hopsworks.core.search_api #

SearchApi #

Returned by

Project.get_search_api

feature_groups #

feature_groups(
    search_term: str | None = None,
    keyword_filter: str | list[str] | None = None,
    tag_filter: dict[str, str]
    | list[dict[str, str] | TagSearchFilter]
    | None = None,
    offset: int = 0,
    limit: int = 100,
    global_search: bool = False,
) -> list[FeatureGroupSearchResult]

Search for feature groups only.

PARAMETER	DESCRIPTION
`search_term`	The term to search for. TYPE: `str \| None` DEFAULT: `None`
`keyword_filter`	Filter results by keywords. Can be a single string or an array of strings. TYPE: `str \| list[str] \| None` DEFAULT: `None`
`tag_filter`	Filter results by tags. Can be a single dictionary, an array of dictionaries, or an array of TagSearchFilter objects. Each tag filter requires: `"name"` (the tag schema name as defined by Hopsworks Admin), `"key"` (the property within that tag schema), and `"value"` (the value to match). TYPE: `dict[str, str] \| list[dict[str, str] \| TagSearchFilter] \| None` DEFAULT: `None`
`offset`	The number of results to skip. TYPE: `int` DEFAULT: `0`
`limit`	The number of search results to return. TYPE: `int` DEFAULT: `100`
`global_search`	If `False`, search in current project only. If `True`, search over all projects. TYPE: `bool` DEFAULT: `False`

RETURNS	DESCRIPTION
`list[FeatureGroupSearchResult]`	A list of metadata objects for feature groups matching the search criteria.

RAISES	DESCRIPTION
`hopsworks.client.exceptions.RestAPIError`	If the backend encounters an error when handling the request

Example

import hopsworks

project = hopsworks.login()
search_api = project.get_search_api()

# Search for feature groups
fg_metas = search_api.feature_groups("customer")

for fg_meta in fg_metas:
    print(f"Feature Group: {fg_meta.name} v{fg_meta.version}")

    # Get the same FeatureGroup object as returned by featurestore.get_feature_group
    fg = fg_meta.get()

feature_store #

feature_store(
    search_term: str | None = None,
    keyword_filter: str | list[str] | None = None,
    tag_filter: dict[str, str]
    | list[dict[str, str] | TagSearchFilter]
    | None = None,
    offset: int = 0,
    limit: int = 100,
    global_search: bool = False,
) -> FeaturestoreSearchResult

Search for feature groups, feature views, training datasets, features, jobs, apps, models, deployments and agents.

PARAMETER	DESCRIPTION
`search_term`	The term to search for. TYPE: `str \| None` DEFAULT: `None`
`keyword_filter`	Filter results by keywords. Can be a single string or an array of strings. TYPE: `str \| list[str] \| None` DEFAULT: `None`
`tag_filter`	Filter results by tags. Can be a single dictionary, an array of dictionaries, or an array of TagSearchFilter objects. Each tag filter requires: `"name"` (the tag schema name as defined by Hopsworks Admin), `"key"` (the property within that tag schema), and `"value"` (the value to match). TYPE: `dict[str, str] \| list[dict[str, str] \| TagSearchFilter] \| None` DEFAULT: `None`
`offset`	The number of results to skip. TYPE: `int` DEFAULT: `0`
`limit`	The number of search results to return. TYPE: `int` DEFAULT: `100`
`global_search`	If `False`, search in current project only. If `True`, search over all projects. TYPE: `bool` DEFAULT: `False`

RETURNS	DESCRIPTION
`FeaturestoreSearchResult`	The search results with one list per entity type: feature groups, feature views, training datasets, features, jobs, apps, models, deployments and agents.

