Upload folder using huggingface_hub

scripts/test_qdrant_client.py

@@ -0,0 +1,29 @@
+from qdrant_client import QdrantClient, models
+
+try:
+    print("Checking QdrantClient methods...")
+    client = QdrantClient(location=":memory:") 
+    client.create_collection("test", vectors_config=models.VectorParams(size=4, distance=models.Distance.COSINE))
+    client.upsert("test", points=[
+        models.PointStruct(id=1, vector=[0.1, 0.1, 0.1, 0.1], payload={"text": "hello"})
+    ])
+    
+    print("Testing query_points...")
+    results = client.query_points(
+        collection_name="test",
+        query=[0.1, 0.1, 0.1, 0.1],
+        limit=1
+    )
+    print(f"Results type: {type(results)}")
+    print(f"Results attributes: {dir(results)}")
+    if hasattr(results, 'points'):
+        print(f"Points type: {type(results.points)}")
+        print(f"First point: {results.points[0]}")
+        print(f"First point payload: {results.points[0].payload}")
+    if hasattr(client, 'search'):
+        print("client.search exists")
+    else:
+        print("client.search DOES NOT exist")
+
+except Exception as e:
+    print(f"Error: {e}")

src/embeddings/vector_store.py

@@ -228,9 +228,9 @@ class QdrantVectorStore:
         
     def search(self, query_embedding, n_results=5, filter_metadata=None):
         # Qdrant expects query_vector
-        results = self.client.search(
+        response = self.client.query_points(
             collection_name=self.collection_name,
-            query_vector=query_embedding,
+            query=query_embedding,
             limit=n_results
         )
         
@@ -239,7 +239,7 @@ class QdrantVectorStore:
         metadatas = []
         distances = []
         
-        for res in results:
+        for res in response.points:
             docs.append(res.payload.get("page_content", ""))
             metadatas.append({k:v for k,v in res.payload.items() if k != "page_content"})
             distances.append(res.score)