uploading sample data and updated yaml

Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
feast-dev · franciscojavierarceo · Jan 30, 2025 · Jan 25, 2025 · Jan 27, 2025 · Jan 27, 2025
commit a1a9408528ce62ddc40925167dad945e82782dd0
diff --git a/Makefile b/Makefile
@@ -6,7 +6,7 @@
     FileSource,
 )
 from feast.data_format import ParquetFormat
-from feast.types import Float32, Array
+from feast.types import Float32, Array, String
 from feast import Entity
 
 item = Entity(name="item_id")
@@ -23,7 +23,14 @@
     name="city_embeddings",
     entities=[item],
     schema=[
-        Field(name="Embeddings", dtype=Array(Float32)),
+        Field(
+            name="vector",
+            dtype=Array(Float32),
+            vector_index=True,
+            vector_search_metric="L2",
+        ),
+        Field(name="sentence_chunks", dtype=String),
+        Field(name="wiki_summary", dtype=String),
     ],
     source=source,
     ttl=timedelta(hours=2),

@@ -4,12 +4,7 @@ registry: data/registry.db
 online_store:
   type: milvus
   vector_enabled: true
-  vector_len: 384
-  host: 127.0.0.1
-#  port: 5432
-  port: 19530
-  username: "username"
-  password: "password"
+  embedding_dim: 384
 
 
 offline_store:

@@ -2,6 +2,7 @@
 import torch
 import torch.nn.functional as F
 from feast import FeatureStore
+from pymilvus import MilvusClient
 from transformers import AutoTokenizer, AutoModel
 from example_repo import city_embeddings_feature_view, item
 TOKENIZER = "sentence-transformers/all-MiniLM-L6-v2"
@@ -37,8 +38,11 @@ def run_demo():
     df = pd.read_parquet("./data/city_wikipedia_summaries_with_embeddings.parquet")
     store.apply([city_embeddings_feature_view, item])
     store.write_to_online_store_async("city_embeddings", df)
-    question = "the most populous city in the U.S. state of Texas?"
 
+    client = MilvusClient(alias="feast", host="localhost", port="19530", token="username:password")
+    print(client.list_collections())
+
+    question = "the most populous city in the U.S. state of Texas?"
     tokenizer = AutoTokenizer.from_pretrained(TOKENIZER)
     model = AutoModel.from_pretrained(MODEL)
     query_embedding = run_model(question, tokenizer, model)

diff --git a/sdk/python/feast/infra/online_stores/postgres_online_store/postgres.py b/sdk/python/feast/infra/online_stores/postgres_online_store/postgres.py
@@ -403,6 +403,26 @@ def retrieve_online_documents(
 
             # Search query template to find the top k items that are closest to the given embedding
             # SELECT * FROM items ORDER BY embedding <-> '[3,1,2]' LIMIT 5;
+            query = sql.SQL(
+                """
+                    SELECT
+                        entity_key,
+                        feature_name,
+                        value,
+                        vector_value,
+                        vector_value {distance_metric_sql} %s::vector as distance,
+                        event_ts FROM {table_name}
+                    WHERE feature_name = {feature_name}
+                    ORDER BY distance
+                    LIMIT {top_k};
+                    """
+            ).format(
+                distance_metric_sql=sql.SQL(distance_metric_sql),
+                table_name=sql.Identifier(table_name),
+                feature_name=sql.Literal(requested_feature),
+                top_k=sql.Literal(top_k),
+            )
+            print(query)
             cur.execute(
                 sql.SQL(
                     """

diff --git a/sdk/python/feast/repo_config.py b/sdk/python/feast/repo_config.py
@@ -60,7 +60,7 @@
     "feast.infra.online_stores.contrib.ikv_online_store.ikv.IKVOnlineStore": "feast.infra.online_stores.ikv_online_store.ikv.IKVOnlineStore",
     "feast.infra.online_stores.contrib.elasticsearch.ElasticSearchOnlineStore": "feast.infra.online_stores.elasticsearch_online_store.ElasticSearchOnlineStore",
     "feast.infra.online_stores.contrib.singlestore_online_store.singlestore.SingleStoreOnlineStore": "feast.infra.online_stores.singlestore_online_store.singlestore.SingleStoreOnlineStore",
-    "feast.infra.online_stores.contrib.qdrant.QdrantOnlineStore": "feast.infra.online_stores.cqdrant.QdrantOnlineStore",
+    # "feast.infra.online_stores.contrib.qdrant.QdrantOnlineStore": "feast.infra.online_stores.cqdrant.QdrantOnlineStore",
 }
 
 ONLINE_STORE_CLASS_FOR_TYPE = {

diff --git a/sdk/python/tests/integration/feature_repos/repo_configuration.py b/sdk/python/tests/integration/feature_repos/repo_configuration.py
@@ -214,6 +214,7 @@
         "dynamodb": (DYNAMO_CONFIG, DynamoDBOnlineStoreCreator),
         "datastore": ("datastore", DatastoreOnlineStoreCreator),
         "bigtable": ("bigtable", BigtableOnlineStoreCreator),
+        # "milvus:": (MILVUS_CONFIG, MilvusOnlineStoreCreator),
     }
 
     for key, replacement in replacements.items():