Merge branch 'master' into mariadb_offline_store

tmihalac · May 13, 2024 · c9d8184 · c9d8184
2 parents 387c56a + bf99640
commit c9d8184
Show file tree

Hide file tree

Showing 50 changed files with 2,536 additions and 1,552 deletions.
diff --git a/.github/workflows/master_only.yml b/.github/workflows/master_only.yml
@@ -142,7 +142,7 @@ jobs:
           SNOWFLAKE_CI_WAREHOUSE: ${{ secrets.SNOWFLAKE_CI_WAREHOUSE }}
         run: pytest --verbose --color=yes sdk/python/tests --integration --benchmark --benchmark-autosave --benchmark-save-data --durations=5
       - name: Upload Benchmark Artifact to S3
-        run: aws s3 cp --recursive .benchmarks s3://feast-ci-pytest-benchmarks
+        run: aws s3 cp --recursive .benchmarks s3://feast-ci-pytest-benchmark
 
   build-all-docker-images:
     if: github.repository == 'feast-dev/feast'

diff --git a/Makefile b/Makefile
@@ -47,7 +47,7 @@ install-python-ci-dependencies-uv:
 	python setup.py build_python_protos --inplace
 
 lock-python-ci-dependencies:
-	python -m piptools compile -U --extra ci --output-file sdk/python/requirements/py$(PYTHON)-ci-requirements.txt
+	uv pip compile --system --no-strip-extras setup.py --extra ci --output-file sdk/python/requirements/py$(PYTHON)-ci-requirements.txt
 
 package-protos:
 	cp -r ${ROOT_DIR}/protos ${ROOT_DIR}/sdk/python/feast/protos
@@ -60,13 +60,15 @@ install-python:
 	python setup.py develop
 
 lock-python-dependencies:
-	python -m piptools compile -U --output-file sdk/python/requirements/py$(PYTHON)-requirements.txt
+	uv pip compile --system --no-strip-extras setup.py --output-file sdk/python/requirements/py$(PYTHON)-requirements.txt 
 
 lock-python-dependencies-all:
-	pixi run --environment py39 --manifest-path infra/scripts/pixi/pixi.toml "python -m piptools compile -U --output-file sdk/python/requirements/py3.9-requirements.txt"
-	pixi run --environment py39 --manifest-path infra/scripts/pixi/pixi.toml "python -m piptools compile -U --extra ci --output-file sdk/python/requirements/py3.9-ci-requirements.txt"
-	pixi run --environment py310 --manifest-path infra/scripts/pixi/pixi.toml "python -m piptools compile -U --output-file sdk/python/requirements/py3.10-requirements.txt"
-	pixi run --environment py310 --manifest-path infra/scripts/pixi/pixi.toml "python -m piptools compile -U --extra ci --output-file sdk/python/requirements/py3.10-ci-requirements.txt"
+	pixi run --environment py39 --manifest-path infra/scripts/pixi/pixi.toml "uv pip compile --system --no-strip-extras setup.py --output-file sdk/python/requirements/py3.9-requirements.txt"
+	pixi run --environment py39 --manifest-path infra/scripts/pixi/pixi.toml "uv pip compile --system --no-strip-extras setup.py --extra ci --output-file sdk/python/requirements/py3.9-ci-requirements.txt"
+	pixi run --environment py310 --manifest-path infra/scripts/pixi/pixi.toml "uv pip compile --system --no-strip-extras setup.py --output-file sdk/python/requirements/py3.10-requirements.txt"
+	pixi run --environment py310 --manifest-path infra/scripts/pixi/pixi.toml "uv pip compile --system --no-strip-extras setup.py --extra ci --output-file sdk/python/requirements/py3.10-ci-requirements.txt"
+	pixi run --environment py311 --manifest-path infra/scripts/pixi/pixi.toml "uv pip compile --system --no-strip-extras setup.py --output-file sdk/python/requirements/py3.11-requirements.txt"
+	pixi run --environment py311 --manifest-path infra/scripts/pixi/pixi.toml "uv pip compile --system --no-strip-extras setup.py --extra ci --output-file sdk/python/requirements/py3.11-ci-requirements.txt"
 
