GeezerVison

Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,149 @@
		from feast.file_utils import replace_str_in_file


		def bootstrap() -> None:
		import pathlib
		from datetime import datetime, timedelta

		import numpy as np
		import pandas as pd

		repo_path = pathlib.Path(__file__).parent.absolute() / "feature_repo"
		project_name = pathlib.Path(__file__).parent.absolute().name
		data_path = repo_path / "data"
		data_path.mkdir(exist_ok=True)

		products = [
		(
		"P001",
		"Wireless Noise-Cancelling Headphones",
		"Premium over-ear headphones with active noise cancellation and 30-hour battery life.",
		"Electronics",
		299.99,
		4.7,
		),
		(
		"P002",
		"Bluetooth Portable Speaker",
		"Waterproof portable speaker with deep bass and 12-hour playtime.",
		"Electronics",
		79.99,
		4.5,
		),
		(
		"P003",
		"Mechanical Gaming Keyboard",
		"RGB mechanical keyboard with Cherry MX switches and programmable keys.",
		"Electronics",
		149.99,
		4.6,
		),
		(
		"P004",
		"Ergonomic Wireless Mouse",
		"Vertical ergonomic mouse designed to reduce wrist strain.",
		"Electronics",
		49.99,
		4.3,
		),
		(
		"P005",
		"Python Machine Learning Cookbook",
		"Practical recipes for building ML models with scikit-learn and TensorFlow.",
		"Books",
		39.99,
		4.4,
		),
		(
		"P006",
		"Data Engineering Fundamentals",
		"Comprehensive guide to building modern data pipelines and architectures.",
		"Books",
		44.99,
		4.6,
		),
		(
		"P007",
		"Introduction to Deep Learning",
		"Beginner-friendly deep learning textbook with hands-on PyTorch examples.",
		"Books",
		54.99,
		4.7,
		),
		(
		"P008",
		"Trail Running Shoes",
		"Lightweight trail running shoes with superior grip and cushioning.",
		"Sports",
		129.99,
		4.6,
		),
		(
		"P009",
		"Premium Yoga Mat",
		"Non-slip extra-thick yoga mat with carrying strap.",
		"Sports",
		34.99,
		4.4,
		),
		(
		"P010",
		"Resistance Bands Set",
		"Set of 5 resistance bands with varying tension levels for home workouts.",
		"Sports",
		24.99,
		4.3,
		),
		(
		"P011",
		"Robot Vacuum Cleaner",
		"Self-navigating robot vacuum with app control and auto-charging.",
		"Home",
		349.99,
		4.5,
		),
		(
		"P012",
		"Air Purifier with HEPA Filter",
		"Room air purifier with true HEPA filter and air quality sensor.",
		"Home",
		199.99,
		4.6,
		),
		]

		embedding_dim = 384
		embeddings = np.zeros((len(products), embedding_dim), dtype=np.float32)
		embeddings[np.arange(len(products)), np.arange(len(products))] = 1.0

		end_date = datetime.now().replace(microsecond=0, second=0, minute=0)
		start_date = end_date - timedelta(days=15)
		timestamps = [start_date + timedelta(hours=i) for i in range(len(products))]

		columns = [
		"product_id",
		"product_name",
		"description",
		"category",
		"price",
		"rating",
		]
		df = pd.DataFrame(products, columns=columns)
		df["price"] = df["price"].astype(np.float32)
		df["rating"] = df["rating"].astype(np.float32)
		df["embedding"] = [embedding.tolist() for embedding in embeddings]
		df["event_timestamp"] = timestamps
		df["created"] = end_date

		products_path = data_path / "products.parquet"
		df.to_parquet(path=str(products_path), allow_truncated_timestamps=True)

		example_py_file = repo_path / "feature_definitions.py"
		replace_str_in_file(example_py_file, "%PROJECT_NAME%", str(project_name))
		replace_str_in_file(
		example_py_file, "%PARQUET_PATH%", str(products_path.relative_to(repo_path))
		)


		if __name__ == "__main__":
		bootstrap()

Empty file added 0 sdk/python/feast/templates/recommendation/feature_repo/__init__.py

Show comments

View file

Open in desktop

Empty file.

43 changes: 43 additions & 0 deletions 43 sdk/python/feast/templates/recommendation/feature_repo/feature_definitions.py

Show comments

View file

Open in desktop

Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,43 @@
		from datetime import timedelta

		from feast import Entity, FeatureService, FeatureView, Field, FileSource, Project
		from feast.types import Array, Float32, String

		project = Project(
		name="%PROJECT_NAME%",
		description="A project for product recommendations using vector similarity search",
		)

		product = Entity(name="product", join_keys=["product_id"])

		products_source = FileSource(
		name="products_source",
		path="%PARQUET_PATH%",
		timestamp_field="event_timestamp",
		created_timestamp_column="created",
		)

		# test_workflow.py writes model embeddings before materialization.
		product_embeddings = FeatureView(
		name="product_embeddings",
		entities=[product],
		ttl=timedelta(days=365),
		schema=[
		Field(
		name="embedding", dtype=Array(Float32), vector_index=True, vector_length=384
		),
		Field(name="product_name", dtype=String),
		Field(name="description", dtype=String),
		Field(name="category", dtype=String),
		Field(name="price", dtype=Float32),
		Field(name="rating", dtype=Float32),
		],
		online=True,
		source=products_source,
		tags={"team": "recommendations"},
		)

		recommendation_service = FeatureService(
		name="recommendation_service",
		features=[product_embeddings],
		)

