Jupyter Notebook

Query & search registries

This guide walks through different ways of querying & searching LaminDB registries.

Let’s start by creating a few exemplary datasets and saving them into a LaminDB instance (hidden cell).

Hide code cell content
# pip install 'lamindb[bionty]'
!lamin init --storage ./test-registries --modules bionty

# python
import lamindb as ln
import bionty as bt
from lamindb.core import datasets

ln.track("pd7UR7Z8hoTq0000")

# Create non-curated datasets
ln.Artifact(datasets.file_jpg_paradisi05(), key="images/my_image.jpg").save()
ln.Artifact(datasets.file_fastq(), key="raw/my_fastq.fastq.gz").save()
ln.Artifact.from_df(datasets.df_iris(), key="iris/iris_collection.parquet").save()

# Create a more complex case
# observation-level metadata
ln.Feature(name="perturbation", dtype="cat[ULabel]").save()
ln.Feature(name="sample_note", dtype="str").save()
ln.Feature(name="cell_type_by_expert", dtype="cat[bionty.CellType]").save()
ln.Feature(name="cell_type_by_model", dtype="cat[bionty.CellType]").save()
# dataset-level metadata
ln.Feature(name="temperature", dtype="float").save()
ln.Feature(name="study", dtype="cat[ULabel]").save()
ln.Feature(name="date_of_study", dtype="date").save()
ln.Feature(name="study_note", dtype="str").save()

## Permissible values for categoricals
ln.ULabel.from_values(["DMSO", "IFNG"], create=True).save()
ln.ULabel.from_values(
    ["Candidate marker study 1", "Candidate marker study 2"], create=True
).save()
bt.CellType.from_values(["B cell", "T cell"], create=True).save()

# Ingest dataset1
adata = datasets.small_dataset1(otype="AnnData")
curator = ln.Curator.from_anndata(
    adata,
    var_index=bt.Gene.ensembl_gene_id,
    categoricals={
        "perturbation": ln.ULabel.name,
        "cell_type_by_expert": bt.CellType.name,
        "cell_type_by_model": bt.CellType.name,
    },
    organism="human",
)
artifact = curator.save_artifact(key="example_datasets/dataset1.h5ad")
artifact.features.add_values(adata.uns)

# Ingest dataset2
adata2 = datasets.small_dataset2(otype="AnnData")
curator = ln.Curator.from_anndata(
    adata2,
    var_index=bt.Gene.ensembl_gene_id,
    categoricals={
        "perturbation": ln.ULabel.name,
        "cell_type_by_model": bt.CellType.name,
    },
    organism="human",
)
artifact2 = curator.save_artifact(key="example_datasets/dataset2.h5ad")
artifact2.features.add_values(adata2.uns)
 initialized lamindb: testuser1/test-registries
 connected lamindb: testuser1/test-registries
 created Transform('pd7UR7Z8hoTq0000'), started new Run('AZiyexLg...') at 2025-03-10 11:53:20 UTC
 saving validated records of 'var_index'
 added 3 records from public with Gene.ensembl_gene_id for "var_index": 'ENSG00000153563', 'ENSG00000010610', 'ENSG00000170458'
 "var_index" is validated against Gene.ensembl_gene_id
 "perturbation" is validated against ULabel.name
 "cell_type_by_expert" is validated against CellType.name
 "cell_type_by_model" is validated against CellType.name
 saving validated records of 'var_index'
 added 1 record from public with Gene.ensembl_gene_id for "var_index": 'ENSG00000004468'
 "var_index" is validated against Gene.ensembl_gene_id
 "perturbation" is validated against ULabel.name
 "cell_type_by_model" is validated against CellType.name

Get an overview

The easiest way to get an overview over all artifacts is by typing df(), which returns the 100 latest artifacts in the Artifact registry.

import lamindb as ln

ln.Artifact.df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
5 ng55rLO99rXyzQGT0000 example_datasets/dataset2.h5ad None .h5ad dataset AnnData 22384 Th4l2amqbulAnwXuwp1yNg None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:29.261000+00:00 1 None 1
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1
3 pwwYvWhmnk23G1Qc0000 iris/iris_collection.parquet None .parquet dataset DataFrame 5088 8jtyI0r4o8fp7Gl7NayGjw None 150.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:22.646000+00:00 1 None 1
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None .fastq.gz None None 20 hi7ZmAzz8sfMd3vIQr-57Q None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.425000+00:00 1 None 1
1 U0FU6XhOkC20EtfV0000 images/my_image.jpg None .jpg None None 29358 r4tnqmKI_SjrkdLzpuWp4g None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.415000+00:00 1 None 1

