Upload app.py

app.py

@@ -0,0 +1,47 @@
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+import gradio as gr
+import pandas as pd
+from sentence_transformers import SentenceTransformer
+
+# טען את המודל
+model = SentenceTransformer("all-MiniLM-L6-v2")
+
+# טען את הדאטהסט מהלינק
+url = "https://huggingface.co/datasets/Pablinho/movies-dataset/resolve/main/9000plus.csv"
+print("Loading dataset...")
+dataset = pd.read_csv(url)
+
+# ודא שהעמודות קיימות
+assert "Title" in dataset.columns
+assert "Overview" in dataset.columns
+
+# נקה שורות עם Overview חסר או לא מחרוזת
+dataset = dataset.dropna(subset=["Overview"])
+dataset = dataset[dataset["Overview"].apply(lambda x: isinstance(x, str))]
+
+# הגבל ל־500 סרטים
+MAX_MOVIES = 500
+dataset = dataset.head(MAX_MOVIES)
+
+print(f"Encoding {len(dataset)} movie descriptions...")
+dataset["embeddings"] = dataset["Overview"].apply(lambda x: model.encode(x).tolist())
+print("Done encoding!")
+
+def recommend_similar_movies(input_text, top_n=5):
+    input_embedding = model.encode([input_text])
+    similarities = cosine_similarity(input_embedding, np.vstack(dataset['embeddings'].to_numpy()))[0]
+    top_indices = similarities.argsort()[::-1][:top_n]
+    results = dataset.iloc[top_indices][['Title', 'Overview']]
+    return "\n\n".join(f"🎬 **{row['Title']}**\n{row['Overview']}" for _, row in results.iterrows())
+
+demo = gr.Interface(
+    fn=recommend_similar_movies,
+    inputs=gr.Textbox(lines=2, placeholder="Describe a movie..."),
+    outputs="text",
+    title="Movie Recommender",
+    description="Get movie recommendations based on your description. Powered by sentence-transformers and cosine similarity."
+)
+
+if __name__ == "__main__":
+    demo.launch()