 benchmark-python:
 	FEAST_USAGE=False IS_TEST=True python -m pytest --integration --benchmark  --benchmark-autosave --benchmark-save-data sdk/python/tests
@@ -183,7 +185,7 @@ test-python-universal-athena:
 	ATHENA_DATA_SOURCE=AwsDataCatalog \
 	ATHENA_DATABASE=default \
 	ATHENA_WORKGROUP=primary \
-	ATHENA_S3_BUCKET_NAME=feast-integration-tests \
+	ATHENA_S3_BUCKET_NAME=feast-int-bucket \
  	python -m pytest -n 8 --integration \
  	 	-k "not test_go_feature_server and \
 		    not test_logged_features_validation and \
@@ -319,6 +321,25 @@ test-python-universal-cassandra-no-cloud-providers:
 	  not test_snowflake" \
 	sdk/python/tests
 
+ test-python-universal-elasticsearch-online:
+	PYTHONPATH='.' \
+		FULL_REPO_CONFIGS_MODULE=sdk.python.feast.infra.online_stores.contrib.elasticsearch_repo_configuration \
+		PYTEST_PLUGINS=sdk.python.tests.integration.feature_repos.universal.online_store.elasticsearch \
+		python -m pytest -n 8 --integration \
+ 			-k "not test_universal_cli and \
+ 				not test_go_feature_server and \
+ 				not test_feature_logging and \
+				not test_reorder_columns and \
+				not test_logged_features_validation and \
+				not test_lambda_materialization_consistency and \
+				not test_offline_write and \
+				not test_push_features_to_offline_store and \
+				not gcs_registry and \
+				not s3_registry and \
+ 				not test_universal_types and \
+				not test_snowflake" \
+ 			sdk/python/tests
+
 test-python-universal:
 	python -m pytest -n 8 --integration sdk/python/tests
 
@@ -370,9 +391,6 @@ kill-trino-locally:
 install-protoc-dependencies:
 	pip install --ignore-installed protobuf==4.24.0 "grpcio-tools>=1.56.2,<2" mypy-protobuf==3.1.0
 
-install-feast-ci-locally:
-	pip install -e ".[ci]"
-
 # Docker
 
 build-docker: build-feature-server-python-aws-docker build-feature-transformation-server-docker build-feature-server-java-docker

diff --git a/docs/SUMMARY.md b/docs/SUMMARY.md
@@ -81,6 +81,7 @@
   * [Snowflake](reference/offline-stores/snowflake.md)
   * [BigQuery](reference/offline-stores/bigquery.md)
   * [Redshift](reference/offline-stores/redshift.md)
+  * [DuckDB](reference/offline-stores/duckdb.md)
   * [Spark (contrib)](reference/offline-stores/spark.md)
   * [PostgreSQL (contrib)](reference/offline-stores/postgres.md)
   * [Trino (contrib)](reference/offline-stores/trino.md)

