
-  static isExplicitChartQuery(query) {
-    const normalized = query.toLowerCase();
-    return normalized.includes("pie chart") || normalized.includes("piechart") || normalized.includes("bar chart") || normalized.includes("barchart") || normalized.includes("radar chart");
-  }
-  static shouldShowCategoryChart(query) {
+  static shouldShowCategoryChart(query, categories) {
+    if (categories.length < 2) {
+      return false;
+    }
     const normalized = query.toLowerCase();
     const chartKeywords = [
       "distribution",
@@ -4477,11 +4462,7 @@ var UITransformer = class {
       "segmentation",
       "split",
       "category breakdown",
-      "category distribution",
-      "pie chart",
-      "piechart",
-      "bar chart",
-      "barchart"
+      "category distribution"
     ];
     return chartKeywords.some((keyword) => normalized.includes(keyword));
   }
@@ -4557,67 +4538,44 @@ var UITransformer = class {
     return null;
   }
   /**
-   * Helper: Dynamically determine what field to group by based on user query
-   */
-  static determineGroupByField(query, data) {
-    const normalized = query.toLowerCase();
-    const match = normalized.match(/(?:by|across|per|based on)\s+([a-zA-Z]+)/i);
-    let targetField = "category";
-    if (match && match[1]) {
-      let field = match[1].toLowerCase();
-      if (field.endsWith("ies")) field = field.replace(/ies$/, "y");
-      else if (field.endsWith("s") && field !== "status") field = field.slice(0, -1);
-      const stopWords = ["the", "all", "different", "various", "some", "these", "those"];
-      if (!stopWords.includes(field)) {
-        targetField = field;
-      }
-    }
-    const hasTargetField = data.some((d) => d.metadata && d.metadata[targetField] !== void 0);
-    if (!hasTargetField && targetField === "category") {
-      if (data.some((d) => d.metadata && d.metadata["type"] !== void 0)) return "type";
-      if (data.some((d) => d.metadata && d.metadata["brand"] !== void 0)) return "brand";
-    }
-    return targetField;
-  }
-  /**
-   * Helper: Detect grouping values dynamically
+   * Helper: Detect categories in data
    */
-  static detectCategories(data, groupByField) {
+  static detectCategories(data) {
     const categories = /* @__PURE__ */ new Set();
     data.forEach((item) => {
       const meta = item.metadata || {};
-      if (meta[groupByField] !== void 0) {
-        const val = meta[groupByField];
-        if (Array.isArray(val)) val.forEach((v) => categories.add(String(v)));
-        else categories.add(String(val));
-      } else if (groupByField === "category") {
-        if (meta.type) categories.add(String(meta.type));
-        if (meta.tag) {
-          const tags = Array.isArray(meta.tag) ? meta.tag : [meta.tag];
-          tags.forEach((t) => categories.add(String(t)));
-        }
-        const categoryMatch = item.content.match(/(?:Category|Type|Class):\s*([^\n]+)/i);
-        if (categoryMatch) categories.add(categoryMatch[1].trim());
+      if (meta.category) {
+        categories.add(String(meta.category));
+      }
+      if (meta.type) {
+        categories.add(String(meta.type));
+      }
+      if (meta.tag) {
+        const tags = Array.isArray(meta.tag) ? meta.tag : [meta.tag];
+        tags.forEach((t) => categories.add(String(t)));
+      }
+      const contentCategories = Array.from(new Set(
+        Array.from(item.content.matchAll(/^\s*([^:\n]+):\s*(?:•|\*|-)*/gm)).map((match) => match[1].trim()).filter(Boolean)
+      ));
+      contentCategories.forEach((category) => categories.add(category));
+      const categoryMatch = item.content.match(/(?:Category|Type|Class):\s*([^\n]+)/i);
+      if (categoryMatch) {
+        categories.add(categoryMatch[1].trim());
       }
     });
     return Array.from(categories);
   }
   /**
-   * Helper: Aggregate data dynamically
+   * Helper: Aggregate data by category
    */
-  static aggregateByCategory(data, categories, groupByField) {
+  static aggregateByCategory(data, categories) {
     const result = {};
     categories.forEach((cat) => {
       result[cat] = 0;
     });
     data.forEach((item) => {
       const meta = item.metadata || {};
-      let itemCategory = "Other";
-      if (meta[groupByField] !== void 0) {
-        itemCategory = String(meta[groupByField]);
-      } else if (groupByField === "category" && meta.type) {
-        itemCategory = String(meta.type);
-      }
+      const itemCategory = meta.category || meta.type || "Other";
       if (Object.prototype.hasOwnProperty.call(result, itemCategory)) {
         result[itemCategory]++;
       } else {
@@ -4667,19 +4625,14 @@ var UITransformer = class {
     });
   }
   /**
-   * Helper: Calculate stock counts dynamically
+   * Helper: Calculate stock counts by category
    */
-  static calculateStockCounts(category, data, groupByField) {
+  static calculateStockCounts(category, data) {
     let inStock = 0;
     let outOfStock = 0;
     data.forEach((d) => {
       const meta = d.metadata || {};
-      let itemCategory = "Other";
-      if (meta[groupByField] !== void 0) {
-        itemCategory = String(meta[groupByField]);
-      } else if (groupByField === "category" && meta.type) {
-        itemCategory = String(meta.type);
-      }
+      const itemCategory = meta.category || meta.type || "Other";
       if (itemCategory === category) {
         if (this.determineStockStatus(d)) {
           inStock++;
@@ -4804,13 +4757,12 @@ DATA SHAPE per type:
 - text:       { "content": "<prose answer>" }
 