You can include fields from other registries.

ln.Artifact.df(
    include=[
        "created_by__name",
        "ulabels__name",
        "cell_types__name",
        "feature_sets__itype",
        "suffix",
    ]
)
Hide code cell output
uid key description created_by__name ulabels__name cell_types__name feature_sets__itype suffix
id
5 ng55rLO99rXyzQGT0000 example_datasets/dataset2.h5ad None Test User1 {DMSO, IFNG, Candidate marker study 2} {B cell, T cell} {bionty.Gene, Feature} .h5ad
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None Test User1 {DMSO, IFNG, Candidate marker study 1} {B cell, T cell} {bionty.Gene, Feature} .h5ad
3 pwwYvWhmnk23G1Qc0000 iris/iris_collection.parquet None Test User1 {None} {None} {None} .parquet
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None Test User1 {None} {None} {None} .fastq.gz
1 U0FU6XhOkC20EtfV0000 images/my_image.jpg None Test User1 {None} {None} {None} .jpg

You can include information about which artifact measures which feature.

df = ln.Artifact.df(features=True)
ln.view(df)  # for clarity, leverage ln.view() to display dtype annotations
Hide code cell output
uidkeydescriptioncell_type_by_expertcell_type_by_modelstudyperturbationtemperaturestudy_notedate_of_study
idstrstrstrcat[bionty.CellType]cat[bionty.CellType]cat[ULabel]cat[ULabel]floatstrdate
5ng55rLO99rXyzQGT0000example_datasets/dataset2.h5adNonenan{'B cell', 'T cell'}{'Candidate marker study 2'}{'DMSO', 'IFNG'}{21.6}{'We had a great time performing this study and the results look compelling.'}{'2024-12-01'}
4On8iqyOJ2RWip5UB0000example_datasets/dataset1.h5adNone{'B cell', 'T cell'}{'B cell', 'T cell'}{'Candidate marker study 1'}{'DMSO', 'IFNG'}nannannan
3pwwYvWhmnk23G1Qc0000iris/iris_collection.parquetNonenannannannannannannan
2YoVPew7vYF41DDWb0000raw/my_fastq.fastq.gzNonenannannannannannannan
1U0FU6XhOkC20EtfV0000images/my_image.jpgNonenannannannannannannan

The flattened table that includes information from all relevant registries is easier to understand than the normalized data. For comparison, here is how to see the later.