diff --git a/docs/project/development-guide.md b/docs/project/development-guide.md
@@ -123,43 +123,44 @@ Note that this means if you are midway through working through a PR and rebase,
 Setting up your development environment for Feast Python SDK / CLI:
 1. Ensure that you have Docker installed in your environment. Docker is used to provision service dependencies during testing, and build images for feature servers and other components.
    - Please note that we use [Docker with BuiltKit](https://docs.docker.com/develop/develop-images/build_enhancements/).
-2. Ensure that you have `make`, Python (3.8 and above) with `pip`, installed.
+   - _Alternatively_ - To use [podman](https://podman.io/) on a Fedora or RHEL machine, follow this [guide](https://github.com/feast-dev/feast/issues/4190)
+2. Ensure that you have `make` and Python (3.9 or above) installed.
 3. _Recommended:_ Create a virtual environment to isolate development dependencies to be installed
   ```sh
   # create & activate a virtual environment
   python -m venv venv/
   source venv/bin/activate
   ```
-4. Upgrade `pip` if outdated
-  ```sh
-  pip install --upgrade pip
-  ```
-5. (M1 Mac only): Follow the [dev guide](https://github.com/feast-dev/feast/issues/2105)
-6. Install pip-tools
-  ```sh
-  pip install pip-tools
-  ```
-7. (Optional): Install Node & Yarn. Then run the following to build Feast UI artifacts for use in `feast ui`
+4. (M1 Mac only): Follow the [dev guide](https://github.com/feast-dev/feast/issues/2105)
+5. Install uv
+It is recommended to use uv for managing python dependencies.
+```sh
+curl -LsSf https://astral.sh/uv/install.sh | sh
+```
+or
+```ssh
+pip install uv
+```
+6. (Optional): Install Node & Yarn. Then run the following to build Feast UI artifacts for use in `feast ui`
 ```
 make build-ui
 ```
-8. Install mysql (needed for ci dependencies)
+7. (Optional) install pixi
+pixi is necessary to run step 8 for all python versions at once.
 ```sh
-brew install mysql
+curl -fsSL https://pixi.sh/install.sh | bash
 ```
-9. Install development dependencies for Feast Python SDK / CLI
+8. (Optional): Recompile python lock files
+If you make changes to requirements or simply want to update python lock files to reflect latest versioons.
 ```sh
-pip install -e ".[dev]"
-```
-
-This will allow the installed feast version to automatically reflect changes to your local development version of Feast without needing to reinstall everytime you make code changes.
-
-10. Compile the protubufs
+make lock-python-dependencies-all
+``` 
+9. Install development dependencies for Feast Python SDK / CLI
+This will install package versions from the lock file, install editable version of feast and compile protobufs.
 ```sh
-make compile-protos-python
+make install-python-ci-dependencies-uv
 ```
-
-11. Spin up Docker Image
+10. Spin up Docker Image
 ```sh
 docker build -t docker-whale -f ./sdk/python/feast/infra/feature_servers/multicloud/Dockerfile .
 ```

diff --git a/docs/reference/alpha-vector-database.md b/docs/reference/alpha-vector-database.md
@@ -0,0 +1,111 @@
+# [Alpha] Vector Database
+**Warning**: This is an _experimental_ feature. To our knowledge, this is stable, but there are still rough edges in the experience. Contributions are welcome!
+
+## Overview
+Vector database allows user to store and retrieve embeddings. Feast provides general APIs to store and retrieve embeddings.
+
+## Integration
+Below are supported vector databases and implemented features:
+
+| Vector Database | Retrieval | Indexing |
+|-----------------|-----------|----------|
+| Pgvector        | [x]       | [ ]      |
+| Elasticsearch   | [x]       | [x]      |
+| Milvus          | [ ]       | [ ]      |
+| Faiss           | [ ]       | [ ]      |
+
+
+## Example
+
+See [https://github.com/feast-dev/feast-workshop/blob/rag/module_4_rag](https://github.com/feast-dev/feast-workshop/blob/rag/module_4_rag) for an example on how to use vector database.
+
+### **Prepare offline embedding dataset**
+Run the following commands to prepare the embedding dataset:
+```shell
+python pull_states.py
+python batch_score_documents.py
+```
+The output will be stored in `data/city_wikipedia_summaries.csv.`
+
+### **Initialize Feast feature store and materialize the data to the online store**
+Use the feature_tore.yaml file to initialize the feature store. This will use the data as offline store, and Pgvector as online store.
+
+```yaml
+project: feast_demo_local
+provider: local
+registry:
+  registry_type: sql
+  path: postgresql://@localhost:5432/feast
+online_store:
+  type: postgres
+  pgvector_enabled: true
+  vector_len: 384
+  host: 127.0.0.1
+  port: 5432