 DECISION RULES (follow strictly):
-1. IF the user explicitly asks for a "pie chart", "bar chart", or "table", you MUST output that exact type. Do not deviate from their request.
-2. bar_chart  \u2192 comparing quantities across categories (e.g. sales by region, price by product). Use this when there is only ONE value per category.
-3. line_chart \u2192 trends or changes over time (dates, months, years, sequential events)
-4. pie_chart  \u2192 proportional breakdown or percentage distribution
-5. radar_chart \u2192 comparing 2 or more products across MULTIPLE attributes.
-6. table      \u2192 multi-field structured records where each item has \u2265 3 attributes
-7. text       \u2192 conversational or free-form answers where no chart adds value
+1. bar_chart  \u2192 comparing quantities across categories (e.g. sales by region, price by product). Use this when there is only ONE value per category.
+2. line_chart \u2192 trends or changes over time (dates, months, years, sequential events)
+3. pie_chart  \u2192 proportional breakdown or percentage distribution
+4. radar_chart \u2192 comparing 2 or more products across MULTIPLE attributes (e.g. comparing features, ratings, or characteristics of 2 specific products). If the user asks to "compare" products and the data contains multiple dimensions or ratings for them, you MUST use this.
+5. table      \u2192 multi-field structured records where each item has \u2265 3 attributes
+6. text       \u2192 conversational or free-form answers where no chart adds value
 
 IMPORTANT:
 - Aggregate numeric values from the raw data \u2014 do not pass raw object arrays as data.
@@ -5968,12 +5920,10 @@ var PostgreSQLProvider = class extends BaseVectorProvider {
           embedding   VECTOR(${this.dimensions})
         )
       `);
-      const metric = this.config.distanceMetric || "cosine";
-      const indexOps = metric === "euclidean" ? "vector_l2_ops" : metric === "dotproduct" ? "vector_ip_ops" : "vector_cosine_ops";
       await client.query(`
         CREATE INDEX IF NOT EXISTS ${this.tableName}_embedding_idx
         ON ${this.tableName}
-        USING hnsw (embedding ${indexOps})
+        USING hnsw (embedding vector_cosine_ops)
       `);
     } finally {
       client.release();
@@ -6045,14 +5995,11 @@ var PostgreSQLProvider = class extends BaseVectorProvider {
     try {
       const efSearch = this.config.options.efSearch || Math.max(topK * 10, 40);
       await client.query(`SET LOCAL hnsw.ef_search = ${efSearch}`);
-      const metric = this.config.distanceMetric || "cosine";
-      const queryOp = metric === "euclidean" ? "<->" : metric === "dotproduct" ? "<#>" : "<=>";
-      const scoreExpr = metric === "euclidean" ? `1 / (1 + (embedding <-> $1::vector))` : metric === "dotproduct" ? `(embedding <#> $1::vector) * -1` : `1 - (embedding <=> $1::vector)`;
       const result = await client.query(
-        `SELECT id, content, metadata, ${scoreExpr} AS score
+        `SELECT id, content, metadata, 1 - (embedding <=> $1::vector) AS score
          FROM ${this.tableName}
          ${whereClause}
-         ORDER BY embedding ${queryOp} $1::vector
+         ORDER BY embedding <=> $1::vector
          LIMIT $2`,
         params
       );

