Update app.py

app.py

@@ -1,70 +1,300 @@
+"""
+HUGGINGFACE SPACE - API FOR STARLIGHT MINI
+This creates a Space with automatic API endpoints
+
+Deploy this to get a FREE, ALWAYS-ON API for your users!
+"""
+
+# ============================================
+# File: app.py (Main file for your Space)
+# ============================================
+
+APP_PY = '''
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+# Load your model
+print("🚀 Loading Starlight Mini...")
+
+MODEL_NAME = "arthu1/starlight-mini"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_NAME,
+    torch_dtype=torch.float16,
+    device_map="auto",
+    low_cpu_mem_usage=True
+)
+
+print("✅ Model loaded!")
+
+def generate_text(
+    prompt: str,
+    max_tokens: int = 100,
+    temperature: float = 0.7,
+    top_p: float = 0.9
+) -> str:
     """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
+    Generate text from prompt
+    This function is automatically exposed as an API endpoint!
     """
-    client = InferenceClient(token=hf_token.token, model="arthu1/starlight-mini")
+    if not prompt:
+        return "Error: Please provide a prompt"
+    
+    try:
+        inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+        
+        with torch.no_grad():
+            outputs = model.generate(
+                **inputs,
+                max_new_tokens=min(max_tokens, 500),
+                temperature=temperature,
+                top_p=top_p,
+                do_sample=True,
+                pad_token_id=tokenizer.eos_token_id
+            )
+        
+        result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+        return result
+    
+    except Exception as e:
+        return f"Error: {str(e)}"
 
-    messages = [{"role": "system", "content": system_message}]
+# Create Gradio interface with API
+with gr.Blocks(title="Starlight Mini API") as demo:
+    gr.Markdown("""
+    # 🌟 Starlight Mini API
+    **Free AI Text Generation - 8B Parameters**
+    
+    This Space provides both a web UI and automatic API endpoints!
+    """)
+    
+    with gr.Tab("💬 Chat Interface"):
+        with gr.Row():
+            with gr.Column():
+                prompt_input = gr.Textbox(
+                    label="Prompt",
+                    placeholder="Enter your prompt here...",
+                    lines=5
+                )
+                
+                with gr.Accordion("⚙️ Settings", open=False):
+                    max_tokens_slider = gr.Slider(
+                        minimum=10,
+                        maximum=500,
+                        value=100,
+                        step=10,
+                        label="Max Tokens"
+                    )
+                    temperature_slider = gr.Slider(
+                        minimum=0.1,
+                        maximum=2.0,
+                        value=0.7,
+                        step=0.1,
+                        label="Temperature"
+                    )
+                    top_p_slider = gr.Slider(
+                        minimum=0.1,
+                        maximum=1.0,
+                        value=0.9,
+                        step=0.05,
+                        label="Top P"
+                    )
+                
+                generate_btn = gr.Button("✨ Generate", variant="primary")
+            
+            with gr.Column():
+                output_text = gr.Textbox(
+                    label="Generated Text",
+                    lines=10
+                )
+        
+        gr.Examples(
+            examples=[
+                ["Once upon a time in a magical forest,"],
+                ["Explain quantum computing in simple terms:"],
+                ["Write a haiku about coding:"],
+            ],
+            inputs=[prompt_input]
+        )
+    
+    with gr.Tab("📡 API Documentation"):
+        gr.Markdown("""
+        ## Using the API
+        
+        This Space automatically provides API endpoints!
+        
+        ### Python Example:
+        ```python
+        from gradio_client import Client
+        
+        client = Client("arthu1/Exquisite-Starlight")
+        result = client.predict(
+            prompt="Hello, Starlight!",
+            max_tokens=100,
+            temperature=0.7,
+            top_p=0.9,
+            api_name="/predict"
+        )
+        print(result)
+        ```
+        
+        ### cURL Example:
+        ```bash
+        curl -X POST https://arthu1-exquisite-starlight.hf.space/api/predict \\
+          -H "Content-Type: application/json" \\
+          -d '{"data": ["Your prompt here", 100, 0.7, 0.9]}'
+        ```
+        
+        ### JavaScript Example:
+        ```javascript
+        const response = await fetch(
+          "https://arthu1-exquisite-starlight.hf.space/api/predict",
+          {
+            method: "POST",
+            headers: { "Content-Type": "application/json" },
+            body: JSON.stringify({
+              data: ["Your prompt here", 100, 0.7, 0.9]
+            })
+          }
+        );
+        const result = await response.json();
+        console.log(result.data[0]);
+        ```
+        
+        ### Rate Limits:
+        - Free tier: Generous limits for personal/small commercial use
+        - If you need more, consider upgrading the Space hardware
+        
+        ### Support:
+        - Report issues on the Space's Community tab
+        - Share feedback and improvements!
+        """)
+    
+    # Connect the button
+    generate_btn.click(
+        fn=generate_text,
+        inputs=[prompt_input, max_tokens_slider, temperature_slider, top_p_slider],
+        outputs=output_text
+    )
 
