Delete app.py

# =====================
# 🦁 SIMBA AI - BACKEND API ONLY
# =====================
# Provides REST API for your custom frontend
# No Gradio interface - Pure backend
# =====================

from flask import Flask, request, jsonify, send_from_directory
from flask_cors import CORS
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from sentence_transformers import SentenceTransformer
import faiss
import numpy as np
import time
import os

print("🚀 Initializing Simba AI Backend API...")

app = Flask(__name__)
CORS(app) # Enable CORS for your frontend

# =====================
# LOAD AI MODEL
# =====================

model_name = "microsoft/DialoGPT-large"

try:
print("📥 Loading AI model...")
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token

model = AutoModelForCausalLM.from_pretrained(
model_name,
torch_dtype=torch.float16,
device_map="auto",
)
print("✅ Simba AI Model Loaded Successfully!")
except Exception as e:
print(f"❌ Model loading error: {e}")
model_name = "microsoft/DialoGPT-medium"
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token
model = AutoModelForCausalLM.from_pretrained(model_name)
print("✅ Light model loaded!")

# =====================
# AFRICAN KNOWLEDGE BASE
# =====================

simba_knowledge_base = [
# CODING
{"question": "Python add function", "answer": "def add(a, b): return a + b"},
{"question": "Factorial function", "answer": "def factorial(n): return 1 if n == 0 else n * factorial(n-1)"},
{"question": "Reverse string function", "answer": "def reverse_string(s): return s[::-1]"},
{"question": "Check even number", "answer": "def is_even(n): return n % 2 == 0"},
{"question": "Multiply function", "answer": "def multiply(x, y): return x * y"},
{"question": "Yoruba greeting function", "answer": "def yoruba_greeting(): return 'Báwo ni'"},

# MATH
{"question": "15 + 27", "answer": "42"},
{"question": "8 × 7", "answer": "56"},
{"question": "100 - 45", "answer": "55"},
{"question": "12 × 12", "answer": "144"},
{"question": "25% of 200", "answer": "50"},

# YORUBA
{"question": "Hello in Yoruba", "answer": "Báwo ni"},
{"question": "Thank you in Yoruba", "answer": "Ẹ sé"},
{"question": "How are you in Yoruba", "answer": "Ṣe daadaa ni"},
{"question": "Good morning in Yoruba", "answer": "Ẹ káàrọ̀"},
{"question": "Good night in Yoruba", "answer": "O dàárọ̀"},
{"question": "Please in Yoruba", "answer": "Jọ̀wọ́"},

# SWAHILI
{"question": "Hello in Swahili", "answer": "Hujambo"},
{"question": "Thank you in Swahili", "answer": "Asante"},

# IGBO
{"question": "Hello in Igbo", "answer": "Nnọọ"},
{"question": "Thank you in Igbo", "answer": "Daalụ"},

# HAUSA
{"question": "Hello in Hausa", "answer": "Sannu"},
{"question": "Thank you in Hausa", "answer": "Na gode"},

# AFRICAN INNOVATION
{"question": "M-Pesa", "answer": "Mobile money service launched in Kenya in 2007"},
{"question": "Andela", "answer": "Trains African software developers for global companies"},
]

print(f"✅ African Knowledge Base: {len(simba_knowledge_base)} entries")

# =====================
# SEARCH SYSTEM
# =====================

try:
embedder = SentenceTransformer('all-MiniLM-L6-v2')
questions = [item["question"] for item in simba_knowledge_base]
question_embeddings = embedder.encode(questions)

dimension = question_embeddings.shape[1]
index = faiss.IndexFlatIP(dimension)
faiss.normalize_L2(question_embeddings)
index.add(question_embeddings)
print("✅ Search System Ready!")
except Exception as e:
print(f"❌ Search system error: {e}")
index = None

def simba_search(query, top_k=2):
"""Search African knowledge base"""
if index is None:
return simba_knowledge_base[:top_k]

try:
query_embedding = embedder.encode([query])
faiss.normalize_L2(query_embedding)
scores, indices = index.search(query_embedding, top_k)

results = []
for i, idx in enumerate(indices[0]):
if idx < len(simba_knowledge_base):
results.append({
"question": simba_knowledge_base[idx]["question"],
"answer": simba_knowledge_base[idx]["answer"],
"score": scores[0][i]
})
return results
except:
return simba_knowledge_base[:top_k]

