Split off AI prompt into separate file, auto include taxonomy in prompt, create prompt debug page

inventory-server/src/prompts/product-validation.txt

@@ -0,0 +1,17 @@
+I will provide a JSON array with product data. Process the array by combining all products from validData and invalidData arrays into a single array, excluding any fields starting with “__”, such as “__index” or “__errors”. Process each product according to the reference guidelines below. If a field is not included in the data, do not include it in your response unless the specific field guidelines below say otherwise. Please respond with:
+
+Respond in the following JSON format:
+{
+  "correctedData": [], // Array of corrected products
+  "changes": [], // Array of strings describing each change made
+  "warnings": [] // Array of strings with warnings or suggestions for manual review
+}
+
+Using the provided guidelines, focus on:
+1. Correcting typos and any incorrect spelling or grammar
+2. Standardizing product names
+3. Correcting and enhancing descriptions by adding details, keywords, and SEO-friendly language
+4. Fixing any obvious errors in measurements, prices, or quantities
+5. Adding correct categories, themes, and colors
+
+Use only the provided data and your own knowledge to make changes. Do not make assumptions or make up information that you're not sure about. If you're unable to make a change you're confident about, leave the field as is.

inventory-server/src/routes/ai-validation.js

@@ -1,35 +1,253 @@
 const express = require('express');
 const router = express.Router();
 const OpenAI = require('openai');
+const fs = require('fs').promises;
+const path = require('path');
 
 const openai = new OpenAI({
   apiKey: process.env.OPENAI_API_KEY
 });
 
-// Helper function to create the prompt for product validation
+// Cache configuration
-function createValidationPrompt(products) {
+const CACHE_TTL = 60 * 60 * 1000; // 1 hour in milliseconds
-  return `You are a product data validation assistant. Please review the following product data and suggest corrections or improvements. Focus on:
-1. Standardizing product names and descriptions
-2. Fixing any obvious errors in measurements, prices, or quantities
-3. Ensuring consistency in formatting
-4. Flagging any suspicious or invalid values
 
-Here is the product data to validate:
+// Cache structure with TTL
-${JSON.stringify(products, null, 2)}
+let cache = {
+  taxonomyData: null,
+  validationPrompt: null,
+  lastUpdated: null
+};
 
-Please respond with:
+// Function to check if cache is valid
-1. The corrected product data in the exact same JSON format
+function isCacheValid() {
-2. A list of changes made and why
+  return cache.lastUpdated && (Date.now() - cache.lastUpdated) < CACHE_TTL;
-3. Any warnings or suggestions for manual review
-
-Respond in the following JSON format:
-{
-  "correctedData": [], // Array of corrected products
-  "changes": [], // Array of changes made
-  "warnings": [] // Array of warnings or suggestions
-}`;
 }
 
