Add AI configuration guide and test script for real AI integration

AI_CONFIGURATION.md

@@ -0,0 +1,141 @@
+# 🤖 AI Configuration Guide
+
+## 🔧 **Fixed Issues:**
+
+### ✅ **Real AI Integration (No More Mock Responses)**
+
+The chat API now uses **real AI** instead of template responses:
+
+1. **Trained Model Priority**: Uses your trained model if available
+2. **HuggingFace API Fallback**: Uses HuggingFace Inference API
+3. **Smart Mock Fallback**: Only uses mock responses as last resort
+
+### ✅ **AI Response Flow:**
+
+```
+User Question → Trained Model → HuggingFace API → Smart Mock
+```
+
+## 🚀 **How It Works:**
+
+### **1. Trained Model (Best)**
+- If `./models/textilindo-trained` exists
+- Uses your custom-trained model
+- Provides most accurate responses
+
+### **2. HuggingFace API (Good)**
+- Requires `HUGGINGFACE_API_KEY` environment variable
+- Uses powerful pre-trained models
+- Good for general questions
+
+### **3. Smart Mock (Fallback)**
+- Only when AI models fail
+- Improved keyword matching
+- Better response relevance
+
+## 🔑 **Setup HuggingFace API Key:**
+
+### **Option 1: Environment Variable**
+```bash
+export HUGGINGFACE_API_KEY=your_api_key_here
+```
+
+### **Option 2: HuggingFace Space Settings**
+1. Go to your space settings
+2. Add environment variable: `HUGGINGFACE_API_KEY`
+3. Set value to your HuggingFace API key
+
+### **Get API Key:**
+1. Visit: https://huggingface.co/settings/tokens
+2. Create new token with "Read" permissions
+3. Copy the token
+
+## 🧪 **Test AI Integration:**
+
+### **Test Questions:**
+```bash
+# Test 1: Operating hours
+curl -X POST "https://harismlnaslm-Textilindo-AI.hf.space/chat" \
+  -H "Content-Type: application/json" \
+  -d '{"message": "Jam berapa Textilindo buka?"}'
+
+# Test 2: Location
+curl -X POST "https://harismlnaslm-Textilindo-AI.hf.space/chat" \
+  -H "Content-Type: application/json" \
+  -d '{"message": "dimana lokasi textilindo?"}'
+
+# Test 3: Shipping
+curl -X POST "https://harismlnaslm-Textilindo-AI.hf.space/chat" \
+  -H "Content-Type: application/json" \
+  -d '{"message": "apa ada gratis ongkir?"}'
+```
+
+## 📊 **Expected Results:**
+
+### **Before (Mock Responses):**
+```json
+{
+  "message": "Jam berapa Textilindo buka?",
+  "response": "Textilindo berkantor pusat di Jl. Raya Prancis...",
+  "status": "success"
+}
+```
+
+### **After (Real AI):**
+```json
+{
+  "message": "Jam berapa Textilindo buka?",
+  "response": "Jam operasional Senin-Jumat 08:00-17:00, Sabtu 08:00-12:00.",
+  "status": "success"
+}
+```
+
+## 🎯 **Training Your Model:**
+
+### **1. Start Training:**
+```bash
+curl -X POST "https://harismlnaslm-Textilindo-AI.hf.space/api/train/start" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model_name": "distilgpt2",
+    "dataset_path": "data/lora_dataset_20250910_145055.jsonl",
+    "max_samples": 20,
+    "epochs": 1
+  }'
+```
+
+### **2. Monitor Progress:**
+```bash
+curl "https://harismlnaslm-Textilindo-AI.hf.space/api/train/status"
+```
+
+### **3. Test Trained Model:**
+```bash
+curl -X POST "https://harismlnaslm-Textilindo-AI.hf.space/api/train/test"
+```
+
+## ✅ **Verification:**
+
+### **Check AI Status:**
+```bash
+curl "https://harismlnaslm-Textilindo-AI.hf.space/health"
+```
+
+### **Test Chat:**
+```bash
+curl -X POST "https://harismlnaslm-Textilindo-AI.hf.space/chat" \
+  -H "Content-Type: application/json" \
+  -d '{"message": "Jam berapa Textilindo buka?"}'
+```
+
+## 🎉 **Success Indicators:**
+
+- ✅ **Relevant Responses**: AI answers match the questions
+- ✅ **No More Mock Fallbacks**: Real AI responses
+- ✅ **Trained Model Priority**: Uses your custom model
+- ✅ **HuggingFace API**: Works with API key
+- ✅ **Smart Fallbacks**: Better error handling
+
+---
+
+**Your AI is now using real intelligence instead of templates! 🚀**

