Create app.py

app.py

@@ -0,0 +1,39 @@
+import os
+import uuid
+import pandas as pd
+from qdrant_client import QdrantClient, models
+from sentence_transformers import SentenceTransformer
+
+# === Step 1: Ensure Qdrant directory exists ===
+if not os.path.exists("qdrant_data"):
+    os.makedirs("qdrant_data")
+
+# === Step 2: Load dataset ===
+data = pd.read_csv("math_dataset(2).csv")  # Ensure this CSV is present and formatted correctly
+
+# === Step 3: Encode questions ===
+embedding_model = SentenceTransformer("intfloat/e5-large")
+vectors = embedding_model.encode(data["problem"].tolist(), show_progress_bar=True)
+
+# === Step 4: Initialize local Qdrant client ===
+client = QdrantClient(path="qdrant_data")
+
+# === Step 5: Create collection (recreate ensures it's fresh) ===
+collection_name = "math_problems"
+client.recreate_collection(
+    collection_name=collection_name,
+    vectors_config=models.VectorParams(size=vectors.shape[1], distance=models.Distance.COSINE)
+)
+
+# === Step 6: Prepare payload and upload with UUIDs ===
+payload = data.to_dict(orient="records")
+ids = [str(uuid.uuid4()) for _ in range(len(vectors))]
+
+client.upload_collection(
+    collection_name=collection_name,
+    vectors=vectors,
+    payload=payload,
+    ids=ids
+)
+
+print("✅ Qdrant vector store created and populated successfully in `qdrant_data/`.")