+// Function to clear cache
+function clearCache() {
+  cache = {
+    taxonomyData: null,
+    validationPrompt: null,
+    lastUpdated: null
+  };
+}
+
+// Debug endpoint to view prompt and cache status
+router.get('/debug', async (req, res) => {
+  try {
+    console.log('Debug endpoint called');
+    const pool = req.app.locals.pool;
+    
+    // Load taxonomy data first
+    console.log('Loading taxonomy data...');
+    const taxonomy = await getTaxonomyData(pool);
+    console.log('Taxonomy data loaded:', {
+      categoriesCount: taxonomy.categories.length,
+      themesCount: taxonomy.themes.length,
+      colorsCount: taxonomy.colors.length,
+      taxCodesCount: taxonomy.taxCodes.length,
+      sizeCategoriesCount: taxonomy.sizeCategories.length
+    });
+
+    // Then load the prompt
+    console.log('Loading prompt...');
+    const currentPrompt = await loadPrompt(pool);
+    const sampleData = [{ name: "Sample Product" }];
+    const fullPrompt = currentPrompt + '\n' + JSON.stringify(sampleData, null, 2);
+
+    const response = {
+      cacheStatus: {
+        isCacheValid: isCacheValid(),
+        lastUpdated: cache.lastUpdated ? new Date(cache.lastUpdated).toISOString() : null,
+        timeUntilExpiry: cache.lastUpdated ? 
+          Math.max(0, CACHE_TTL - (Date.now() - cache.lastUpdated)) / 1000 + ' seconds' : 
+          'expired',
+      },
+      taxonomyStats: taxonomy ? {
+        categories: countItems(taxonomy.categories),
+        themes: taxonomy.themes.length,
+        colors: taxonomy.colors.length,
+        taxCodes: taxonomy.taxCodes.length,
+        sizeCategories: taxonomy.sizeCategories.length
+      } : null,
+      basePrompt: currentPrompt,
+      sampleFullPrompt: fullPrompt,
+      promptLength: fullPrompt.length,
+    };
+
+    console.log('Sending response with stats:', response.taxonomyStats);
+    res.json(response);
+  } catch (error) {
+    console.error('Debug endpoint error:', error);
+    res.status(500).json({ error: error.message });
+  }
+});
+
+// Helper function to count total items in hierarchical structure
+function countItems(items) {
+  return items.reduce((count, item) => {
+    return count + 1 + (item.subcategories ? countItems(item.subcategories) : 0);
+  }, 0);
+}
+
+// Force cache refresh endpoint
+router.post('/refresh-cache', async (req, res) => {
+  try {
+    clearCache();
+    const pool = req.app.locals.pool;
+    await loadPrompt(pool); // This will rebuild the cache
+    res.json({ 
+      success: true, 
+      message: 'Cache refreshed successfully',
+      newCacheTime: new Date(cache.lastUpdated).toISOString()
+    });
+  } catch (error) {
+    console.error('Cache refresh error:', error);
+    res.status(500).json({ error: error.message });
+  }
+});
+
+// Function to fetch and format taxonomy data
+async function getTaxonomyData(pool) {
+  if (cache.taxonomyData && isCacheValid()) {
+    return cache.taxonomyData;
+  }
+
+  // Fetch categories with hierarchy
+  const [categories] = await pool.query(`
+    SELECT cat_id, name, master_cat_id, level_order 
+    FROM (
+      SELECT cat_id,name,NULL AS master_cat_id,1 AS level_order 
+      FROM product_categories s 
+      WHERE type=10 
+      UNION ALL 
+      SELECT c.cat_id,c.name,c.master_cat_id,2 AS level_order 
+      FROM product_categories c 
+      JOIN product_categories s ON c.master_cat_id=s.cat_id 
+      WHERE c.type=11 AND s.type=10 
+      UNION ALL 
+      SELECT sc.cat_id,sc.name,sc.master_cat_id,3 AS level_order 
+      FROM product_categories sc 
+      JOIN product_categories c ON sc.master_cat_id=c.cat_id 
+      JOIN product_categories s ON c.master_cat_id=s.cat_id 
+      WHERE sc.type=12 AND c.type=11 AND s.type=10 
+      UNION ALL 
+      SELECT ssc.cat_id,ssc.name,ssc.master_cat_id,4 AS level_order 
+      FROM product_categories ssc 
+      JOIN product_categories sc ON ssc.master_cat_id=sc.cat_id 
+      JOIN product_categories c ON sc.master_cat_id=c.cat_id 
+      JOIN product_categories s ON c.master_cat_id=s.cat_id 
+      WHERE ssc.type=13 AND sc.type=12 AND c.type=11 AND s.type=10
+    ) AS hierarchy 
+    ORDER BY level_order,cat_id
+  `);
+
+  // Fetch themes with hierarchy
+  const [themes] = await pool.query(`
+    SELECT cat_id, name, master_cat_id, level_order 
+    FROM (
+      SELECT t.cat_id,t.name,null as master_cat_id,1 AS level_order 
+      FROM product_categories t 
+      WHERE t.type=20 
+      UNION ALL 
+      SELECT ts.cat_id,ts.name,ts.master_cat_id,2 AS level_order 
+      FROM product_categories ts 
+      JOIN product_categories t ON ts.master_cat_id=t.cat_id 
+      WHERE ts.type=21 AND t.type=20
+    ) AS hierarchy 
+    ORDER BY level_order,name
+  `);
+
+  // Fetch colors
+  const [colors] = await pool.query('SELECT color, name FROM product_color_list ORDER BY name');
+
+  // Fetch tax codes
+  const [taxCodes] = await pool.query('SELECT tax_code_id, name FROM product_tax_codes ORDER BY name');
+
+  // Fetch size categories
+  const [sizeCategories] = await pool.query('SELECT cat_id, name FROM product_categories WHERE type=50 ORDER BY name');
+
+  // Format categories into a hierarchical structure
+  const formatHierarchy = (items, level = 1, parentId = null) => {
+    return items
+      .filter(item => item.level_order === level && item.master_cat_id === parentId)
+      .map(item => {
+        const children = formatHierarchy(items, level + 1, item.cat_id);
+        return {
+          name: item.name,
+          ...(children.length > 0 ? { subcategories: children } : {})
+        };
+      });
+  };
+
+  // Format themes similarly but with only two levels
+  const formatThemes = (items) => {
+    return items
+      .filter(item => item.level_order === 1)
+      .map(item => {
+        const subthemes = items
+          .filter(subitem => subitem.master_cat_id === item.cat_id)
+          .map(subitem => subitem.name);
+        return {
+          name: item.name,
+          ...(subthemes.length > 0 ? { subthemes } : {})
+        };
+      });
+  };
+
+  cache.taxonomyData = {
+    categories: formatHierarchy(categories),
+    themes: formatThemes(themes),
+    colors: colors.map(c => c.name),
+    taxCodes: (taxCodes || []).map(tc => ({ id: tc.tax_code_id, name: tc.name })),
+    sizeCategories: (sizeCategories || []).map(sc => ({ id: sc.cat_id, name: sc.name }))
+  };
+  cache.lastUpdated = Date.now();
+
+  return cache.taxonomyData;
+}
+
+// Load the prompt from file and inject taxonomy data
+async function loadPrompt(pool) {
+  if (cache.validationPrompt && isCacheValid()) {
+    return cache.validationPrompt;
+  }
+
+  const promptPath = path.join(__dirname, '..', 'prompts', 'product-validation.txt');
+  const basePrompt = await fs.readFile(promptPath, 'utf8');
+  
+  // Get taxonomy data
+  const taxonomy = await getTaxonomyData(pool);
+  
+  // Format taxonomy data for the prompt
+  const taxonomySection = `
+Available Categories:
+${JSON.stringify(taxonomy.categories)}
+
+Available Themes:
+${JSON.stringify(taxonomy.themes)}
+
+Available Colors:
+${JSON.stringify(taxonomy.colors)}
+
+Available Tax Codes:
+${JSON.stringify(taxonomy.taxCodes)}
+
+Available Size Categories:
+${JSON.stringify(taxonomy.sizeCategories)}
+
+Here is the product data to validate:`;
+
+  // Combine the prompt sections
+  cache.validationPrompt = basePrompt + '\n' + taxonomySection;
+  cache.lastUpdated = Date.now();
+
+  return cache.validationPrompt;
+}
+
+// Set up cache clearing interval
+setInterval(clearCache, CACHE_TTL);
+
 router.post('/validate', async (req, res) => {
   try {
     const { products } = req.body;
@@ -40,20 +258,22 @@ router.post('/validate', async (req, res) => {
       return res.status(400).json({ error: 'Products must be an array' });
     }
 
