### Install Python Dependencies

Source: https://github.com/feast-dev/feast/blob/master/examples/credit-risk-end-to-end/README.md

Install the necessary Python packages for the example using pip. Ensure your virtual environment is activated.

```bash
pip install -r requirements.txt
```

--------------------------------

### Basic Permission Setup Examples

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/auth/kubernetes_auth_setup.md

Demonstrates setting up various permission types including role-based, group-based, namespace-based, and combined policies for Feast resources. These permissions can be applied via `feast apply`.

```python
from feast.feast_object import ALL_RESOURCE_TYPES
from feast.permissions.action import READ, AuthzedAction, ALL_ACTIONS
from feast.permissions.permission import Permission
from feast.permissions.policy import (
    RoleBasedPolicy,
    GroupBasedPolicy,
    NamespaceBasedPolicy,
    CombinedGroupNamespacePolicy
)

# Role-based permission
role_perm = Permission(
    name="role_permission",
    types=ALL_RESOURCE_TYPES,
    policy=RoleBasedPolicy(roles=["reader-role"]),
    actions=[AuthzedAction.DESCRIBE] + READ
)

# Group-based permission (new)
data_team_perm = Permission(
    name="data_team_permission",
    types=ALL_RESOURCE_TYPES,
    policy=GroupBasedPolicy(groups=["data-team", "ml-engineers"]),
    actions=[AuthzedAction.DESCRIBE] + READ
)

# Namespace-based permission (new)
prod_perm = Permission(
    name="production_permission",
    types=ALL_RESOURCE_TYPES,
    policy=NamespaceBasedPolicy(namespaces=["production"]),
    actions=[AuthzedAction.DESCRIBE] + READ
)

# Combined permission (new)
dev_staging_perm = Permission(
    name="dev_staging_permission",
    types=ALL_RESOURCE_TYPES,
    policy=CombinedGroupNamespacePolicy(
        groups=["dev-team"],
        namespaces=["staging"]
    ),
    actions=ALL_ACTIONS
)
```

--------------------------------

### Install Dependencies

Source: https://github.com/feast-dev/feast/blob/master/infra/website/README.md

Installs project dependencies using npm. Run this before starting the development server.

```bash
npm install
```

--------------------------------

### Initialize and Setup Feast Project

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/feast/templates/pytorch_nlp/README.md

Initializes a new Feast project with the pytorch_nlp template and installs necessary dependencies.

```bash
# Create new project
feast init my-sentiment-demo -t pytorch_nlp
cd my-sentiment-demo

# Install dependencies
pip install torch>=2.0.0 transformers>=4.30.0

# Navigate to feature repository
cd feature_repo
```

--------------------------------

### Install Feast Feature Server in Different Modes

Source: https://github.com/feast-dev/feast/blob/master/infra/charts/feast-feature-server/README.md

Examples for installing the Feast Feature Server in various deployment modes. Ensure you have a base64 encoded feature_store.yaml file ready.

```bash
helm install feast-feature-server feast-charts/feast-feature-server --set feature_store_yaml_base64=$(base64 > feature_store.yaml)
```

```bash
helm install feast-offline-server feast-charts/feast-feature-server --set feast_mode=offline  --set feature_store_yaml_base64=$(base64 > feature_store.yaml)
```

```bash
helm install feast-ui-server feast-charts/feast-feature-server --set feast_mode=ui  --set feature_store_yaml_base64=$(base64 > feature_store.yaml)
```

```bash
helm install feast-registry-server feast-charts/feast-feature-server --set feast_mode=registry  --set feature_store_yaml_base64=$(base64 > feature_store.yaml)
```

--------------------------------

### Run Registry Server in Different Modes

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/feature-servers/registry-server.md

Examples of how to start the registry server in its three supported modes: gRPC only, REST + gRPC, and REST only.

```bash
feast serve_registry
```

```bash
feast serve_registry --rest-api
```

```bash
feast serve_registry --rest-api --no-grpc
```

--------------------------------

### Start and Create Redis Cluster

Source: https://github.com/feast-dev/feast/blob/master/docs/how-to-guides/adding-or-reusing-tests.md

Use these commands to start a local Redis cluster for testing purposes. Ensure Redis is installed and accessible in your PATH.

```bash
./infra/scripts/redis-cluster.sh start
./infra/scripts/redis-cluster.sh create
```

--------------------------------

### Install Colima and Kubectl

Source: https://github.com/feast-dev/feast/blob/master/examples/operator-quickstart/01-Install.ipynb

Installs the Colima container runtime and kubectl CLI on macOS. Starts Colima with specified configurations for a local Kubernetes environment.

```bash
brew install colima kubectl
colima start -r containerd -k -m 3 -d 100 -c 2 --cpu-type max -a x86_64
colima list
```

