Create app_backend.py

app_backend.py

@@ -0,0 +1,87 @@
+from flask import Flask, request, jsonify
+from flask_cors import CORS
+import os
+import openai
+import pandas as pd
+import json
+from functools import lru_cache
+
+app = Flask(__name__)
+CORS(app)  # Enable CORS for cross-origin requests
+
+# Configure DeepSeek API
+openai.api_key = os.getenv("DEEPSEEK_API_KEY")
+openai.api_base = "https://api.deepseek.com/v1"
+
+# Cache for expensive computations (e.g., dataset stats)
+@lru_cache(maxsize=128)
+def get_dataset_stats(df_json):
+    df = pd.read_json(df_json)
+    stats = {
+        "rows": df.shape[0],
+        "columns": df.shape[1],
+        "missing_values": df.isna().sum().sum(),
+        "column_types": {col: str(df[col].dtype) for col in df.columns},
+    }
+    return stats
+
+@app.route('/chat', methods=['POST'])
+def chat():
+    try:
+        data = request.json
+        user_input = data.get('message')
+        df_json = data.get('dataset', None)
+        problem_type = data.get('problem_type', None)
+        target = data.get('target', None)
+        best_model = data.get('best_model', None)
+
+        # Get dataset stats if available
+        context = ""
+        if df_json:
+            stats = get_dataset_stats(df_json)
+            context += f"Dataset Stats:\n- Rows: {stats['rows']}\n- Columns: {stats['columns']}\n- Missing Values: {stats['missing_values']}\n"
+            context += "Column Types:\n"
+            for col, dtype in stats['column_types'].items():
+                context += f"- {col}: {dtype}\n"
+
+        if problem_type:
+            context += f"Problem Type: {problem_type}\n"
+        if target:
+            context += f"Target Column: {target}\n"
+        if best_model:
+            context += f"Best Model: {best_model}\n"
+
+        # Create enhanced prompt with context
+        system_prompt = (
+            "You are an AI assistant in Neural-Vision Enhanced, a data analysis and modeling app. "
+            "The app has three pages:\n"
+            "- **Data Upload**: Upload CSV files, view stats, or generate EDA reports.\n"
+            "- **Model Training**: Train classification, regression, or clustering models using PyCaret.\n"
+            "- **Validation & Exploration**: Evaluate and visualize trained models.\n"
+            f"Current context:\n{context}"
+        )
+
+        # Call DeepSeek API
+        response = openai.ChatCompletion.create(
+            model="deepseek-chat",
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": user_input}
+            ],
+            temperature=0.7,
+            max_tokens=500
+        )
+
+        return jsonify({
+            "response": response.choices[0].message.content,
+            "status": "success"
+        })
+
+    except Exception as e:
+        return jsonify({
+            "response": f"Error: {str(e)}",
+            "status": "error"
+        }), 500
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=5001)