RAISES	DESCRIPTION
`hopsworks.client.exceptions.RestAPIError`	If the backend encounters an error when handling the request

Example

import hopsworks

project = hopsworks.login()
search_api = project.get_search_api()

# Simple search
result = search_api.feature_store("search-term")

# Access results
for fg_meta in result.feature_groups:
    print(f"Feature Group: {fg_meta.name} v{fg_meta.version}")
    print(f"Description: {fg_meta.description}")
    print(f"Highlights: {fg_meta.highlights}")

    # Get the same FeatureGroup object as returned by featurestore.get_feature_group
    fg = fg_meta.get()

# Search with a single keyword (string)
result = search_api.feature_store("search-term", keyword_filter="ml")

# Search with multiple keywords (array of strings)
result = search_api.feature_store("search-term", keyword_filter=["ml", "production"])

# Search with tag filter as a single dictionary
result = search_api.feature_store(
    "search-term",
    tag_filter={"name": "tag1", "key": "environment", "value": "production"}
)

# Search with tag filter as an array of dictionaries
result = search_api.feature_store(
    "search-term",
    tag_filter=[
        {"name": "tag1", "key": "environment", "value": "production"},
        {"name": "tag2", "key": "version", "value": "v1.0"}
    ]
)

# Search with TagSearchFilter objects
from hopsworks_common.core.search_api import TagSearchFilter
tags = [
    TagSearchFilter(name="tag1", key="environment", value="production"),
    TagSearchFilter(name="tag2", key="version", value="v1.0")
]
result = search_api.feature_store("search-term", tag_filter=tags)

# Search with both keyword_filter and tag_filter
result = search_api.feature_store(
    "search-term",
    keyword_filter=["ml", "production"],
    tag_filter=tags
)

feature_views #

feature_views(
    search_term: str | None = None,
    keyword_filter: str | list[str] | None = None,
    tag_filter: dict[str, str]
    | list[dict[str, str] | TagSearchFilter]
    | None = None,
    offset: int = 0,
    limit: int = 100,
    global_search: bool = False,
) -> list[FeatureViewSearchResult]

Search for feature views only.

PARAMETER	DESCRIPTION
`search_term`	The term to search for. TYPE: `str \| None` DEFAULT: `None`
`keyword_filter`	Filter results by keywords. Can be a single string or an array of strings. TYPE: `str \| list[str] \| None` DEFAULT: `None`
`tag_filter`	Filter results by tags. Can be a single dictionary, an array of dictionaries, or an array of TagSearchFilter objects. Each tag filter requires: `name` (the tag schema name as defined by Hopsworks Admin), `key` (the property within that tag schema), and `value` (the value to match). TYPE: `dict[str, str] \| list[dict[str, str] \| TagSearchFilter] \| None` DEFAULT: `None`
`offset`	The number of results to skip. TYPE: `int` DEFAULT: `0`
`limit`	The number of search results to return. TYPE: `int` DEFAULT: `100`
`global_search`	If `False`, search in current project only. If `True`, search over all projects. TYPE: `bool` DEFAULT: `False`

RETURNS	DESCRIPTION
`list[FeatureViewSearchResult]`	A list of metadata objects for feature views matching the search criteria.

RAISES	DESCRIPTION
`hopsworks.client.exceptions.RestAPIError`	If the backend encounters an error when handling the request

Example

import hopsworks

project = hopsworks.login()
search_api = project.get_search_api()

# Search for feature views
fv_metas = search_api.feature_views("customer")

for fv_meta in fv_metas:
    print(f"Feature View: {fv_meta.name} v{fv_meta.version}")

    # Get the same FeatureView object as returned by featurestore.get_feature_view
    fv = fv_meta.get()

features #

features(
    search_term: str | None = None,
    keyword_filter: str | list[str] | None = None,
    tag_filter: dict[str, str]
    | list[dict[str, str] | TagSearchFilter]
    | None = None,
    offset: int = 0,
    limit: int = 100,
    global_search: bool = False,
) -> list[FeatureSearchResult]

Search for features only.

