Create main.py

main.py

@@ -0,0 +1,44 @@
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from flask import Flask, request, jsonify
+
+device = "cuda" # the device to load the model onto
+
+model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
+tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.1")
+
+
+
+@app.route('/recommend', methods=['POST'])
+def recommendation():
+    content = request.json
+    user_degree = content.get('degree')
+    user_stream = content.get('stream')
+    user_semester = content.get('semester')
+    messages = [
+    {"role": "user", "content": f"""
+    You need to act like as recommendataion engine for course recommendation based on below details.
+
+    Degree: {user_degree}
+    Stream: {user_stream}
+    Current Semester: {user_semester}
+
+
+    Based on above details recommend the courses that realtes to above details 
+    Note: Output should bevalid json format in below format:
+    {{"course1:ABC,course2:DEF,course3:XYZ,...}}
+    
+    """},
+    
+    ]
+    
+    encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
+    
+    model_inputs = encodeds.to(device)
+    model.to(device)
+    
+    generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
+    decoded = tokenizer.batch_decode(generated_ids)
+    return jsonify({"res":decoded[0]})
+
+if __name__ == '__main__':
+    app.run(debug=True)