--------------------------------

### Install KServe

Source: https://github.com/feast-dev/feast/blob/master/infra/website/docs/blog/kubeflow-fraud-detection-e2e.md

Installs KServe by creating a namespace, setting it as the current context, and running the quick installation script. Remember to switch back to the Kubeflow namespace afterwards.

```bash
kubectl create namespace kserve
kubectl config set-context --current --namespace=kserve
curl -s "https://raw.githubusercontent.com/kserve/kserve/release-0.15/hack/quick_install.sh" | bash
kubectl config set-context --current --namespace=kubeflow
```

--------------------------------

### Start Milvus Containers with Docker Compose

Source: https://github.com/feast-dev/feast/blob/master/examples/online_store/milvus_tutorial/README.md

Use this command to start the Milvus server, etcd, and MinIO containers. Ensure Docker is installed and running.

```bash
docker compose up -d
```

--------------------------------

### Navigate to Example Directory

Source: https://github.com/feast-dev/feast/blob/master/examples/mcp_feature_store/README.md

Change your current directory to the MCP feature store example within the Feast repository.

```bash
cd examples/mcp_feature_store
```

--------------------------------

### Redis Online Store Creator Example

Source: https://github.com/feast-dev/feast/blob/master/docs/how-to-guides/customizing-feast/adding-support-for-a-new-online-store.md

Example of an OnlineStoreCreator for a Redis online store, including container start, log waiting, and stop.

```python
class RedisOnlineStoreCreator(OnlineStoreCreator):
    def __init__(self, project_name: str, **kwargs):
        super().__init__(project_name)

    def create_online_store(self) -> Dict[str, str]:
        self.container.start()
        log_string_to_wait_for = "Ready to accept connections"
        wait_for_logs(
            container=self.container, predicate=log_string_to_wait_for, timeout=10
        )
        self.container.stop()
```

--------------------------------

### Running Feast Agent Demo

Source: https://github.com/feast-dev/feast/blob/master/infra/website/docs/blog/feast-agents-mcp.md

Clone the Feast repository and navigate to the agent example directory. Execute the './run_demo.sh' script to start the demo, optionally providing an OpenAI API key for live LLM integration.

```bash
git clone https://github.com/feast-dev/feast.git
cd feast/examples/agent_feature_store

./run_demo.sh                          # demo mode (no API key needed)
OPENAI_API_KEY=sk-... ./run_demo.sh    # live LLM tool-calling
```

--------------------------------

### Start the React App

Source: https://github.com/feast-dev/feast/blob/master/ui/README.md

Command to start the React development server after setting up Feast UI.

```bash
// Start the React App
yarn start
```

--------------------------------

### Install Feast

Source: https://github.com/feast-dev/feast/blob/master/docs/blog/feast-0-10-announcement.md

Install the Feast library using pip. This is the first step to using Feast.

```bash
pip install feast
```

--------------------------------

### Initialize Feast NLP Project Template

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/alpha-static-artifacts.md

This command initializes a new Feast project using the PyTorch NLP template, which includes a complete example of static artifact loading for sentiment analysis. It then navigates to the feature repository and starts the Feast server.

```bash
feast init my-nlp-project -t pytorch_nlp
cd my-nlp-project/feature_repo
feast serve
```

--------------------------------

### Install Feast Helm Chart

Source: https://github.com/feast-dev/feast/blob/master/infra/charts/feast/README.md

Install the Feast Helm chart with a release name of 'feast-release'.

```bash
helm install feast-release feast-charts/feast
```

--------------------------------

### Start Feature Transformation Server

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/feast.md

Starts a local server specifically for feature transformations.

```python
serve_transformations(port=6006)
```

--------------------------------

### Install Feast with OpenLineage Support

Source: https://github.com/feast-dev/feast/blob/master/examples/openlineage-integration/README.md

Install the Feast library with the OpenLineage integration package. This is a prerequisite for running the demo.

```bash
pip install feast[openlineage]
```

--------------------------------

### Generate Sample Data

Source: https://github.com/feast-dev/feast/blob/master/examples/agent_feature_store/README.md

Run the setup script to generate customer profiles, knowledge base articles with embeddings, and an agent memory scaffold.

```bash
cd examples/agent_feature_store
python setup_data.py
```

--------------------------------

### Get Popular Tags API Examples

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/feature-servers/registry-server.md