-    messages.extend(history)
+# Launch with API enabled
+demo.launch(
+    show_api=True,  # This enables automatic API endpoints!
+    share=False  # Space URL is already public
+)
+'''
 
-    messages.append({"role": "user", "content": message})
+# ============================================
+# File: requirements.txt
+# ============================================
 
-    response = ""
+REQUIREMENTS = '''
+gradio
+transformers
+torch
+accelerate
+gradio_client
+'''
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+# ============================================
+# File: README.md
+# ============================================
 
-        response += token
-        yield response
+README = '''---
+title: Starlight Mini API
+emoji: 🌟
+colorFrom: purple
+colorTo: blue
+sdk: gradio
+sdk_version: 4.44.0
+app_file: app.py
+pinned: false
+---
 
+# Starlight Mini API
 
+Free AI text generation API powered by an 8B parameter model.
+
+## Features
+- 🌟 8B parameter model
+- 💬 Web UI for testing
+- 📡 Automatic API endpoints
+- 🚀 Always online (free CPU tier)
+- ⚡ Fast inference
+
+## Usage
+
+### Web UI
+Just visit this Space and start chatting!
+
+### API
+See the "API Documentation" tab for code examples in Python, JavaScript, and cURL.
+
+## Model
+Based on arthu1/starlight-mini - a fine-tuned model optimized for helpfulness and coding tasks.
+
+## Credits
+Created by arthu1 / Nova Devs (North.ai)
+'''
+
+# ============================================
+# DEPLOYMENT INSTRUCTIONS
+# ============================================
+
+INSTRUCTIONS = """
+HOW TO DEPLOY YOUR SPACE:
+
+1. Go to https://huggingface.co/new-space
+
+2. Fill in:
+   - Space name: Exquisite-Starlight (or whatever you want)
+   - License: Apache-2.0
+   - SDK: Gradio
+   - Hardware: CPU (free!) or upgrade to GPU if needed
+
+3. Create the Space
+
+4. Upload these 3 files:
+   - app.py (the code above)
+   - requirements.txt
+   - README.md
+
+5. Wait 5-10 minutes for it to build
+
+6. Done! You get:
+   ✅ Public URL: https://huggingface.co/spaces/arthu1/Exquisite-Starlight
+   ✅ API URL: https://arthu1-exquisite-starlight.hf.space/api/predict
+   ✅ Web UI for testing
+   ✅ Always online (free!)
+
+7. Share the URLs with your users!
+
+IMPORTANT:
+- CPU is FREE forever
+- If you need faster inference, upgrade to GPU (costs money)
+- API endpoints are automatic - Gradio creates them for you!
+- Users can call your API from any language
+
+Your users will be happy because:
+- Free access
+- ChatGPT-like experience
+- Simple API to integrate
+- Always online
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
 
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
+print(f"""
+FILES TO CREATE:
+
+1. app.py:
+{APP_PY}
+
+2. requirements.txt:
+{REQUIREMENTS}
 
+3. README.md:
+{README}
 
-if __name__ == "__main__":
-    demo.launch()
+{INSTRUCTIONS}
+""")