Convert to Gradio app for simpler deployment

README.md

@@ -3,7 +3,9 @@ title: Code Review Assistant
 emoji: 🤖
 colorFrom: blue
 colorTo: green
-sdk: docker
+sdk: gradio
+sdk_version: 4.0.0
+app_file: app.py
 pinned: false
 ---
 
@@ -21,20 +23,14 @@ An automated code review system powered by Gemma-2b that provides intelligent co
 
 ### LLMOps Integration
 - Uses Gemma-2b for intelligent code analysis
-- Tracks model performance and accuracy
-- Monitors response times and token usage
+- Provides detailed code analysis
+- Generates actionable suggestions
 
-### Performance Monitoring
-- Real-time metrics dashboard
-- Review history tracking
-- Response time monitoring
-- Usage statistics
-
-### Modern Web Interface
-- Interactive code submission
-- Syntax highlighting with CodeMirror
-- Real-time review results
-- Metrics visualization
+### User Interface
+- Simple and intuitive Gradio interface
+- Code input with syntax highlighting
+- Language selection dropdown
+- Example code snippets included
 
 ## Environment Variables
 
@@ -42,49 +38,31 @@ The following environment variables need to be set in your Hugging Face Space:
 
 - `HUGGING_FACE_TOKEN`: Your Hugging Face API token (required)
 - `MODEL_NAME`: google/gemma-2b-it (default)
-- `DEBUG`: false (default)
-- `LOG_LEVEL`: INFO (default)
-- `PORT`: 7860 (default)
-
-## API Endpoints
-
-- `POST /api/v1/review`: Submit code for review
-  ```json
-  {
-    "code": "your code here",
-    "language": "python"
-  }
-  ```
-- `GET /api/v1/metrics`: Get system metrics
-- `GET /api/v1/history`: Get review history
-- `GET /health`: Check system health
 
 ## Usage
 
-1. Enter your code in the editor
-2. Select the programming language
-3. Click "Submit for Review"
+1. Enter your code in the text box
+2. Select the programming language from the dropdown
+3. Click "Submit" to get the review
 4. View the detailed analysis including:
    - Critical issues
    - Suggested improvements
    - Best practices
    - Security considerations
 
-## Metrics
+## Example Code
 
-The system tracks various metrics including:
-- Total reviews performed
-- Average response time
-- Number of suggestions per review
-- Daily usage statistics
+Try the included example code snippets to see how the review system works:
+- Python function example
+- JavaScript array processing example
 
-## Deployment
+## Model Details
 
-This Space is deployed using Docker and runs on Hugging Face's infrastructure. The application automatically handles:
-- Model initialization and optimization
-- Memory management
-- Performance monitoring
-- Error handling and logging
+This application uses the Gemma-2b-it model from Google, which is:
+- Optimized for instruction following
+- Capable of detailed code analysis
+- Efficient for deployment
+- Suitable for code review tasks
 