Examples of how to call the GET /api/v1/metrics/popular_tags endpoint to discover Feature Views by popular tags. Supports filtering by project and custom limits.

```bash
curl -H "Authorization: Bearer <token>" \
  "http://localhost:6572/api/v1/metrics/popular_tags"
```

```bash
curl -H "Authorization: Bearer <token>" \
  "http://localhost:6572/api/v1/metrics/popular_tags?project=my_project"
```

```bash
curl -H "Authorization: Bearer <token>" \
  "http://localhost:6572/api/v1/metrics/popular_tags?project=my_project&limit=3"
```

--------------------------------

### Run OpenLineage Integration Example

Source: https://github.com/feast-dev/feast/blob/master/infra/website/docs/blog/feast-openlineage-integration.md

Steps to run the end-to-end OpenLineage integration example. Requires Marquez to be running first.

```bash
# Start Marquez first
docker run -p 5000:5000 -p 3000:3000 marquezproject/marquez

# Clone and run the example
cd feast/examples/openlineage-integration
python openlineage_demo.py --url http://localhost:5000

# View lineage at http://localhost:3000
```

--------------------------------

### Example OpenTelemetry Configuration

Source: https://github.com/feast-dev/feast/blob/master/docs/getting-started/components/open-telemetry.md

An example configuration snippet showing how to enable metrics and set the OpenTelemetry Collector endpoint.

```yaml
metrics:
  enabled: true
  otelCollector:
    endpoint: "otel-collector.default.svc.cluster.local:4317"
```

--------------------------------

### Install Feast with Hybrid Offline Store Dependencies

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/offline-stores/hybrid.md

Install Feast with all required offline store dependencies for the stores you plan to use. This example shows installation for Spark and Snowflake.

```bash
pip install 'feast[spark,snowflake]'
```

--------------------------------

### View Feast Init Help

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/feast/templates/milvus/README.md

Display available templates and options for initializing a new Feast project.

```bash
feast init --help
```

--------------------------------

### Install Feast with Online Store Dependencies

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/online-stores/hybrid.md

Install Feast with the necessary dependencies for all online stores you plan to use with the HybridOnlineStore. For example, to use GCP and Cassandra, install 'feast[gcp,cassandra]'.

```bash
pip install 'feast[gcp,cassandra]'
```

--------------------------------

### Feast Server TLS Output Example

Source: https://github.com/feast-dev/feast/blob/master/docs/how-to-guides/starting-feast-servers-tls-mode.md

Example output when starting a Feast server in TLS mode, indicating the server is serving over HTTPS.

```text
11/07/2024 11:10:01 AM feast.offline_server INFO: Found SSL certificates in the args so going to start offline server in TLS(SSL) mode.
11/07/2024 11:10:01 AM feast.offline_server INFO: Offline store server serving at: grpc+tls://127.0.0.1:8815
11/07/2024 11:10:01 AM feast.offline_server INFO: offline server starting with pid: [11606]
```

```text
INFO:     Started server process [78872]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on https://0.0.0.0:8888 (Press CTRL+C to quit)
```

--------------------------------

### serve_ui

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/index.md

Starts the UI server locally.

```APIDOC
## serve_ui(host: str, port: int, get_registry_dump: Callable, registry_ttl_sec: int, root_path: str = '', tls_key_path: str = '', tls_cert_path: str = '') -> None

Start the UI server locally
```

--------------------------------

### Install Feast with Qdrant Support

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/alpha-vector-database.md

Installs the Feast package with Qdrant integration. This command is for setting up Feast to connect with Qdrant.

```bash
pip install feast[qdrant]
```

--------------------------------

### Start UI Server

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/source/feast.md

Launch the UI server locally using `serve_ui`. This requires a callable for `get_registry_dump` and configuration for port, root path, and TLS.

```python
serve_ui(host='localhost', port=9090, get_registry_dump=get_registry_dump)
```

--------------------------------

### Startup Model Loading (Optimized)

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/feast/templates/pytorch_nlp/README.md

Illustrates the optimized approach of loading a model once at server startup.

```python
# ✅ Model loads once at server startup
def sentiment_prediction(inputs):
    global _sentiment_model  # Pre-loaded model
    return _sentiment_model(inputs["text"])
```

--------------------------------

### Create and Activate Virtual Environment

Source: https://github.com/feast-dev/feast/blob/master/examples/credit-risk-end-to-end/README.md

Use these commands to create a virtual environment for the example and activate it. This helps isolate project dependencies.

```bash
# create venv-example virtual environment
python -m venv venv-example
# activate environment
source venv-example/bin/activate
```

--------------------------------

### Build and Run Go Feature Server

Source: https://github.com/feast-dev/feast/blob/master/go/README.md

Build the Go Feature Server executable and start it as an HTTP or gRPC server. Ensure a feature_store.yaml file is present for configuration.

```bash
go build -o feast-go ./go/main.go
```

```bash
./feast-go --type=http --port=8080 --metrics-port=9090
```

```bash
#./feast-go --type=grpc  --port=[your-choice] --metrics-port=9091
```