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@retrivora-ai/rag-engine",
-  "version": "1.8.9",
+  "version": "1.9.0",
   "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/config/RagConfig.ts

@@ -44,8 +44,6 @@ export interface VectorDBConfig {
    * - searchFields?: string[] | string // optional override for which columns receive exact-match boosts
    */
   options: Record<string, unknown>;
-  /** Optional distance metric (defaults to cosine if not specified and supported by provider) */
-  distanceMetric?: 'cosine' | 'euclidean' | 'dotproduct';
 }
 
 // ---------------------------------------------------------------------------

package/src/providers/vectordb/ChromaDBProvider.ts

@@ -41,13 +41,9 @@ export class ChromaDBProvider extends BaseVectorProvider {
     } catch (err) {
       if (axios.isAxiosError(err) && err.response?.status === 404) {
         // Create the collection if it doesn't exist
-        const metric = this.config.distanceMetric || 'cosine';
-        const space = metric === 'euclidean' ? 'l2' : metric === 'dotproduct' ? 'ip' : 'cosine';
-
         console.log(`[ChromaDBProvider] ⏳ Collection "${this.indexName}" not found. Creating...`);
         const { data } = await this.http.post('/api/v1/collections', {
           name: this.indexName,
-          metadata: { "hnsw:space": space }
         });
         this.collectionId = data.id;
         console.log(`[ChromaDBProvider] ✅ Created collection "${this.indexName}" (id: ${this.collectionId})`);

package/src/providers/vectordb/MultiTablePostgresProvider.ts

@@ -66,13 +66,10 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
           embedding   VECTOR(${this.dimensions})
         )
       `);
-      const metric = this.config.distanceMetric || 'cosine';
-      const indexOps = metric === 'euclidean' ? 'vector_l2_ops' : metric === 'dotproduct' ? 'vector_ip_ops' : 'vector_cosine_ops';
-
       await client.query(`
         CREATE INDEX IF NOT EXISTS ${this.uploadTable}_embedding_idx
         ON ${this.uploadTable}
-        USING hnsw (embedding ${indexOps})
+        USING hnsw (embedding vector_cosine_ops)
       `);
 
       const res = await client.query(`
@@ -150,13 +147,10 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
         await client.query(createTableSql);
         
         // Create Index
-        const metric = this.config.distanceMetric || 'cosine';
-        const indexOps = metric === 'euclidean' ? 'vector_l2_ops' : metric === 'dotproduct' ? 'vector_ip_ops' : 'vector_cosine_ops';
-
         await client.query(`
           CREATE INDEX IF NOT EXISTS "${tableName}_embedding_idx"
           ON "${tableName}"
-          USING hnsw (embedding ${indexOps})
+          USING hnsw (embedding vector_cosine_ops)
         `);
         
         // Ensure this new table is added to our search scope
@@ -280,13 +274,6 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
         let sqlQuery = '';
         let params: unknown[] = [];
 