13 changes: 13 additions & 0 deletions 13 sdk/python/feast/templates/recommendation/feature_repo/feature_store.yaml

Show comments

View file

Open in desktop

Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,13 @@
		project: my_project
		# By default, the registry is a file (but can be turned into a more scalable SQL-backed registry)
		registry: data/registry.db
		# The provider primarily specifies default offline / online stores & storing the registry in a given cloud
		provider: local
		online_store:
		type: sqlite
		path: data/online_store.db
		vector_enabled: true
		entity_key_serialization_version: 3
		# By default, no_auth for authentication and authorization, other possible values kubernetes and oidc. Refer the documentation for more details.
		auth:
		type: no_auth

70 changes: 70 additions & 0 deletions 70 sdk/python/feast/templates/recommendation/feature_repo/test_workflow.py

Show comments

View file

Open in desktop

Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,70 @@
		import subprocess
		import sys
		from datetime import datetime
		from pathlib import Path

		import numpy as np
		import pandas as pd

		from feast import FeatureStore


		def run_demo() -> None:
		try:
		from sentence_transformers import SentenceTransformer
		except ImportError:
		print("sentence-transformers is required: pip install sentence-transformers")
		sys.exit(1)

		model = SentenceTransformer("all-MiniLM-L6-v2")
		products_path = Path("data/products.parquet")
		products = pd.read_parquet(products_path)
		descriptions = (products["product_name"] + ". " + products["description"]).tolist()
		embeddings = model.encode(descriptions, normalize_embeddings=True)
		products["embedding"] = [
		embedding.astype(np.float32).tolist() for embedding in embeddings
		]
		products.to_parquet(products_path, allow_truncated_timestamps=True)

		print("\nApplying feature definitions")
		subprocess.run(["feast", "apply"], check=True)

		print("\nLoading features into the online store")
		store = FeatureStore(repo_path=".")
		store.materialize_incremental(end_date=datetime.now())

		query = "gaming laptop accessories"
		print(f"\nSearching for: {query}")
		query_embedding = model.encode([query], normalize_embeddings=True)[0].tolist()

		results = store.retrieve_online_documents_v2(
		features=[
		"product_embeddings:embedding",
		"product_embeddings:product_id",
		"product_embeddings:product_name",
		"product_embeddings:category",
		"product_embeddings:price",
		"product_embeddings:rating",
		],
		query=query_embedding,
		top_k=5,
		).to_dict()

		if results and len(results.get("product_id", [])) > 0:
		num_results = len(results["product_id"])
		print(f" Top {num_results} recommendations:")
		for i in range(num_results):
		name = results["product_name"][i]
		category = results["category"][i]
		price = results["price"][i]
		rating = results["rating"][i]
		print(f" {i + 1}. {name} [{category}] - ${price:.2f} (rating: {rating})")
		else:
		print(" No results found.")

		print("\nTearing down the feature store")
		subprocess.run(["feast", "teardown"], check=True)


		if __name__ == "__main__":
		run_demo()

32 changes: 32 additions & 0 deletions 32 sdk/python/tests/unit/local_feast_tests/test_init.py

Show comments

View file

Open in desktop

Original file line number	Diff line number	Diff line change
Expand Up		@@ -3,6 +3,9 @@
		from pathlib import Path
		from textwrap import dedent

		import pandas as pd

		from feast.repo_operations import init_repo
		from feast.utils import _utc_now
		from tests.utils.cli_repo_creator import CliRunner

Expand Down Expand Up		@@ -81,3 +84,32 @@ def test_postgres_template_registry_path_is_parameterized() -> None:
		contents = template_fs_yaml.read_text(encoding="utf-8")
		expected = "path: postgresql://DB_USERNAME:DB_PASSWORD@DB_HOST:DB_PORT/DB_NAME"
		assert expected in contents


		def test_recommendation_template_init(tmp_path: Path) -> None:
		repo_path = tmp_path / "recommendation_project"

		init_repo(
		"recommendation_project",
		template="recommendation",
		repo_path=str(repo_path),
		)

		feature_repo = repo_path / "feature_repo"
		config = (feature_repo / "feature_store.yaml").read_text(encoding="utf-8")
		assert "project: recommendation_project" in config
		assert "type: sqlite" in config
		assert "vector_enabled: true" in config

		definitions = (feature_repo / "feature_definitions.py").read_text(encoding="utf-8")
		assert "vector_index=True" in definitions
		assert "vector_length=384" in definitions
		assert 'name="recommendation_project"' in definitions
		assert 'path="data/products.parquet"' in definitions

		products_path = feature_repo / "data" / "products.parquet"
		assert products_path.is_file()
		products = pd.read_parquet(products_path)
		assert len(products) == 12
		assert all(len(embedding) == 384 for embedding in products["embedding"])
		assert not (repo_path / "bootstrap.py").exists()

Add this suggestion to a batch that can be applied as a single commit. This suggestion is invalid because no changes were made to the code. Suggestions cannot be applied while the pull request is closed. Suggestions cannot be applied while viewing a subset of changes. Only one suggestion per line can be applied in a batch. Add this suggestion to a batch that can be applied as a single commit. Applying suggestions on deleted lines is not supported. You must change the existing code in this line in order to create a valid suggestion. Outdated suggestions cannot be applied. This suggestion has been applied or marked resolved. Suggestions cannot be applied from pending reviews. Suggestions cannot be applied on multi-line comments. Suggestions cannot be applied while the pull request is queued to merge. Suggestion cannot be applied right now. Please check back later.

You are visitor 01402520 — GeezerVison does not store the pages you look up.
Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.