PARAMETER	DESCRIPTION
`search_term`	The term to search for. TYPE: `str \| None` DEFAULT: `None`
`keyword_filter`	Filter results by keywords. Can be a single string or an array of strings. TYPE: `str \| list[str] \| None` DEFAULT: `None`
`tag_filter`	Filter results by tags. Can be a single dictionary, an array of dictionaries, or an array of TagSearchFilter objects. Each tag filter requires: `name` (the tag schema name as defined by Hopsworks Admin), `key` (the property within that tag schema), and `value` (the value to match). TYPE: `dict[str, str] \| list[dict[str, str] \| TagSearchFilter] \| None` DEFAULT: `None`
`offset`	The number of results to skip. TYPE: `int` DEFAULT: `0`
`limit`	The number of search results to return. TYPE: `int` DEFAULT: `100`
`global_search`	If `False`, search in current project only. If `True`, search over all projects. TYPE: `bool` DEFAULT: `False`

RETURNS	DESCRIPTION
`list[FeatureSearchResult]`	A list of features matching the search criteria.

RAISES	DESCRIPTION
`hopsworks.client.exceptions.RestAPIError`	If the backend encounters an error when handling the request

Example

import hopsworks

project = hopsworks.login()
search_api = project.get_search_api()

# Search for features
features = search_api.features("age")

for feature in features:
    print(f"Feature: {feature.name}")

training_datasets #

training_datasets(
    search_term: str | None = None,
    keyword_filter: str | list[str] | None = None,
    tag_filter: dict[str, str]
    | list[dict[str, str] | TagSearchFilter]
    | None = None,
    offset: int = 0,
    limit: int = 100,
    global_search: bool = False,
) -> list[TrainingDatasetSearchResult]

Search for training datasets only.

PARAMETER	DESCRIPTION
`search_term`	The term to search for. TYPE: `str \| None` DEFAULT: `None`
`keyword_filter`	Filter results by keywords. Can be a single string or an array of strings. TYPE: `str \| list[str] \| None` DEFAULT: `None`
`tag_filter`	Filter results by tags. Can be a single dictionary, an array of dictionaries, or an array of TagSearchFilter objects. Each tag filter requires: `name` (the tag schema name as defined by Hopsworks Admin), `key` (the property within that tag schema), and `value` (the value to match). TYPE: `dict[str, str] \| list[dict[str, str] \| TagSearchFilter] \| None` DEFAULT: `None`
`offset`	The number of results to skip. TYPE: `int` DEFAULT: `0`
`limit`	The number of search results to return. TYPE: `int` DEFAULT: `100`
`global_search`	If `False`, search in current project only. If `True`, search over all projects. TYPE: `bool` DEFAULT: `False`

RETURNS	DESCRIPTION
`list[TrainingDatasetSearchResult]`	A list of metadata objects for training datasets matching the search criteria.

RAISES	DESCRIPTION
`hopsworks.client.exceptions.RestAPIError`	If the backend encounters an error when handling the request

Example

import hopsworks

project = hopsworks.login()
search_api = project.get_search_api()

# Search for training datasets
td_metas = search_api.training_datasets("model")

for td_meta in td_metas:
    print(f"Training Dataset: {td_meta.name} v{td_meta.version}")

    # Get the same TrainingDataset object as returned by featurestore.get_training_dataset
    td = td_meta.get()

TagSearchFilter #

Filter for searching entities by tag.

Returned by

key `property` #

Key of the tag.

name `property` #

Name of the tag.

value `property` #

Value of the tag key.

FeatureGroupSearchResult #

Bases: SearchResultItem

Search result for a Feature Group.

Returned by

FeaturestoreSearchResult.feature_groups
SearchApi.feature_groups
FeatureStore.search_feature_groups

get #

get() -> FeatureGroup | None

Retrieve the full FeatureGroup object.

This uses the project associated with this search result to obtain a connection to the feature store and then fetches the Feature Group with the given name and version.

RETURNS	DESCRIPTION
`FeatureGroup \| None`	The full Feature Group object corresponding to this search result.

RAISES	DESCRIPTION
`Exception`	If the connection to the feature store fails or the Feature Group cannot be retrieved.