--------------------------------

### Install SQLAlchemy dialect for external databases (Shell)

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/registries/sql.md

When using a database with an external dialect not directly supported by SQLAlchemy, install the corresponding SQLAlchemy dialect package using pip. This example shows installation for CockroachDB.

```shell
pip install sqlalchemy-cockroachdb
```

--------------------------------

### start_server

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/source/modules.md

Starts the feature server.

```APIDOC
## start_server()

### Description
Starts the feature server.

### Method
`start_server`

### Parameters
This function does not explicitly list parameters in the provided source. Refer to the Feast SDK for detailed parameter information.
```

--------------------------------

### Multi-Version Materialization Workflow Example (CLI)

Source: https://github.com/feast-dev/feast/blob/master/docs/rfcs/feature-view-versioning.md

Demonstrates materializing data for multiple versions of the same feature view to support different models. This allows models to query their respective versions online.

```bash
# Model A uses v1, Model B uses v2 — populate both tables
feast materialize --views driver_stats --version v1 2024-01-01T00:00:00 2024-02-01T00:00:00
feast materialize --views driver_stats --version v2 2024-01-01T00:00:00 2024-02-01T00:00:00

# Models can now query their respective versions online
# Model A: store.get_online_features(features=["driver_stats@v1:trips_today"], ...)
# Model B: store.get_online_features(features=["driver_stats@v2:trips_today"], ...)
```

--------------------------------

### Get Torch Module

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/feast.md

Retrieves the torch module if available. Raises an error if torch is not installed or CUDA libraries are missing.

```APIDOC
## feast.torch_wrapper.get_torch()

### Description
Return the torch module if available, else raise a friendly error. This prevents crashing on import if CUDA libs are missing.

### Returns
`torch` module if available.
```

--------------------------------

### Initialize and Serve Feature Repository

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/feature-servers/python-feature-server.md

Demonstrates the steps to initialize a new Feast feature repository, apply configurations, materialize data, and start the feature server.

```bash
$ feast init feature_repo
Creating a new Feast repository in /home/tsotne/feast/feature_repo.

$ cd feature_repo

$ feast apply
Created entity driver
Created feature view driver_hourly_stats
Created feature service driver_activity

Created sqlite table feature_repo_driver_hourly_stats

$ feast materialize-incremental $(date +%Y-%m-%d)
Materializing 1 feature views to 2021-09-09 17:00:00-07:00 into the sqlite online store.

driver_hourly_stats from 2021-09-09 16:51:08-07:00 to 2021-09-09 17:00:00-07:00:
100%|████████████████████████████████████████████████████████████████| 5/5 [00:00<00:00, 295.24it/s]

$ feast serve
09/10/2021 10:42:11 AM INFO:Started server process [8889]
INFO:     Waiting for application startup.
09/10/2021 10:42:11 AM INFO:Waiting for application startup.
INFO:     Application startup complete.
09/10/2021 10:42:11 AM INFO:Application startup complete.
INFO:     Uvicorn running on http://127.0.0.1:6566 (Press CTRL+C to quit)
09/10/2021 10:42:11 AM INFO:Uvicorn running on http://127.0.0.1:6566 (Press CTRL+C to quit)
```

--------------------------------

### Configure Local Registry

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/registries/local.md

Example configuration for a local registry in feature_store.yaml. This setup is intended for experimentation and specifies a local file path for the registry and a Dask offline store.

```yaml
project: feast_local
registry:
  path: registry.pb
  cache_ttl_seconds: 60
online_store: null
offline_store:
  type: dask
```

--------------------------------

### Start Feast Feature Servers with Podman Compose

Source: https://github.com/feast-dev/feast/blob/master/examples/podman_local/README.md

Launches the necessary containers for online, offline, and registry feature servers. Ensure Podman Compose is installed and the docker-compose.yml file is present.

```bash
podman-compose up -d
```

--------------------------------

### Example feature_store.yaml

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/feature-repository/feature-store-yaml.md

This is a basic example of a feature_store.yaml file. It specifies the project name, registry location, provider, and online store configuration.

```yaml
project: loyal_spider
registry: data/registry.db
provider: local
online_store:
    type: sqlite
    path: data/online_store.db
```