test_api_simple.py

@@ -0,0 +1,90 @@
+#!/usr/bin/env python3
+"""
+Simple test for the pure API
+"""
+
+import requests
+import json
+
+def test_api():
+    base_url = "https://harismlnaslm-Textilindo-AI.hf.space"
+    
+    print("🧪 Testing Textilindo AI Pure API")
+    print("=" * 50)
+    
+    # Test 1: API Info
+    print("1️⃣ Testing API Info...")
+    try:
+        response = requests.get(f"{base_url}/")
+        print(f"Status: {response.status_code}")
+        if response.status_code == 200:
+            try:
+                data = response.json()
+                print(f"✅ API Info: {data.get('name', 'Unknown')}")
+                print(f"   Hardware: {data.get('hardware', 'Unknown')}")
+                print(f"   Status: {data.get('status', 'Unknown')}")
+            except:
+                print("❌ Response is not JSON (still serving HTML)")
+        else:
+            print(f"❌ Error: {response.status_code}")
+    except Exception as e:
+        print(f"❌ Error: {e}")
+    
+    # Test 2: Health Check
+    print("\n2️⃣ Testing Health Check...")
+    try:
+        response = requests.get(f"{base_url}/health")
+        print(f"Status: {response.status_code}")
+        if response.status_code == 200:
+            data = response.json()
+            print(f"✅ Health: {data.get('status', 'Unknown')}")
+        else:
+            print(f"❌ Error: {response.status_code}")
+    except Exception as e:
+        print(f"❌ Error: {e}")
+    
+    # Test 3: GPU Info
+    print("\n3️⃣ Testing GPU Info...")
+    try:
+        response = requests.get(f"{base_url}/api/train/gpu")
+        print(f"Status: {response.status_code}")
+        if response.status_code == 200:
+            data = response.json()
+            print(f"✅ GPU: {data}")
+        else:
+            print(f"❌ Error: {response.status_code}")
+    except Exception as e:
+        print(f"❌ Error: {e}")
+    
+    # Test 4: Training Data
+    print("\n4️⃣ Testing Training Data...")
+    try:
+        response = requests.get(f"{base_url}/api/train/data")
+        print(f"Status: {response.status_code}")
+        if response.status_code == 200:
+            data = response.json()
+            print(f"✅ Data Files: {data.get('count', 0)}")
+            for file in data.get('files', []):
+                print(f"   📁 {file.get('name', 'Unknown')}: {file.get('lines', 0)} lines")
+        else:
+            print(f"❌ Error: {response.status_code}")
+    except Exception as e:
+        print(f"❌ Error: {e}")
+    
+    # Test 5: Chat API
+    print("\n5️⃣ Testing Chat API...")
+    try:
+        response = requests.post(f"{base_url}/chat", json={"message": "dimana lokasi textilindo?"})
+        print(f"Status: {response.status_code}")
+        if response.status_code == 200:
+            data = response.json()
+            print(f"✅ Chat Response: {data.get('response', 'No response')}")
+        else:
+            print(f"❌ Error: {response.status_code}")
+    except Exception as e:
+        print(f"❌ Error: {e}")
+    
+    print("\n🎉 API Test Complete!")
+
+if __name__ == "__main__":
+    test_api()

test_chat_ai.py

@@ -0,0 +1,54 @@
+#!/usr/bin/env python3
+"""
+Test script to verify AI chat integration is working
+"""
+
+import requests
+import json
+
+def test_chat_ai():
+    base_url = "https://harismlnaslm-Textilindo-AI.hf.space"
+    
+    print("🤖 Testing AI Chat Integration")
+    print("=" * 50)
+    
+    # Test questions
+    test_questions = [
+        "Jam berapa Textilindo buka?",
+        "dimana lokasi textilindo?",
+        "apa ada gratis ongkir?",
+        "berapa ketentuan pembelian?",
+        "apa bisa dikirimkan sample?"
+    ]
+    
+    for i, question in enumerate(test_questions, 1):
+        print(f"\n{i}️⃣ Testing: '{question}'")
+        
+        try:
+            response = requests.post(
+                f"{base_url}/chat",
+                json={"message": question},
+                headers={"Content-Type": "application/json"}
+            )
+            
+            if response.status_code == 200:
+                data = response.json()
+                ai_response = data.get('response', 'No response')
+                print(f"✅ AI Response: {ai_response}")
+                
+                # Check if response is relevant
+                if question.lower() in ai_response.lower() or any(word in ai_response.lower() for word in question.lower().split()):
+                    print("✅ Response appears relevant")
+                else:
+                    print("⚠️ Response might not be relevant")
+                    
+            else:
+                print(f"❌ Error: {response.status_code} - {response.text}")
+                
+        except Exception as e:
+            print(f"❌ Error: {e}")
+    
+    print("\n🎉 Chat AI Test Complete!")
+
+if __name__ == "__main__":
+    test_chat_ai()