FeatureSearchResult #

Bases: SearchResultItem

Search result for a Feature.

Returned by

FeaturestoreSearchResult.features
SearchApi.features
FeatureStore.search_features

FeatureViewSearchResult #

Bases: SearchResultItem

Search result for a Feature View.

Returned by

FeaturestoreSearchResult.feature_views
SearchApi.feature_views
FeatureStore.search_feature_views

get #

get() -> FeatureView | None

Retrieve the full FeatureView object.

This uses the project associated with this search result to obtain a connection to the feature store and then fetches the Feature View with the given name and version.

RETURNS	DESCRIPTION
`FeatureView \| None`	The full FeatureView instance corresponding to this search result.

RAISES	DESCRIPTION
`Exception`	If the connection to the feature store fails or the Feature View cannot be retrieved.

FeaturestoreSearchResult #

Every bucket of a search: feature store entities, jobs, apps, models, deployments and agents.

Returned by

agents `property` #

agents: list[SearchResultItem]

List of Agent search results.

agents_offset `property` #

agents_offset: int

Total offset for the return list of agents within the whole result.

agents_total `property` #

agents_total: int

Total number of Agents matching the search.

apps `property` #

apps: list[SearchResultItem]

List of App search results.

apps_offset `property` #

apps_offset: int

Total offset for the return list of apps within the whole result.

apps_total `property` #

apps_total: int

Total number of Apps matching the search.

deployments `property` #

deployments: list[SearchResultItem]

List of Deployment search results.

deployments_offset `property` #

deployments_offset: int

Total offset for the return list of deployments within the whole result.

deployments_total `property` #

deployments_total: int

Total number of Deployments matching the search.

feature_groups `property` #

feature_groups: list[FeatureGroupSearchResult]

List of Feature Group search results.

feature_groups_offset `property` #

feature_groups_offset: int

Total offset for the return list of feature groups within the whole result.

feature_groups_total `property` #

feature_groups_total: int

Total number of Feature Groups matching the search.

feature_views `property` #

feature_views: list[FeatureViewSearchResult]

List of Feature View search results.

feature_views_offset `property` #

feature_views_offset: int

Total offset for the return list of feature views within the whole result.

feature_views_total `property` #

feature_views_total: int

Total number of Feature Views matching the search.

features `property` #

features: list[FeatureSearchResult]

List of Feature search results.

features_offset `property` #

features_offset: int

Total offset for the return list of features within the whole result.

features_total `property` #

features_total: int

Total number of Features matching the search.

jobs `property` #

jobs: list[SearchResultItem]

List of Job search results.

jobs_offset `property` #

jobs_offset: int

Total offset for the return list of jobs within the whole result.

jobs_total `property` #

jobs_total: int

Total number of Jobs matching the search.

models `property` #

models: list[SearchResultItem]

List of Model search results.

models_offset `property` #

models_offset: int

Total offset for the return list of models within the whole result.

models_total `property` #

models_total: int

Total number of Models matching the search.

training_datasets `property` #

training_datasets: list[TrainingDatasetSearchResult]

List of Training Dataset search results.

training_datasets_offset `property` #

training_datasets_offset: int

Total offset for the return list of training datasets within the whole result.

training_datasets_total `property` #

training_datasets_total: int

Total number of Training Datasets matching the search.

Highlights #

Container for search result highlights showing where matches occurred.

The results are highlighted by wrapping the matched terms in  tags. Check the OpenSearch Highlight Queries for more details.

Returned by

SearchResultItem.highlights

description `property` #

description: str | None

Highlighted description with the matched parts enwrapped in  tags.

features `property` #

features: list

Highlighted features with the matched parts enwrapped in  tags.

keywords `property` #

keywords: list

Highlighted keywords with the matched parts enwrapped in  tags.

name `property` #

name: str | None

Highlighted name with the matched parts enwrapped in  tags.

raw_data `property` #

raw_data: dict

Raw highlights data.

source_feature_groups `property` #

source_feature_groups: list

Highlighted source feature groups with the matched parts enwrapped in  tags.

tags `property` #

tags: list

List of highlighted tags with the matched parts enwrapped in  tags.

has_highlights #

has_highlights() -> bool

Check if there are any highlights.

