Create app.py

app.py

@@ -0,0 +1,59 @@
+from flask import Flask, request, jsonify
+import torch
+from transformers import pipeline
+import logging
+
+app = Flask(__name__)
+logging.basicConfig(level=logging.INFO)
+
+# Загрузка модели при старте
+@app.before_first_request
+def load_model():
+    global generator
+    try:
+        generator = pipeline(
+            "text-generation",
+            model="mistralai/Mistral-7B-Instruct-v0.3",
+            torch_dtype=torch.float16,
+            device_map="auto",
+            max_length=1024
+        )
+        logging.info("Model loaded successfully")
+    except Exception as e:
+        logging.error(f"Error loading model: {e}")
+
+@app.route('/')
+def home():
+    return jsonify({"message": "RAG Model API is running!"})
+
+@app.route('/generate', methods=['POST'])
+def generate():
+    try:
+        data = request.json
+        prompt = data.get('prompt', '')
+        
+        if not prompt:
+            return jsonify({"error": "No prompt provided"}), 400
+        
+        # Генерация ответа
+        result = generator(
+            prompt,
+            max_new_tokens=512,
+            temperature=0.7,
+            top_p=0.9,
+            do_sample=True
+        )
+        
+        generated_text = result[0]['generated_text']
+        
+        return jsonify({
+            "response": generated_text,
+            "status": "success"
+        })
+        
+    except Exception as e:
+        logging.error(f"Generation error: {e}")
+        return jsonify({"error": str(e)}), 500
+
+if __name__ == '__main__':
+    app.run(host='0.0.0.0', port=7860, debug=False)