-    const prompt = createValidationPrompt(products);
+    // Load the prompt and append the products data
-    console.log('📝 Generated prompt:', prompt);
+    const basePrompt = await loadPrompt(req.app.locals.pool);
+    const fullPrompt = basePrompt + '\n' + JSON.stringify(products, null, 2);
+    console.log('📝 Generated prompt:', fullPrompt);
 
     console.log('🤖 Sending request to OpenAI...');
     const completion = await openai.chat.completions.create({
-      model: "gpt-4o-mini",
+      model: "gpt-4-turbo-preview",
       messages: [
         {
           role: "system",
-          content: "You are a product data validation assistant that helps ensure product data is accurate, consistent, and properly formatted."
+          content: "You are a specialized e-commerce product data processor for a crafting supplies website tasked with providing complete, correct, appealing, and SEO-friendly product listings. You should write professionally, but in a friendly and engaging tone."
         },
         {
           role: "user",
-          content: prompt
+          content: fullPrompt
         }
       ],
       temperature: 0.3,

inventory/src/App.tsx

@@ -17,6 +17,7 @@ import { Vendors } from '@/pages/Vendors';
 import { Categories } from '@/pages/Categories';
 import { Import } from '@/pages/Import';
 import { ChakraProvider } from '@chakra-ui/react';
+import { AiValidationDebug } from "@/pages/AiValidationDebug"
 
 const queryClient = new QueryClient();
 