-        const metric = this.config.distanceMetric || 'cosine';
-        const scoreExpr = metric === 'euclidean' 
-          ? `1 / (1 + (embedding <-> $1::vector))` 
-          : metric === 'dotproduct' 
-          ? `(embedding <#> $1::vector) * -1` 
-          : `1 - (embedding <=> $1::vector)`;
-
         if (queryText) {
           const hasEntityHints = entityHints.length > 0;
           const exactNameScoreExpr = hasEntityHints
@@ -303,9 +290,9 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
           // Actual Hybrid Search: Semantic Vector Score + Full-Text Keyword Rank
           sqlQuery = `
             SELECT *, 
-             (${scoreExpr}) AS vector_score,
+             (1 - (embedding <=> $1::vector)) AS vector_score,
              COALESCE(ts_rank(to_tsvector('english', (to_jsonb(t) - 'embedding')::text), to_tsquery('english', $2)), 0) AS keyword_score,
-             ((${scoreExpr}) + (COALESCE(ts_rank(to_tsvector('english', (to_jsonb(t) - 'embedding')::text), to_tsquery('english', $2)), 0) * 2.0) ${exactNameScoreExpr}) AS hybrid_score
+             ((1 - (embedding <=> $1::vector)) + (COALESCE(ts_rank(to_tsvector('english', (to_jsonb(t) - 'embedding')::text), to_tsquery('english', $2)), 0) * 2.0) ${exactNameScoreExpr}) AS hybrid_score
             FROM "${table}" t
             ORDER BY hybrid_score DESC
             LIMIT 50
@@ -315,7 +302,7 @@ export class MultiTablePostgresProvider extends BaseVectorProvider {
           // Fallback to Vector-only Search
           sqlQuery = `
             SELECT *, 
-             (${scoreExpr}) AS hybrid_score
+             (1 - (embedding <=> $1::vector)) AS hybrid_score
             FROM "${table}" t
             ORDER BY hybrid_score DESC
             LIMIT 50

package/src/providers/vectordb/PostgreSQLProvider.ts

@@ -97,13 +97,10 @@ export class PostgreSQLProvider extends BaseVectorProvider {
           embedding   VECTOR(${this.dimensions})
         )
       `);
-      const metric = this.config.distanceMetric || 'cosine';
-      const indexOps = metric === 'euclidean' ? 'vector_l2_ops' : metric === 'dotproduct' ? 'vector_ip_ops' : 'vector_cosine_ops';
-      
       await client.query(`
         CREATE INDEX IF NOT EXISTS ${this.tableName}_embedding_idx
         ON ${this.tableName}
-        USING hnsw (embedding ${indexOps})
+        USING hnsw (embedding vector_cosine_ops)
       `);
     } finally {
       client.release();
@@ -185,19 +182,11 @@ export class PostgreSQLProvider extends BaseVectorProvider {
       const efSearch = (this.config.options.efSearch as number) || Math.max(topK * 10, 40);
       await client.query(`SET LOCAL hnsw.ef_search = ${efSearch}`);
 
-      const metric = this.config.distanceMetric || 'cosine';
-      const queryOp = metric === 'euclidean' ? '<->' : metric === 'dotproduct' ? '<#>' : '<=>';
-      const scoreExpr = metric === 'euclidean' 
-        ? `1 / (1 + (embedding <-> $1::vector))` 
-        : metric === 'dotproduct' 
-        ? `(embedding <#> $1::vector) * -1` 
-        : `1 - (embedding <=> $1::vector)`;
-
       const result = await client.query(
-        `SELECT id, content, metadata, ${scoreExpr} AS score
+        `SELECT id, content, metadata, 1 - (embedding <=> $1::vector) AS score
          FROM ${this.tableName}
          ${whereClause}
-         ORDER BY embedding ${queryOp} $1::vector
+         ORDER BY embedding <=> $1::vector
          LIMIT $2`,
         params
       );

package/src/providers/vectordb/QdrantProvider.ts

@@ -120,14 +120,11 @@ export class QdrantProvider extends BaseVectorProvider {
         const opts = this.config.options as Record<string, unknown>;
         const dimensionsForCreate = (opts.dimensions as number) || 1536;
 
-        const metric = this.config.distanceMetric || 'cosine';
-        const distance = metric === 'euclidean' ? 'Euclid' : metric === 'dotproduct' ? 'Dot' : 'Cosine';
-
         console.log(`[QdrantProvider] ⏳ Creating collection "${this.indexName}" (dimensions: ${dimensionsForCreate})...`);
         await this.http.put(`/collections/${this.indexName}`, {
           vectors: {
             size: dimensionsForCreate,
-            distance: distance,
+            distance: 'Cosine',
           },
         });
         console.log(`[QdrantProvider] ✅ Created collection "${this.indexName}"`);