--------------------------------

### serve_ui

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/index.md

Starts the UI server locally, requiring a registry dump callable and port configuration, with optional TLS.

```APIDOC
## serve_ui(host: str, port: int, get_registry_dump: Callable, registry_ttl_sec: int, root_path: str = '', tls_key_path: str = '', tls_cert_path: str = '') -> None

### Description
Start the UI server locally.

### Parameters
* **host** – The host address to bind the server to.
* **port** – The port number to bind the server to.
* **get_registry_dump** – A callable that returns the registry dump.
* **registry_ttl_sec** – Time-to-live for registry entries in seconds.
* **root_path** – The root path for the UI server. Defaults to ''.
* **tls_key_path** – Path to the TLS key file for HTTPS.
* **tls_cert_path** – Path to the TLS certificate file for HTTPS.
```

--------------------------------

### Production Feature Store Configuration (GCP)

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/feast/templates/pytorch_nlp/README.md

Example `feature_store.yaml` configuration for deploying the feature store on GCP production. This setup requires a Redis server for the online store and BigQuery for the offline store.

```yaml
# feature_store.yaml for GCP production (requires cloud services)
project: sentiment_analysis_prod
provider: gcp
registry: gs://my-bucket/feast/registry.pb
online_store:
  type: redis                      # Requires separate Redis server
  connection_string: redis://my-redis-cluster:6379
offline_store:
  type: bigquery
  project_id: my-gcp-project
```

--------------------------------

### Production Feature Store Configuration (AWS)

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/feast/templates/pytorch_nlp/README.md

Example `feature_store.yaml` configuration for deploying the feature store on AWS production. This setup requires a Redis server for the online store and BigQuery for the offline store.

```yaml
# feature_store.yaml for AWS production (requires Redis setup)
project: sentiment_analysis_prod
provider: aws
registry: s3://my-bucket/feast/registry.pb
online_store:
  type: redis                      # Requires separate Redis server
  connection_string: redis://my-redis-cluster:6379
offline_store:
  type: bigquery
  project_id: my-gcp-project
```

--------------------------------

### FeastInitOptions

Source: https://github.com/feast-dev/feast/blob/master/infra/feast-operator/docs/api/markdown/ref.md

FeastInitOptions defines how to run a `feast init` command.

```APIDOC
## FeastInitOptions

### Description
FeastInitOptions defines how to run a `feast init`.

### Fields
- `minimal` (boolean): If true, initializes a minimal Feast project.
- `template` (string): Template for the created project.
```

--------------------------------

### serve_ui

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/feast.md

Starts the UI server locally, providing a web interface for interacting with the feature store. Requires a callable for registry dump and other configurations.

```APIDOC
## serve_ui

### Description
Start the UI server locally.

### Method
`serve_ui`

### Parameters
#### Path Parameters
None

#### Query Parameters
* **host** (str) - Required - The host address to bind the server to.
* **port** (int) - Required - The port number to listen on.
* **get_registry_dump** (Callable) - Required - A callable function to get the registry dump.
* **registry_ttl_sec** (int) - Required - Time-to-live for registry entries in seconds.
* **root_path** (str) - Optional - The root path for the UI. Defaults to ''.
* **tls_key_path** (str) - Optional - Path to the TLS key file for HTTPS.
* **tls_cert_path** (str) - Optional - Path to the TLS certificate file for HTTPS.

### Response
None
```

--------------------------------

### RAG Query Example with Feast and Sentence Transformers

Source: https://github.com/feast-dev/feast/blob/master/infra/website/docs/blog/feast-ray-distributed-processing.md

Demonstrates retrieving similar documents using Feast's online store with a query embedding generated by SentenceTransformer. Requires Feast and SentenceTransformer to be installed.

```python
from feast import FeatureStore
from sentence_transformers import SentenceTransformer

# Initialize feature store
store = FeatureStore(repo_path=".")

# Generate query embedding
model = SentenceTransformer("all-MiniLM-L6-v2")
query_embedding = model.encode(["sci-fi movie about space"])[0].tolist()

# Retrieve similar documents
results = store.retrieve_online_documents_v2(
    features=[
        "document_embeddings:embedding",
        "document_embeddings:movie_name",
        "document_embeddings:movie_director",
    ],
    query=query_embedding,
    top_k=5,
).to_dict()

# Display results
for i in range(len(results["document_id_pk"])):
    print(f"{i+1}. {results['movie_name'][i]}")
    print(f"   Director: {results['movie_director'][i]}")
    print(f"   Distance: {results['distance'][i]:.3f}")
```

--------------------------------

### Run Demo Script

Source: https://github.com/feast-dev/feast/blob/master/examples/agent_feature_store/README.md

Execute the main demo script. Set OPENAI_API_KEY for live LLM tool-calling.

```bash
cd examples/agent_feature_store
./run_demo.sh

# Or with live LLM tool-calling:
OPENAI_API_KEY=sk-... ./run_demo.sh
```

