Update app.py

app.py

@@ -1,60 +1,46 @@
-import gradio as gr
-import pandas as pd
-import numpy as np
-import pickle
-from sentence_transformers import SentenceTransformer, util
-import os
-
-# =========================
-# قراءة البيانات وEmbeddings من ملفات موجودة داخل Space
-# =========================
-with open("books.pkl", "rb") as f:
-    books = pickle.load(f)
-
-with open("theses.pkl", "rb") as f:
-    theses = pickle.load(f)
-
-books["type"] = "Book"
-theses["type"] = "Thesis"
-library = pd.concat([books, theses], ignore_index=True)
-
-with open("books_embeddings.pkl", "rb") as f:
-    books_emb = pickle.load(f)
-
-with open("theses_embeddings.pkl", "rb") as f:
-    theses_emb = pickle.load(f)
-
-library_embeddings = np.vstack([books_emb, theses_emb])
-
-# =========================
-# تحميل موديل MiniLM من فولدر موجود داخل Space
-# =========================
-model = SentenceTransformer("AI_Library_Model")
-
-# =========================
-# دالة البحث
-# =========================
-def search_library(query, source_type):
-    filtered = library[library["type"] == source_type]
-    filtered_emb = library_embeddings[filtered.index]
-
-    query_emb = model.encode(query)
-    scores = util.cos_sim(query_emb, filtered_emb)[0]
-    top_idx = np.argsort(scores.cpu().numpy())[::-1][:5]
-
-    results = filtered.iloc[top_idx][["title","author","year","field"]]
-    return results
-
-# =========================
-# واجهة Gradio تاب واحدة
-# =========================
-with gr.Blocks() as demo:
-    gr.Markdown("## مكتبة AI Explorer - البحث الحر المحلي")
-    with gr.Row():
-        query = gr.Textbox(label="اكتب سؤال البحث")
-        source = gr.Dropdown(choices=["Book", "Thesis"], label="نوع المصدر")
-        btn = gr.Button("بحث")
-    output = gr.Dataframe(headers=["العنوان","المؤلف","السنة","المجال"])
-    btn.click(search_library, inputs=[query, source], outputs=output)
-
-demo.launch()
+import joblib
+import gradio as gr
+import numpy as np
+
+# =========================
+# تحميل البيانات
+# =========================
+books = joblib.load("books.pkl")
+theses = joblib.load("Theses.pkl")
+books_emb = joblib.load("books_embeddings.pkl")
+theses_emb = joblib.load("theses_embeddings.pkl")
+
+# =========================
+# مثال دالة بحث بسيطة
+# =========================
+from sklearn.metrics.pairwise import cosine_similarity
+
+def search_library(query_embedding, top_k=5):
+    # دمج كل Embeddings
+    all_emb = np.vstack([books_emb, theses_emb])
+    similarity = cosine_similarity([query_embedding], all_emb)[0]
+    top_indices = similarity.argsort()[-top_k:][::-1]
+    
+    results = []
+    for idx in top_indices:
+        if idx < len(books):
+            results.append(books[idx])
+        else:
+            results.append(theses[idx - len(books)])
+    return results
+
+# =========================
+# واجهة Gradio
+# =========================
+def search_interface(query_embedding):
+    return search_library(query_embedding)
+
+demo = gr.Interface(
+    fn=search_interface,
+    inputs=gr.inputs.Dataframe(),  # هنا ممكن تغيّري حسب نوع المدخل
+    outputs="text",
+    title="Library Search",
+    description="بحث في مكتبة الكتب والرسائل"
+)
+
+demo.launch()