@@ -71,6 +72,7 @@ function App() {
             <Route path="/analytics" element={<Analytics />} />
             <Route path="/settings" element={<Settings />} />
             <Route path="/forecasting" element={<Forecasting />} />
+            <Route path="/ai-validation/debug" element={<AiValidationDebug />} />
             <Route path="*" element={<Navigate to="/" replace />} />
           </Route>
         </Routes>

inventory/src/pages/AiValidationDebug.tsx

@@ -0,0 +1,206 @@
+import { useEffect, useState } from "react"
+import { Button } from "@/components/ui/button"
+import { Card, CardContent, CardHeader, CardTitle } from "@/components/ui/card"
+import { ScrollArea } from "@/components/ui/scroll-area"
+import { Code } from "@/components/ui/code"
+import { useToast } from "@/hooks/use-toast"
+import { Loader2 } from "lucide-react"
+import config from "@/config"
+
+interface CacheStatus {
+  isCacheValid: boolean
+  lastUpdated: string | null
+  timeUntilExpiry: string
+}
+
+interface TaxonomyStats {
+  categories: number
+  themes: number
+  colors: number
+  taxCodes: number
+  sizeCategories: number
+}
+
+interface DebugData {
+  cacheStatus: CacheStatus
+  taxonomyStats: TaxonomyStats | null
+  basePrompt: string
+  sampleFullPrompt: string
+  promptLength: number
+}
+
+export function AiValidationDebug() {
+  const [isLoading, setIsLoading] = useState(false)
+  const [debugData, setDebugData] = useState<DebugData | null>(null)
+  const { toast } = useToast()
+
+  const fetchDebugData = async () => {
+    setIsLoading(true)
+    try {
+      const response = await fetch(`${config.apiUrl}/ai-validation/debug`)
+      if (!response.ok) {
+        throw new Error('Failed to fetch debug data')
+      }
+      const data = await response.json()
+      setDebugData(data)
+    } catch (error) {
+      console.error('Error fetching debug data:', error)
+      toast({
+        variant: "destructive",
+        title: "Error",
+        description: error instanceof Error ? error.message : "Failed to fetch debug data"
+      })
+    } finally {
+      setIsLoading(false)
+    }
+  }
+
+  const refreshCache = async () => {
+    if (!confirm('Are you sure you want to refresh the cache?')) return
+
+    setIsLoading(true)
+    try {
+      const response = await fetch(`${config.apiUrl}/ai-validation/refresh-cache`, {
+        method: 'POST'
+      })
+      if (!response.ok) {
+        throw new Error('Failed to refresh cache')
+      }
+      const data = await response.json()
+      if (data.success) {
+        toast({
+          title: "Success",
+          description: "Cache refreshed successfully"
+        })
+        fetchDebugData()
+      } else {
+        throw new Error(data.error || 'Failed to refresh cache')
+      }
+    } catch (error) {
+      console.error('Error refreshing cache:', error)
+      toast({
+        variant: "destructive",
+        title: "Error",
+        description: error instanceof Error ? error.message : "Failed to refresh cache"
+      })
+    } finally {
+      setIsLoading(false)
+    }
+  }
+
+  useEffect(() => {
+    fetchDebugData()
+  }, [])
+
+  return (
+    <div className="container mx-auto py-6 space-y-6">
+      <div className="flex items-center justify-between">
+        <h1 className="text-3xl font-bold tracking-tight">AI Validation Debug</h1>
+        <div className="space-x-4">
+          <Button
+            variant="outline"
+            onClick={fetchDebugData}
+            disabled={isLoading}
+          >
+            {isLoading && <Loader2 className="mr-2 h-4 w-4 animate-spin" />}
+            Refresh Data
+          </Button>
+          <Button
+            variant="outline"
+            onClick={refreshCache}
+            disabled={isLoading}
+          >
+            {isLoading && <Loader2 className="mr-2 h-4 w-4 animate-spin" />}
+            Force Cache Refresh
+          </Button>
+        </div>
+      </div>
+
+      {debugData && (
+        <div className="grid grid-cols-1 md:grid-cols-3 gap-6">
+          <Card>
+            <CardHeader>
+              <CardTitle>Cache Status</CardTitle>
+            </CardHeader>
+            <CardContent>
+              <div className="space-y-2">
+                <div>Valid: {debugData.cacheStatus.isCacheValid ? "Yes" : "No"}</div>
+                <div>Last Updated: {debugData.cacheStatus.lastUpdated || "never"}</div>
+                <div>Expires in: {debugData.cacheStatus.timeUntilExpiry}</div>
+              </div>
+            </CardContent>
+          </Card>
+
+          <Card>
+            <CardHeader>
+              <CardTitle>Taxonomy Stats</CardTitle>
+            </CardHeader>
+            <CardContent>
+              {debugData.taxonomyStats ? (
+                <div className="space-y-2">
+                  <div>Categories: {debugData.taxonomyStats.categories}</div>
+                  <div>Themes: {debugData.taxonomyStats.themes}</div>
+                  <div>Colors: {debugData.taxonomyStats.colors}</div>
+                  <div>Tax Codes: {debugData.taxonomyStats.taxCodes}</div>
+                  <div>Size Categories: {debugData.taxonomyStats.sizeCategories}</div>
+                </div>
+              ) : (
+                <div>No taxonomy data available</div>
+              )}
+            </CardContent>
+          </Card>
+
+          <Card>
+            <CardHeader>
+              <CardTitle>Prompt Length</CardTitle>
+            </CardHeader>
+            <CardContent>
+              <div className="space-y-4">
+                <div className="space-y-2">
+                  <div>Characters: {debugData.promptLength}</div>
+                  <div>Tokens (est.): ~{Math.round(debugData.promptLength / 4)}</div>
+                </div>
+                <div className="space-y-2">
+                  <label htmlFor="costPerMillion" className="text-sm text-muted-foreground">
+                    Cost per million tokens ($)
+                  </label>
+                  <input
+                    id="costPerMillion"
+                    type="number"
+                    className="w-full px-3 py-2 border rounded-md"
+                    defaultValue="3"
+                    onChange={(e) => {
+                      const costPerMillion = parseFloat(e.target.value)
+                      if (!isNaN(costPerMillion)) {
+                        const tokens = Math.round(debugData.promptLength / 4)
+                        const cost = (tokens / 1_000_000) * costPerMillion * 100 // Convert to cents
+                        const costElement = document.getElementById('tokenCost')
+                        if (costElement) {
+                          costElement.textContent = cost.toFixed(1)
+                        }
+                      }
+                    }}
+                  />
+                  <div className="text-sm">
+                    Cost: <span id="tokenCost">{((Math.round(debugData.promptLength / 4) / 1_000_000) * 3 * 100).toFixed(1)}</span>¢
+                  </div>
+                </div>
+              </div>
+            </CardContent>
+          </Card>
+
+          <Card className="col-span-full">
+            <CardHeader>
+              <CardTitle>Full Sample Prompt</CardTitle>
+            </CardHeader>
+            <CardContent>
+              <ScrollArea className="h-[500px] w-full rounded-md border p-4">
+                <Code className="whitespace-pre-wrap">{debugData.sampleFullPrompt}</Code>
+              </ScrollArea>
+            </CardContent>
+          </Card>
+        </div>
+      )}
+    </div>
+  )
+} 