--------------------------------

### Get Online Features Using Feature Service

Source: https://github.com/feast-dev/feast/blob/master/docs/how-to-guides/federated-feature-store.md

Retrieve online features for training or inference by referencing a FeatureService name. This example demonstrates fetching features for a specific entity row, including both platform and team-defined features.

```python
# In team's training or inference code
from feast import FeatureStore

store = FeatureStore(repo_path=".")

# Get online features using team's feature service
features = store.get_online_features(
    features="team_marketing_campaign_model",
    entity_rows=[
        {"customer_id": "C123", "current_cart_value": 150.0}
    ],
).to_dict()

print(features)
# Output includes both platform features and team's ODFV:
# {
#   "customer_id": ["C123"],
#   "total_purchases": [42],
#   "avg_order_value": [125.50],
#   "purchase_propensity_score": [42.3]
# }
```

--------------------------------

### Dockerfile for Containerized Deployment with Static Artifacts

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/alpha-static-artifacts.md

This Dockerfile demonstrates how to include static artifacts in your container image for Feast. It copies the requirements, installs dependencies, copies the feature repository (including static artifacts), and sets the command to start the Feast server.

```dockerfile
FROM python:3.11-slim

# Install dependencies
COPY requirements.txt .
RUN pip install -r requirements.txt

# Copy feature repository including static_artifacts.py
COPY feature_repo/ /app/feature_repo/

WORKDIR /app/feature_repo

# Start feature server
CMD ["feast", "serve", "--host", "0.0.0.0"]
```

--------------------------------

### Scheduled Materialization with Airflow

Source: https://github.com/feast-dev/feast/blob/master/docs/how-to-guides/running-feast-in-production.md

Use the PythonOperator in Airflow to schedule Feast materialization jobs. Ensure the Feast Python SDK is installed and the feature repository is synced. This example demonstrates how to materialize feature views incrementally, with an option to let Airflow manage materialization state and include an overlap for late data.

```python
from airflow.decorators import task
from feast import RepoConfig, FeatureStore
from feast.infra.online_stores.dynamodb import DynamoDBOnlineStoreConfig
from feast.repo_config import RegistryConfig

# Define Python callable
@task()
def materialize(data_interval_start=None, data_interval_end=None):
  repo_config = RepoConfig(
    registry=RegistryConfig(path="s3://[YOUR BUCKET]/registry.pb"),
    project="feast_demo_aws",
    provider="aws",
    offline_store="file",
    online_store=DynamoDBOnlineStoreConfig(region="us-west-2"),
    entity_key_serialization_version=3
  )
  store = FeatureStore(config=repo_config)
  # Option 1: materialize just one feature view
  # store.materialize_incremental(datetime.datetime.now(), feature_views=["my_fv_name"])
  # Option 2: materialize all feature views incrementally
  # store.materialize_incremental(datetime.datetime.now())
  # Option 3: Let Airflow manage materialization state
  # Add 1 hr overlap to account for late data
  store.materialize(data_interval_start.subtract(hours=1), data_interval_end)
```

--------------------------------

### Initialize Feast Project with Ray Template

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/offline-stores/ray.md

Use the `feast init -t ray` command to quickly set up a new Feast project with pre-configured Ray offline store and compute engine.

```bash
feast init -t ray my_ray_project
cd my_ray_project/feature_repo
```

--------------------------------

### Install MongoDB Extra

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/online-stores/mongodb.md

Install the MongoDB extra for Feast. Ensure you also install the dependency for your chosen offline store.

```bash
pip install 'feast[mongodb]'
```

--------------------------------

### Bootstrap a New Feast Project

Source: https://github.com/feast-dev/feast/blob/master/docs/getting-started/quickstart.md

Use the `feast init` command to create a new feature repository. Navigate into the created directory to begin configuration.

```bash
feast init my_project
cd my_project/feature_repo
```

--------------------------------

### Install Milvus Extra

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/online-stores/milvus.md

Install the Milvus extra for Feast. Ensure you also install the dependency for your chosen offline store.

```bash
pip install 'feast[milvus]'
```

--------------------------------

### Install Feast

Source: https://github.com/feast-dev/feast/blob/master/examples/quickstart/quickstart.ipynb

Install the Feast library using pip. A runtime restart is recommended after installation to ensure correct dependency loading.

```python
%%sh
pip install feast -U -q
echo "Please restart your runtime now (Runtime -> Restart runtime). This ensures that the correct dependencies are loaded."
```

--------------------------------

### FeatureStore.serve()

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/modules.md

Starts a feature server to serve features online.

```APIDOC
## FeatureStore.serve()

### Description
Starts a feature server that serves features online. This allows real-time retrieval of feature values.

### Method
```python
FeatureStore.serve(port: int = 6006)
```

### Parameters
#### Path Parameters
None

#### Query Parameters
None

#### Request Body
*   **port** (int) - Optional - The port on which to run the feature server. Defaults to 6006.
```