RETURNS	DESCRIPTION
`bool`	Whether any of the highlight fields contain data.

Project #

Represents a project associated with a search result.

Returned by

SearchResultItem.project

id `property` #

id: int

Project ID.

name `property` #

name: str

Project name.

SearchResultItem #

Base class for search result items.

Returned by

FeaturestoreSearchResult.agents
FeaturestoreSearchResult.apps
FeaturestoreSearchResult.deployments
FeaturestoreSearchResult.jobs
FeaturestoreSearchResult.models

description `property` #

Description of the resource.

highlights `property` #

highlights: Highlights

Search highlights showing matched terms.

href `property` #

URL to get the full resource.

name `property` #

Name of the resource.

project `property` #

project: Project | None

Parent project of this resource.

raw_data `property` #

Raw data from the search result.

version `property` #

Version of the resource.

TrainingDatasetSearchResult #

Bases: SearchResultItem

Search result for a Training Dataset.

Returned by

FeaturestoreSearchResult.training_datasets
SearchApi.training_datasets
FeatureStore.search_training_datasets

get #

get() -> TrainingDataset | None

Retrieve the full TrainingDataset object.

This uses the project associated with this search result to obtain a connection to the feature store and then fetches the Training Dataset with the given name and version.

RETURNS	DESCRIPTION
`TrainingDataset \| None`	The full TrainingDataset instance corresponding to this search result.

RAISES	DESCRIPTION
`Exception`	If the connection to the feature store fails or the Training Dataset cannot be retrieved.

hopsworks.core.search_api #

SearchApi #

feature_groups #

feature_store #

feature_views #

features #

training_datasets #

TagSearchFilter #

key property #

name property #

value property #

FeatureGroupSearchResult #

get #

FeatureSearchResult #

FeatureViewSearchResult #

get #

FeaturestoreSearchResult #

agents property #

agents_offset property #

agents_total property #

apps property #

apps_offset property #

apps_total property #

deployments property #

deployments_offset property #

deployments_total property #

feature_groups property #

feature_groups_offset property #

feature_groups_total property #

feature_views property #

feature_views_offset property #

feature_views_total property #

features property #

features_offset property #

features_total property #

jobs property #

jobs_offset property #

jobs_total property #

models property #

models_offset property #

models_total property #

training_datasets property #

training_datasets_offset property #

training_datasets_total property #

Highlights #

description property #

features property #

keywords property #

name property #

raw_data property #

source_feature_groups property #

tags property #

has_highlights #

Project #

id property #

name property #

SearchResultItem #

description property #

highlights property #

href property #

name property #

project property #

raw_data property #

version property #

TrainingDatasetSearchResult #

get #

key `property` #

name `property` #

value `property` #

agents `property` #

agents_offset `property` #

agents_total `property` #

apps `property` #

apps_offset `property` #

apps_total `property` #

deployments `property` #

deployments_offset `property` #

deployments_total `property` #

feature_groups `property` #

feature_groups_offset `property` #

feature_groups_total `property` #

feature_views `property` #

feature_views_offset `property` #

feature_views_total `property` #

features `property` #

features_offset `property` #

features_total `property` #

jobs `property` #

jobs_offset `property` #

jobs_total `property` #

models `property` #

models_offset `property` #

models_total `property` #

training_datasets `property` #

training_datasets_offset `property` #

training_datasets_total `property` #

description `property` #

features `property` #

keywords `property` #

name `property` #

raw_data `property` #

source_feature_groups `property` #

tags `property` #

id `property` #

name `property` #

description `property` #

highlights `property` #

href `property` #

name `property` #

project `property` #

raw_data `property` #

version `property` #