inventory/src/pages/Import.tsx

@@ -27,7 +27,7 @@ const BASE_IMPORT_FIELDS = [
     label: "UPC",
     key: "upc",
     description: "Universal Product Code/Barcode",
-    alternateMatches: ["upc","UPC","barcode", "bar code", "JAN", "EAN"],
+    alternateMatches: ["barcode", "bar code", "jan", "ean"],
     fieldType: { type: "input" },
     width: 140,
     validations: [
@@ -94,7 +94,7 @@ const BASE_IMPORT_FIELDS = [
     label: "MSRP",
     key: "msrp",
     description: "Manufacturer's Suggested Retail Price",
-    alternateMatches: ["retail", "retail price", "sugg retail", "price", "sugg. Retail","msrp","MSRP"],
+    alternateMatches: ["retail", "retail price", "sugg retail", "price", "sugg. retail","default price"],
     fieldType: { 
       type: "input",
       price: true 
@@ -136,7 +136,7 @@ const BASE_IMPORT_FIELDS = [
     label: "Case Pack",
     key: "case_qty",
     description: "Number of units per case",
-    alternateMatches: ["mc qty","MC Qty","case qty","Case Qty"],
+    alternateMatches: ["mc qty","case qty","case pack"],
     fieldType: { type: "input" },
     width: 50,
     validations: [
@@ -208,6 +208,7 @@ const BASE_IMPORT_FIELDS = [
     label: "Weight",
     key: "weight",
     description: "Product weight (in lbs)",
+    alternateMatches: ["weight (lbs.)"],
     fieldType: { type: "input" },
     width: 100,
     validations: [
@@ -295,6 +296,7 @@ const BASE_IMPORT_FIELDS = [
     label: "Description",
     key: "description",
     description: "Detailed product description",
+    alternateMatches: ["details/description"],
     fieldType: { 
       type: "input",
       multiline: true