--------------------------------

### serve_ui

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/source/feast.md

Starts the UI server locally, providing a web interface for interacting with the feature store.

```APIDOC
## serve_ui

### Description
Start the UI server locally.

### Method Signature
`serve_ui(host: str, port: int, get_registry_dump: Callable, registry_ttl_sec: int, root_path: str = '', tls_key_path: str = '', tls_cert_path: str = '') -> None`

### Parameters
* **host** (str) - Required - The host address to bind the server to.
* **port** (int) - Required - The port number to listen on.
* **get_registry_dump** (Callable) - Required - A callable function to get the registry dump.
* **registry_ttl_sec** (int) - Required - The time-to-live for registry entries in seconds.
* **root_path** (str) - Optional - The root path for the UI server. Defaults to ''.
* **tls_key_path** (str) - Optional - Path to the TLS key file.
* **tls_cert_path** (str) - Optional - Path to the TLS certificate file.
```

--------------------------------

### Install Feast with dbt support

Source: https://github.com/feast-dev/feast/blob/master/docs/how-to-guides/dbt-integration.md

Install Feast with the dbt integration package. Alternatively, install the dbt artifacts parser directly.

```bash
pip install 'feast[dbt]'
```

```bash
pip install dbt-artifacts-parser
```

--------------------------------

### Install Oracle Extras

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/offline-stores/oracle.md

Install the Oracle extras for Feast to enable Oracle offline store functionality. This command installs the necessary dependencies.

```bash
pip install 'feast[oracle]'
```

--------------------------------

### Start Registry Server

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/source/feast.md

Start the registry server locally using `serve_registry`. Configure the port and optionally enable the REST API.

```python
serve_registry(port=6604)
```

--------------------------------

### Install OpenTelemetry Operator

Source: https://github.com/feast-dev/feast/blob/master/docs/getting-started/components/open-telemetry.md

Apply the OpenTelemetry operator YAML file to install the operator. Ensure cert-manager is installed and pods are running beforehand.

```bash
kubectl apply -f https://github.com/open-telemetry/opentelemetry-operator/releases/latest/download/opentelemetry-operator.yaml
```

--------------------------------

### Install Feast MCP Support

Source: https://github.com/feast-dev/feast/blob/master/docs/getting-started/genai.md

Install Feast with MCP support using pip. This command installs the necessary packages to enable MCP functionality.

```bash
pip install feast[mcp]
```

--------------------------------

### Initialize a Feast Project

Source: https://github.com/feast-dev/feast/blob/master/skills/SKILL.md

Use this command to create a new Feast project directory with a basic configuration.

```bash
feast init my_project
cd my_project
feast apply
```

--------------------------------

### Install Prerequisites for MacOS

Source: https://github.com/feast-dev/feast/blob/master/examples/kind-quickstart/01-Install.ipynb

Installs and configures necessary tools like Colima, Kind, Helm, kubectl, and yq on a MacOS environment. Ensure you have Homebrew installed.

```bash
brew install colima
colima start
brew install kind
kind create cluster --name feast
kind start
brew install helm
brew install kubectl
kubectl config use-context kind-feast
brew install yq
```

--------------------------------

### Agent Demo Mode: SSO Setup and Memory Recall

Source: https://github.com/feast-dev/feast/blob/master/examples/agent_feature_store/README.md

Simulates agent reasoning for an enterprise customer asking about SSO, including memory recall and customer lookup. Demonstrates memory continuity when the customer returns.

```text
=================================================================
  Scene 1: Enterprise customer (C1001) asks about SSO
  Customer: C1001  |  Query: "How do I set up SSO for my team?"
=================================================================
  [Demo mode] Simulating agent reasoning

  Round 1 | recall_memory(customer_id=C1001)
          -> No prior interactions found

  Round 1 | lookup_customer(customer_id=C1001)
          -> Alice Johnson | enterprise plan | $24,500 spend | 1 open tickets

  Round 1 | search_knowledge_base(query="How do I set up SSO for my team?...")
          -> Best match: "Configuring single sign-on (SSO)"

  Round 2 | Generating personalised response...

  ─────────────────────────────────────────────────────────────
  Agent Response:
  ─────────────────────────────────────────────────────────────
  Hi Alice!
  Since you're on our Enterprise plan, SSO is available for your
  team. Go to Settings > Security > SSO and enter your Identity
  Provider metadata URL. We support SAML 2.0 and OIDC...

  [Checkpoint] Memory saved: topic="SSO setup"

=================================================================
  Scene 4: C1001 returns -- does the agent remember Scene 1?
  Customer: C1001  |  Query: "I'm back about my SSO question from earlier."
=================================================================
  [Demo mode] Simulating agent reasoning

  Round 1 | recall_memory(customer_id=C1001)
          -> Previous topic: SSO setup
          -> Open issue: none
          -> Interaction count: 1

  Round 1 | lookup_customer(customer_id=C1001)
          -> Alice Johnson | enterprise plan | $24,500 spend | 1 open tickets

  Round 2 | Generating personalised response...

  ─────────────────────────────────────────────────────────────
  Agent Response:
  ─────────────────────────────────────────────────────────────
  Welcome back, Alice! I can see from our records that we last
  discussed "SSO setup". How can I help you today?

  [Checkpoint] Memory saved: topic="SSO setup"