# =====================
# SIMBA AI CORE FUNCTION
# =====================

def generate_simba_response(message):
"""Core function to generate Simba AI response"""

start_time = time.time()

# Quick responses for common greetings
quick_responses = {
"hello": "🦁 Báwo ni! Hello! I'm Simba AI, the first African LLM.",
"hi": "🦁 Báwo ni! Welcome to Simba AI!",
"hey": "🦁 Hello! I'm Simba AI, specializing in African languages and coding.",
}

lower_message = message.lower().strip()
if lower_message in quick_responses:
return {
"response": quick_responses[lower_message],
"response_time": round(time.time() - start_time, 2),
"knowledge_used": ["quick_response"]
}

try:
# Search for relevant knowledge
search_results = simba_search(message, top_k=2)

# Build context
context = "African Knowledge Reference:\n"
for i, result in enumerate(search_results, 1):
context += f"{i}. {result['question']}: {result['answer']}\n"

# Build prompt
prompt = f"User: {message}\nAfrican Knowledge: {context}\nSimba AI:"

# Generate response
inputs = tokenizer.encode(prompt, return_tensors="pt", max_length=512, truncation=True)

with torch.no_grad():
outputs = model.generate(
inputs,
max_new_tokens=100,
temperature=0.7,
do_sample=True,
pad_token_id=tokenizer.eos_token_id,
)

full_response = tokenizer.decode(outputs[0], skip_special_tokens=True)

# Extract response
if "Simba AI:" in full_response:
response = full_response.split("Simba AI:")[-1].strip()
else:
response = full_response[len(prompt):].strip()

if not response.startswith("🦁"):
response = f"🦁 {response}"

response_time = round(time.time() - start_time, 2)

return {
"response": response,
"response_time": response_time,
"knowledge_used": [r["question"] for r in search_results],
"model": model_name
}

except Exception as e:
return {
"response": f"🦁 Simba AI is currently learning. Please try again!",
"response_time": round(time.time() - start_time, 2),
"error": str(e)
}

# =====================
# API ROUTES
# =====================

@app .route('/')
def home():
return jsonify({
"message": "🦁 Simba AI Backend API - First African LLM",
"status": "running",
"endpoints": {
"/api/chat": "POST - Chat with Simba AI",
"/api/health": "GET - Health check",
"/api/info": "GET - API information"
}
})

@app .route('/api/health')
def health_check():
return jsonify({
"status": "healthy",
"model": model_name,
"timestamp": time.time()
})

@app .route('/api/info')
def api_info():
return jsonify({
"name": "Simba AI - First African LLM",
"version": "1.0",
"model": model_name,
"capabilities": [
"African Languages: Yoruba, Swahili, Igbo, Hausa",
"Python Coding & Programming",
"Mathematics & Problem Solving",
"African Innovation Knowledge"
],
"knowledge_base_size": len(simba_knowledge_base)
})

@app .route('/api/chat', methods=['POST'])
def chat():
try:
data = request.get_json()

if not data or 'message' not in data:
return jsonify({
"error": "Missing 'message' in request body"
}), 400

user_message = data['message']

if not user_message.strip():
return jsonify({
"error": "Message cannot be empty"
}), 400

# Generate response
result = generate_simba_response(user_message)

return jsonify({
"success": True,
"user_message": user_message,
"simba_response": result["response"],
"response_time": result["response_time"],
"knowledge_used": result.get("knowledge_used", []),
"model": result.get("model", model_name),
"timestamp": time.time()
})

except Exception as e:
return jsonify({
"success": False,
"error": str(e),
"timestamp": time.time()
}), 500

