Create app.py

app.py

@@ -0,0 +1,25 @@
+import gradio as gr
+from transformers import pipeline
+
+# Load fine-tuned model from Hugging Face Hub
+t5_recommender = pipeline(model="RedaAlami/t5_recommendation_sports_equipment_english")
+
+def recommend(items_purchased, candidates):
+    prompt = f"ITEMS PURCHASED: {{{items_purchased}}} - CANDIDATES FOR RECOMMENDATION: {{{candidates}}} - RECOMMENDATION: "
+    model_output = t5_recommender(prompt)
+    recommendation = model_output[0]['generated_text']
+    return recommendation
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Sports Equipment Recommender")
+    with gr.Row():
+        with gr.Column():
+            items_input = gr.Textbox(label="Items Purchased")
+            candidates_input = gr.Textbox(label="Candidates for Recommendation")
+        with gr.Column():
+            recommendation_output = gr.Textbox(label="Recommendation")
+
+    recommend_button = gr.Button("Get Recommendation")
+    recommend_button.click(fn=recommend, inputs=[items_input, candidates_input], outputs=recommendation_output)
+
+demo.launch()