```

--------------------------------

### Install scikit-learn (if needed)

Source: https://github.com/feast-dev/feast/blob/master/docs/tutorials/azure/README.md

If you encounter issues during the model training stage, install or reinstall scikit-learn version 0.22.1. After installation, restart the kernel and resume the tutorial.

```python
!pip install scikit-learn==0.22.1
```

--------------------------------

### Example .feastignore File

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/feast-ignore.md

This example demonstrates various patterns that can be used in a .feastignore file to exclude specific files, directories, and file types from being processed by `feast apply`.

```text
# Ignore virtual environment
venv
```

```text
# Ignore a specific Python file
scripts/foo.py
```

```text
# Ignore all Python files directly under scripts directory
scripts/*.py
```

```text
# Ignore all "foo.py" anywhere under scripts directory
scripts/**/foo.py
```

--------------------------------

### Install Pre-commit Hooks

Source: https://github.com/feast-dev/feast/blob/master/docs/project/development-guide.md

Installs pre-commit and its associated hooks to automatically lint and format the codebase on commit. Ensure Python 3.10+ and uv are installed first.

```sh
make install-precommit
```

--------------------------------

### Start Ray Cluster for Feast

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/offline-stores/ray.md

Instructions for starting a Ray cluster for distributed data access with Feast. This includes starting the head node and configuring worker nodes.

```bash
ray start --head --port=10001
```

```bash
# On worker nodes
ray start --address='head-node-ip:10001'
```

--------------------------------

### Initialize Feast Project with Cassandra Provider

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/online-stores/scylladb.md

Create a new Feast project configured to use Cassandra as the online store provider. This sets up the basic project structure.

```bash
feast init REPO_NAME -t cassandra
```

--------------------------------

### Initialize Feast with GCP Template

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/feast/templates/milvus/README.md

Start a new Feast project using the Google Cloud Platform template for a scalable offline store.

```bash
feast init -t gcp
```

--------------------------------

### Install PostgreSQL using Helm

Source: https://github.com/feast-dev/feast/blob/master/examples/operator-postgres-tls-demo/01-Install-postgres-tls-using-helm.ipynb

Installs the PostgreSQL chart from Bitnami using Helm, applying the custom TLS and authentication configurations defined in 'values.yaml'. The installation is performed in the 'feast' namespace.

```bash
!helm install postgresql bitnami/postgresql --version 16.4.9 -f values.yaml -n feast
```

--------------------------------

### FeatureView Initialization Example

Source: https://github.com/feast-dev/feast/blob/master/sdk/python/docs/source/source/index.md

This example demonstrates how to initialize a FeatureView with various configurations, including name, source, entities, TTL, and online/offline settings. It's useful for defining a logical group of features for data retrieval and management.

```python
from datetime import timedelta
from feast import FeatureView, ValueType, Entity, Feature, FileSource


# Define entities
user = Entity(name="user_id", value_type=ValueType.INT64, description="unique user identifier")

# Define feature view
user_profile_fv = FeatureView(
    name="user_profile",
    entities=[user],
    ttl=timedelta(days=1),
    online=True,
    offline=False,
    schema=[
        Feature(name="name", value_type=ValueType.STRING),
        Feature(name="age", value_type=ValueType.INT64),
    ],
    source=FileSource(path="/path/to/user_profile.parquet")
)
```

--------------------------------

### Install pypdf Package

Source: https://github.com/feast-dev/feast/blob/master/examples/rag-docling/docling-demo.ipynb

Installs the pypdf library, which is required for PDF processing.

```python
! pip install pypdf
```

--------------------------------

### Install OpenLineage Dependency

Source: https://github.com/feast-dev/feast/blob/master/docs/reference/openlineage.md

Install the OpenLineage Python package or Feast with the OpenLineage extra.

```bash
pip install openlineage-python
```

```bash
pip install feast[openlineage]
```