 ## License
 

app.py

@@ -0,0 +1,140 @@
+import gradio as gr
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+from huggingface_hub import login
+import os
+import logging
+from datetime import datetime
+
+# Configure logging
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Environment variables
+HF_TOKEN = os.getenv("HUGGING_FACE_TOKEN")
+MODEL_NAME = os.getenv("MODEL_NAME", "google/gemma-2b-it")
+
+class CodeReviewer:
+    def __init__(self):
+        self.model = None
+        self.tokenizer = None
+        self.device = "cpu"
+        self.initialize_model()
+        
+    def initialize_model(self):
+        """Initialize the model and tokenizer."""
+        try:
+            if HF_TOKEN:
+                login(token=HF_TOKEN)
+            
+            logger.info("Loading tokenizer...")
+            self.tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+            
+            logger.info("Loading model...")
+            self.model = AutoModelForCausalLM.from_pretrained(
+                MODEL_NAME,
+                device_map={"": self.device},
+                torch_dtype=torch.float32,
+                low_cpu_mem_usage=True
+            )
+            logger.info("Model loaded successfully")
+        except Exception as e:
+            logger.error(f"Error initializing model: {e}")
+            raise
+
+    def create_review_prompt(self, code: str, language: str) -> str:
+        """Create a structured prompt for code review."""
+        return f"""Review this {language} code. List specific points in these sections:
+Issues:
+Improvements:
+Best Practices:
+Security:
+
+Code:
+```{language}
+{code}
+```"""
+
+    def review_code(self, code: str, language: str) -> str:
+        """Perform code review using the model."""
+        try:
+            prompt = self.create_review_prompt(code, language)
+            
+            inputs = self.tokenizer(
+                prompt,
+                return_tensors="pt",
+                truncation=True,
+                max_length=512,
+                padding=True
+            )
+            
+            with torch.no_grad():
+                outputs = self.model.generate(
+                    **inputs,
+                    max_new_tokens=512,
+                    do_sample=True,
+                    temperature=0.7,
+                    top_p=0.95,
+                    num_beams=1,
+                    early_stopping=True
+                )
+            
+            response = self.tokenizer.decode(outputs[0], skip_special_tokens=True)
+            return response[len(prompt):].strip()
+            
+        except Exception as e:
+            logger.error(f"Error during code review: {e}")
+            return f"Error performing code review: {str(e)}"
+
+# Initialize the reviewer
+reviewer = CodeReviewer()
+
+def review_code_interface(code: str, language: str) -> str:
+    """Gradio interface function for code review."""
+    if not code.strip():
+        return "Please enter some code to review."
+    
+    try:
+        result = reviewer.review_code(code, language)
+        return result
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=review_code_interface,
+    inputs=[
+        gr.Textbox(
+            lines=10,
+            placeholder="Enter your code here...",
+            label="Code"
+        ),
+        gr.Dropdown(
+            choices=["python", "javascript", "java", "cpp", "typescript", "go", "rust"],
+            value="python",
+            label="Language"
+        )
+    ],
+    outputs=gr.Textbox(
+        label="Review Results",
+        lines=10
+    ),
+    title="Code Review Assistant",
+    description="An automated code review system powered by Gemma-2b that provides intelligent code analysis and suggestions for improvements.",
+    examples=[
+        ["""def add_numbers(a, b):
+    return a + b""", "python"],
+        ["""function calculateSum(numbers) {
+    let sum = 0;
+    for(let i = 0; i < numbers.length; i++) {
+        sum += numbers[i];
+    }
+    return sum;
+}""", "javascript"]
+    ],
+    theme=gr.themes.Soft()
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()

requirements.txt

@@ -1,36 +1,12 @@
 # Core dependencies
-fastapi==0.104.1
-uvicorn[standard]==0.24.0
-python-dotenv==1.0.0
-pydantic==2.4.2
-pydantic-settings==2.0.3
-
-# Model and ML
-transformers>=4.39.0  # Updated to latest version for Gemma support
-# torch is installed separately in Dockerfile
-numpy<2.0.0  # Added explicit numpy version
-accelerate==0.27.2
-safetensors==0.4.2
-bitsandbytes==0.41.1  # For model quantization
-sentencepiece==0.1.99
-
-# Monitoring and metrics
-prometheus-client==0.17.1
-prometheus-fastapi-instrumentator==6.1.0
-
-# Database
-sqlalchemy==2.0.23
-alembic==1.12.1
-psycopg2-binary==2.9.9
-
-# Testing
-pytest==7.4.3
-pytest-asyncio==0.21.1
-httpx==0.24.1
+gradio>=4.0.0
+transformers>=4.39.0
+torch>=2.0.0
+accelerate>=0.27.2
+safetensors>=0.4.2
+sentencepiece>=0.1.99
 
 # Utilities
-python-multipart==0.0.6
-python-jose==3.3.0
-passlib==1.7.4
-aiofiles==23.2.1
-jinja2==3.1.2
+python-dotenv>=1.0.0
+pydantic>=2.4.2
+numpy<2.0.0