# =====================
# LAUNCH
# =====================

if __name__ == '__main__':
print("🎯 Simba AI Backend API Ready!")
print("🌐 Endpoints:")
print(" GET /api/health - Health check")
print(" GET /api/info - API information")
print(" POST /api/chat - Chat with Simba AI")
print("\n🚀 Starting server...")
app.run(host='0.0.0.0', port=7860, debug=False)

app.py

@@ -1,320 +0,0 @@
-# =====================
-# 🦁 SIMBA AI - First African LLM (FAST VERSION)
-# =====================
-# Optimized for free Hugging Face hosting
-# Uses DialoGPT-large - Fast & Reliable
-# =====================
-
-import gradio as gr
-import torch
-from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
-from sentence_transformers import SentenceTransformer
-import faiss
-import numpy as np
-import time
-
-print("🚀 Initializing Simba AI - Fast African LLM...")
-
-# =====================
-# LOAD AI MODEL - OPTIMIZED
-# =====================
-
-# Using DialoGPT-large - Fast, reliable, works on free tier
-model_name = "microsoft/DialoGPT-large"
-
-try:
-    print("📥 Loading optimized AI model...")
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    tokenizer.pad_token = tokenizer.eos_token
-
-    model = AutoModelForCausalLM.from_pretrained(
-        model_name,
-        torch_dtype=torch.float16,
-        device_map="auto",
-    )
-    print("✅ Simba AI Model Loaded Successfully! (Fast Version)")
-    
-except Exception as e:
-    print(f"❌ Model loading error: {e}")
-    print("🔄 Using even lighter model...")
-    model_name = "microsoft/DialoGPT-medium"
-    tokenizer = AutoTokenizer.from_pretrained(model_name)
-    tokenizer.pad_token = tokenizer.eos_token
-    model = AutoModelForCausalLM.from_pretrained(model_name)
-    print("✅ Light model loaded!")
-
-# =====================
-# AFRICAN KNOWLEDGE BASE
-# =====================
-
-simba_knowledge_base = [
-    # CODING
-    {"question": "Python add function", "answer": "def add(a, b): return a + b"},
-    {"question": "Factorial function", "answer": "def factorial(n): return 1 if n == 0 else n * factorial(n-1)"},
-    {"question": "Reverse string function", "answer": "def reverse_string(s): return s[::-1]"},
-    {"question": "Check even number", "answer": "def is_even(n): return n % 2 == 0"},
-    {"question": "Multiply function", "answer": "def multiply(x, y): return x * y"},
-    {"question": "Yoruba greeting function", "answer": "def yoruba_greeting(): return 'Báwo ni'"},
-    
-    # MATH
-    {"question": "15 + 27", "answer": "42"},
-    {"question": "8 × 7", "answer": "56"},
-    {"question": "100 - 45", "answer": "55"},
-    {"question": "12 × 12", "answer": "144"},
-    {"question": "25% of 200", "answer": "50"},
-    {"question": "9 × 6", "answer": "54"},
-    
-    # YORUBA
-    {"question": "Hello in Yoruba", "answer": "Báwo ni"},
-    {"question": "Thank you in Yoruba", "answer": "Ẹ sé"},
-    {"question": "How are you in Yoruba", "answer": "Ṣe daadaa ni"},
-    {"question": "Good morning in Yoruba", "answer": "Ẹ káàrọ̀"},
-    {"question": "Good night in Yoruba", "answer": "O dàárọ̀"},
-    {"question": "Please in Yoruba", "answer": "Jọ̀wọ́"},
-    {"question": "Welcome in Yoruba", "answer": "Káàbọ̀"},
-    
-    # SWAHILI
-    {"question": "Hello in Swahili", "answer": "Hujambo"},
-    {"question": "Thank you in Swahili", "answer": "Asante"},
-    {"question": "How are you in Swahili", "answer": "Habari yako"},
-    {"question": "Good morning in Swahili", "answer": "Habari za asubuhi"},
-    
-    # IGBO
-    {"question": "Hello in Igbo", "answer": "Nnọọ"},
-    {"question": "Thank you in Igbo", "answer": "Daalụ"},
-    {"question": "How are you in Igbo", "answer": "Kedu ka ị mere?"},
-    
-    # HAUSA
-    {"question": "Hello in Hausa", "answer": "Sannu"},
-    {"question": "Thank you in Hausa", "answer": "Na gode"},
-    {"question": "How are you in Hausa", "answer": "Yaya lafiya?"},
-    
-    # AFRICAN INNOVATION
-    {"question": "M-Pesa", "answer": "Mobile money service launched in Kenya in 2007, revolutionized banking"},