+  database: feast
+  user: ""
+  password: ""
+
+
+offline_store:
+  type: file
+entity_key_serialization_version: 2
+```
+Run the following command in terminal to apply the feature store configuration:
+
+```shell
+feast apply
+```
+
+Note that when you run `feast apply` you are going to apply the following Feature View that we will use for retrieval later:  
+
+```python
+city_embeddings_feature_view = FeatureView(
+    name="city_embeddings",
+    entities=[item],
+    schema=[
+        Field(name="Embeddings", dtype=Array(Float32)),
+    ],
+    source=source,
+    ttl=timedelta(hours=2),
+)
+```
+
+Then run the following command in the terminal to materialize the data to the online store:  
+
+```shell  
+CURRENT_TIME=$(date -u +"%Y-%m-%dT%H:%M:%S")  
+feast materialize-incremental $CURRENT_TIME  
+```
+
+### **Prepare a query embedding**
+```python
+from batch_score_documents import run_model, TOKENIZER, MODEL
+from transformers import AutoTokenizer, AutoModel
+
+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)
+query = query_embedding.detach().cpu().numpy().tolist()[0]
+```
+
+### **Retrieve the top 5 similar documents**
+First create a feature store instance, and use the `retrieve_online_documents` API to retrieve the top 5 similar documents to the specified query.
+
+```python
+from feast import FeatureStore
+store = FeatureStore(repo_path=".")
+features = store.retrieve_online_documents(
+    feature="city_embeddings:Embeddings",
+    query=query,
+    top_k=5
+).to_dict()
+
+def print_online_features(features):
+    for key, value in sorted(features.items()):
+        print(key, " : ", value)
+
+print_online_features(features)
+```
diff --git a/docs/reference/data-sources/file.md b/docs/reference/data-sources/file.md
@@ -3,11 +3,7 @@
 ## Description
 
 File data sources are files on disk or on S3.
-Currently only Parquet files are supported.
-
-{% hint style="warning" %}
-FileSource is meant for development purposes only and is not optimized for production use.
-{% endhint %}
+Currently only Parquet and Delta formats are supported.
 
 ## Example
 

diff --git a/docs/reference/data-sources/overview.md b/docs/reference/data-sources/overview.md
@@ -2,8 +2,8 @@
 
 ## Functionality
 
-In Feast, each batch data source is associated with a corresponding offline store.
-For example, a `SnowflakeSource` can only be processed by the Snowflake offline store.
+In Feast, each batch data source is associated with corresponding offline stores.
+For example, a `SnowflakeSource` can only be processed by the Snowflake offline store, while a `FileSource` can be processed by both File and DuckDB offline stores.
 Otherwise, the primary difference between batch data sources is the set of supported types.
 Feast has an internal type system, and aims to support eight primitive types (`bytes`, `string`, `int32`, `int64`, `float32`, `float64`, `bool`, and `timestamp`) along with the corresponding array types.
 However, not every batch data source supports all of these types.

diff --git a/docs/reference/offline-stores/README.md b/docs/reference/offline-stores/README.md
@@ -22,6 +22,10 @@ Please see [Offline Store](../../getting-started/architecture-and-components/off
 [redshift.md](redshift.md)
 {% endcontent-ref %}
 
+{% content-ref url="duckdb.md" %}
+[duckdb.md](duckdb.md)
+{% endcontent-ref %}
+
 {% content-ref url="spark.md" %}
 [spark.md](spark.md)
 {% endcontent-ref %}

diff --git a/docs/reference/offline-stores/duckdb.md b/docs/reference/offline-stores/duckdb.md
@@ -0,0 +1,56 @@
+# DuckDB offline store
+
+## Description
+
+The duckdb offline store provides support for reading [FileSources](../data-sources/file.md). It can read both Parquet and Delta formats. DuckDB offline store uses [ibis](https://ibis-project.org/) under the hood to convert offline store operations to DuckDB queries.
+
+* Entity dataframes can be provided as a Pandas dataframe.
+
+## Getting started
+In order to use this offline store, you'll need to run `pip install 'feast[duckdb]'`.
+
+## Example
+
+{% code title="feature_store.yaml" %}
+```yaml
+project: my_project
+registry: data/registry.db
+provider: local
+offline_store:
+    type: duckdb
+online_store:
+    path: data/online_store.db
+```
+{% endcode %}
+
+## Functionality Matrix
+
+The set of functionality supported by offline stores is described in detail [here](overview.md#functionality).
+Below is a matrix indicating which functionality is supported by the DuckDB offline store.
+
+|                                                                    | DuckdDB |
+| :----------------------------------------------------------------- | :----   |