-    {"question": "Andela", "answer": "Trains African software developers for global tech companies"},
-    {"question": "Flutterwave", "answer": "Nigerian fintech company providing payment infrastructure across Africa"},
-    {"question": "Paystack", "answer": "Nigerian payment processing company acquired by Stripe for $200M"},
-    
-    # SIMBA AI IDENTITY
-    {"question": "What is Simba AI", "answer": "Simba AI is the first African Large Language Model, specializing in African languages, coding, and mathematics"},
-    {"question": "Simba AI purpose", "answer": "To advance African AI innovation and make AI accessible for African languages and contexts"},
-]
-
-print(f"✅ African Knowledge Base: {len(simba_knowledge_base)} expert entries")
-
-# =====================
-# FAST SEARCH SYSTEM
-# =====================
-
-try:
-    print("🔍 Loading fast search system...")
-    embedder = SentenceTransformer('all-MiniLM-L6-v2')
-    
-    # Build search index
-    questions = [item["question"] for item in simba_knowledge_base]
-    question_embeddings = embedder.encode(questions)
-
-    dimension = question_embeddings.shape[1]
-    index = faiss.IndexFlatIP(dimension)
-    faiss.normalize_L2(question_embeddings)
-    index.add(question_embeddings)
-
-    print("✅ Fast Search System Ready!")
-except Exception as e:
-    print(f"❌ Search system error: {e}")
-    index = None
-
-def simba_search(query, top_k=3):
-    """Fast search African knowledge base"""
-    if index is None:
-        return simba_knowledge_base[:top_k]
-    
-    try:
-        query_embedding = embedder.encode([query])
-        faiss.normalize_L2(query_embedding)
-        
-        scores, indices = index.search(query_embedding, top_k)
-        
-        results = []
-        for i, idx in enumerate(indices[0]):
-            if idx < len(simba_knowledge_base):
-                results.append({
-                    "question": simba_knowledge_base[idx]["question"],
-                    "answer": simba_knowledge_base[idx]["answer"],
-                    "score": scores[0][i]
-                })
-        
-        return results
-    except Exception as e:
-        return simba_knowledge_base[:top_k]
-
-# =====================
-# FAST SIMBA AI CHAT FUNCTION
-# =====================
-
-def simba_ai_chat(message, history):
-    """Fast chat function with timeout protection"""
-    
-    start_time = time.time()
-    
-    # Quick responses for common greetings (instant)
-    quick_responses = {
-        "hello": "🦁 Báwo ni! Hello! I'm Simba AI, the first African LLM. I specialize in African languages, coding, and mathematics. How can I assist you today?",
-        "hi": "🦁 Báwo ni! Welcome to Simba AI - Africa's first Large Language Model!",
-        "hey": "🦁 Hello! I'm Simba AI. Ask me about African languages, Python coding, or math problems!",
-        "hola": "🦁 Báwo ni! I see you speak Spanish. I specialize in African languages like Yoruba, Swahili, Igbo, and Hausa!",
-    }
-    
-    lower_message = message.lower().strip()
-    if lower_message in quick_responses:
-        return quick_responses[lower_message]
-    
-    try:
-        # Search for relevant knowledge
-        search_results = simba_search(message, top_k=2)
-        
-        # Build smart context
-        context = "📚 African Knowledge:\n"
-        for i, result in enumerate(search_results, 1):
-            context += f"{i}. {result['question']}: {result['answer']}\n"
-        
-        # Optimized prompt for DialoGPT
-        prompt = f"User: {message}\nAfrican Knowledge: {context}\nSimba AI:"
-        
-        # Fast generation
-        inputs = tokenizer.encode(prompt, return_tensors="pt", max_length=512, truncation=True)
-        
-        with torch.no_grad():
-            outputs = model.generate(
-                inputs,
-                max_new_tokens=100,
-                temperature=0.7,
-                do_sample=True,
-                pad_token_id=tokenizer.eos_token_id,
-                repetition_penalty=1.1,
-                num_return_sequences=1,
-            )
-        
-        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