+| `get_historical_features` (point-in-time correct join)             | yes     |
+| `pull_latest_from_table_or_query` (retrieve latest feature values) | yes     |
+| `pull_all_from_table_or_query` (retrieve a saved dataset)          | yes     |
+| `offline_write_batch` (persist dataframes to offline store)        | yes     |
+| `write_logged_features` (persist logged features to offline store) | yes     |
+
+Below is a matrix indicating which functionality is supported by `IbisRetrievalJob`.
+
+|                                                       | DuckDB|
+| ----------------------------------------------------- | ----- |
+| export to dataframe                                   | yes   |
+| export to arrow table                                 | yes   |
+| export to arrow batches                               | no    |
+| export to SQL                                         | no    |
+| export to data lake (S3, GCS, etc.)                   | no    |
+| export to data warehouse                              | no    |
+| export as Spark dataframe                             | no    |
+| local execution of Python-based on-demand transforms  | yes   |
+| remote execution of Python-based on-demand transforms | no    |
+| persist results in the offline store                  | yes   |
+| preview the query plan before execution               | no    |
+| read partitioned data                                 | yes   |
+
+To compare this set of functionality against other offline stores, please see the full [functionality matrix](overview.md#functionality-matrix).
diff --git a/docs/reference/offline-stores/overview.md b/docs/reference/offline-stores/overview.md
@@ -42,17 +42,17 @@ Below is a matrix indicating which offline stores support which methods.
 
 Below is a matrix indicating which `RetrievalJob`s support what functionality.
 
-| | File | BigQuery | Snowflake | Redshift | Postgres | Spark | Trino |
-| --------------------------------- | --- | --- | --- | --- | --- | --- | --- |
-| export to dataframe                                   | yes | yes | yes | yes | yes | yes | yes |
-| export to arrow table                                 | yes | yes | yes | yes | yes | yes | yes |
-| export to arrow batches                               | no  | no  | no  | yes | no  | no  | no  |
-| export to SQL                                         | no  | yes | yes  | yes | yes | no | yes |
-| export to data lake (S3, GCS, etc.)                   | no  | no  | yes | no  | yes | no  | no  |
-| export to data warehouse                              | no  | yes | yes | yes | yes | no  | no  |
-| export as Spark dataframe                             | no  | no  | yes | no  | no  | yes | no  |
-| local execution of Python-based on-demand transforms  | yes | yes | yes | yes | yes | no  | yes |
-| remote execution of Python-based on-demand transforms | no  | no  | no  | no  | no  | no  | no  |
-| persist results in the offline store                  | yes | yes | yes | yes | yes | yes | no  |
-| preview the query plan before execution               | yes | yes | yes | yes | yes | yes | yes |
-| read partitioned data                                 | yes | yes | yes | yes | yes | yes | yes |
+| | File | BigQuery | Snowflake | Redshift | Postgres | Spark | Trino | DuckDB |
+| --------------------------------- | --- | --- | --- | --- | --- | --- | --- | --- |
+| export to dataframe                                   | yes | yes | yes | yes | yes | yes | yes | yes | 
+| export to arrow table                                 | yes | yes | yes | yes | yes | yes | yes | yes |
+| export to arrow batches                               | no  | no  | no  | yes | no  | no  | no  | no  |
+| export to SQL                                         | no  | yes | yes | yes | yes | no  | yes | no  |
+| export to data lake (S3, GCS, etc.)                   | no  | no  | yes | no  | yes | no  | no  | no  |
+| export to data warehouse                              | no  | yes | yes | yes | yes | no  | no  | no  |
+| export as Spark dataframe                             | no  | no  | yes | no  | no  | yes | no  | no  |
+| local execution of Python-based on-demand transforms  | yes | yes | yes | yes | yes | no  | yes | yes |
+| remote execution of Python-based on-demand transforms | no  | no  | no  | no  | no  | no  | no  | no  |
+| persist results in the offline store                  | yes | yes | yes | yes | yes | yes | no  | yes |
+| preview the query plan before execution               | yes | yes | yes | yes | yes | yes | yes | no  |
+| read partitioned data                                 | yes | yes | yes | yes | yes | yes | yes | yes |