-        
-        # Extract just the Simba AI response
-        if "Simba AI:" in response:
-            final_response = response.split("Simba AI:")[-1].strip()
-        else:
-            final_response = response[len(prompt):].strip()
-        
-        # Add African flair
-        if not final_response.startswith("🦁"):
-            final_response = f"🦁 {final_response}"
-            
-        response_time = time.time() - start_time
-        print(f"✅ Response generated in {response_time:.2f} seconds")
-        
-        return final_response
-        
-    except Exception as e:
-        error_msg = f"🦁 Simba AI is thinking... Please try again! (Error: {str(e)})"
-        print(f"❌ Generation error: {e}")
-        return error_msg
-
-# =====================
-# FAST GRADIO INTERFACE
-# =====================
-
-# African theme CSS
-css = """
-.gradio-container {
-    font-family: 'Arial', sans-serif;
-}
-.header {
-    text-align: center;
-    padding: 25px;
-    background: linear-gradient(135deg, #ff7e5f, #feb47b);
-    color: white;
-    border-radius: 15px;
-    margin-bottom: 20px;
-    border: 2px solid #e65c50;
-}
-.african-pattern {
-    background: linear-gradient(45deg, #ff7e5f 25%, transparent 25%), 
-                linear-gradient(-45deg, #ff7e5f 25%, transparent 25%), 
-                linear-gradient(45deg, transparent 75%, #ff7e5f 75%), 
-                linear-gradient(-45deg, transparent 75%, #ff7e5f 75');
-    background-size: 20px 20px;
-    background-position: 0 0, 0 10px, 10px -10px, -10px 0px;
-    opacity: 0.1;
-}
-"""
-
-# Create fast interface
-with gr.Blocks(css=css, theme=gr.themes.Soft()) as demo:
-    
-    gr.HTML("""
-    <div class="header">
-        <h1>🦁 Simba AI - First African LLM</h1>
-        <h3>Fast & Optimized - African Languages, Coding & Mathematics</h3>
-        <p>Powered by DialoGPT-large • Responses in 5-15 seconds</p>
-    </div>
-    """)
-    
-    chatbot = gr.Chatbot(
-        label="🦁 Chat with Simba AI",
-        height=500,
-        show_copy_button=True,
-        placeholder="Ask about African languages, Python coding, or math..."
-    )
-    
-    with gr.Row():
-        msg = gr.Textbox(
-            label="Your message",
-            placeholder="Type your question here...",
-            lines=2,
-            scale=4
-        )
-        send_btn = gr.Button("🚀 Ask Simba AI", variant="primary", scale=1)
-    
-    with gr.Row():
-        clear_btn = gr.Button("🧹 Clear Chat")
-        info_btn = gr.Button("ℹ️ About Simba AI")
-    
-    # Quick action examples
-    gr.Examples(
-        examples=[
-            "Hello",
-            "How do you say thank you in Yoruba?",
-            "Write Python function to add numbers",
-            "What is 15 + 27?",
-            "Tell me about M-Pesa",
-            "How are you in Swahili?",
-            "Create factorial function",
-            "Calculate 8 × 7"
-        ],
-        inputs=msg,
-        label="💡 Quick Actions:"
-    )
-    
-    # Event handlers
-    def respond(message, chat_history):
-        bot_message = simba_ai_chat(message, chat_history)
-        chat_history.append((message, bot_message))
-        return "", chat_history
-    
-    def show_info():
-        return [("", "🦁 **Simba AI - First African LLM**\n\n**Capabilities:**\n• African Languages: Yoruba, Swahili, Igbo, Hausa\n• Python Coding & Programming\n• Mathematics & Problem Solving\n• African Tech Innovation\n\n**Powered by:** DialoGPT-large + African Knowledge Base\n**Response Time:** 5-15 seconds\n**Mission:** Advance African AI Innovation")]
-    
-    msg.submit(respond, [msg, chatbot], [msg, chatbot])
-    send_btn.click(respond, [msg, chatbot], [msg, chatbot])
-    clear_btn.click(lambda: None, None, chatbot, queue=False)
-    info_btn.click(show_info, None, chatbot)
-
-# =====================
-# LAUNCH
-# =====================
-
-if __name__ == "__main__":
-    print("🎯 Simba AI is ready! Launching interface...")
-    demo.launch(
-        debug=True,
-        share=True,
-        show_error=True
-    )