ln.view()
Hide code cell output
****************
* module: core *
****************
Artifact
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
5 ng55rLO99rXyzQGT0000 example_datasets/dataset2.h5ad None .h5ad dataset AnnData 22384 Th4l2amqbulAnwXuwp1yNg None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:29.261000+00:00 1 None 1
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1
3 pwwYvWhmnk23G1Qc0000 iris/iris_collection.parquet None .parquet dataset DataFrame 5088 8jtyI0r4o8fp7Gl7NayGjw None 150.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:22.646000+00:00 1 None 1
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None .fastq.gz None None 20 hi7ZmAzz8sfMd3vIQr-57Q None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.425000+00:00 1 None 1
1 U0FU6XhOkC20EtfV0000 images/my_image.jpg None .jpg None None 29358 r4tnqmKI_SjrkdLzpuWp4g None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.415000+00:00 1 None 1
Feature
uid name dtype is_type unit description array_rank array_size array_shape proxy_dtype synonyms _expect_many _curation space_id type_id run_id created_at created_by_id _aux _branch_code
id
8 FaXW89uqY9Zs study_note str None None None 0 0 None None None True None 1 None 1 2025-03-10 11:53:22.963000+00:00 1 {'af': {'0': None, '1': True}} 1
7 PSbtBGRfD3mb date_of_study date None None None 0 0 None None None True None 1 None 1 2025-03-10 11:53:22.957000+00:00 1 {'af': {'0': None, '1': True}} 1
6 ZJZytwt9LNRr study cat[ULabel] None None None 0 0 None None None True None 1 None 1 2025-03-10 11:53:22.952000+00:00 1 {'af': {'0': None, '1': True}} 1
5 WbxEZk72otCq temperature float None None None 0 0 None None None True None 1 None 1 2025-03-10 11:53:22.945000+00:00 1 {'af': {'0': None, '1': True}} 1
4 H5cb12oKYflY cell_type_by_model cat[bionty.CellType] None None None 0 0 None None None True None 1 None 1 2025-03-10 11:53:22.940000+00:00 1 {'af': {'0': None, '1': True}} 1
3 FzaeqP09WEPb cell_type_by_expert cat[bionty.CellType] None None None 0 0 None None None True None 1 None 1 2025-03-10 11:53:22.933000+00:00 1 {'af': {'0': None, '1': True}} 1
2 00a9ntn61Mv2 sample_note str None None None 0 0 None None None True None 1 None 1 2025-03-10 11:53:22.927000+00:00 1 {'af': {'0': None, '1': True}} 1
FeatureValue
value hash space_id feature_id run_id created_at created_by_id _aux _branch_code
id
1 21.6 None 1 5 1 2025-03-10 11:53:26.861000+00:00 1 None 1
2 2024-12-01 None 1 7 1 2025-03-10 11:53:26.861000+00:00 1 None 1
3 We had a great time performing this study and ... None 1 8 1 2025-03-10 11:53:26.861000+00:00 1 None 1
4 22.6 None 1 5 1 2025-03-10 11:53:29.345000+00:00 1 None 1
5 2025-02-13 None 1 7 1 2025-03-10 11:53:29.345000+00:00 1 None 1
Run
uid name started_at finished_at reference reference_type _is_consecutive _status_code space_id transform_id report_id _logfile_id environment_id initiated_by_run_id created_at created_by_id _aux _branch_code
id
1 AZiyexLgaLlIneoJ3Yfh None 2025-03-10 11:53:20.649603+00:00 None None None None 0 1 1 None None None None 2025-03-10 11:53:20.650000+00:00 1 None 1
Schema
uid name description n dtype itype is_type otype hash minimal_set ordered_set maximal_set _curation slot space_id type_id validated_by_id composite_id run_id created_at created_by_id _aux _branch_code
id
1 vqBwvOAAJMjjR7LhW105 None None 3 int bionty.Gene False None f2UVeHefaZxXFjmUwo9Ozw True False False None None 1 None None None 1 2025-03-10 11:53:26.780000+00:00 1 None 1
2 a6hwqmVB33WX3DDUs4zA None None 4 None Feature False DataFrame hxeedp4oh317eU737orrPA True False False None None 1 None None None 1 2025-03-10 11:53:26.784000+00:00 1 None 1
3 grjsLaVOtYKVwK0epn7G None None 3 int bionty.Gene False None QW2rHuIo5-eGNZbRxHMDCw True False False None None 1 None None None 1 2025-03-10 11:53:29.285000+00:00 1 None 1
4 AtKU537sdaOXw4movplg None None 2 None Feature False DataFrame Dl2Xkrhsc8wFQIioVWi2MQ True False False None None 1 None None None 1 2025-03-10 11:53:29.288000+00:00 1 None 1
Storage
uid root description type region instance_uid space_id run_id created_at created_by_id _aux _branch_code
id
1 ydvY7yXVwN2Y /home/runner/work/lamindb/lamindb/docs/test-re... None local None hlGq1WkbeSSf 1 None 2025-03-10 11:53:13.587000+00:00 1 None 1
Transform
uid key description type source_code hash reference reference_type space_id _template_id version is_latest created_at created_by_id _aux _branch_code
id
1 pd7UR7Z8hoTq0000 registries.ipynb Query & search registries notebook None None None None 1 None None True 2025-03-10 11:53:20.645000+00:00 1 None 1
ULabel
uid name is_type description reference reference_type space_id type_id run_id created_at created_by_id _aux _branch_code
id
5 kms6Coek perturbation False None None None 1 None 1 2025-03-10 11:53:26.684000+00:00 1 None 1
3 jPS6tYAj Candidate marker study 1 False None None None 1 None 1 2025-03-10 11:53:22.983000+00:00 1 None 1
4 MmaHDytE Candidate marker study 2 False None None None 1 None 1 2025-03-10 11:53:22.983000+00:00 1 None 1
1 MBHqLcLR DMSO False None None None 1 None 1 2025-03-10 11:53:22.973000+00:00 1 None 1
2 EkIlAz0i IFNG False None None None 1 None 1 2025-03-10 11:53:22.973000+00:00 1 None 1
******************
* module: bionty *
******************
CellType
uid name ontology_id abbr synonyms description space_id source_id run_id created_at created_by_id _aux _branch_code
id
1 1m3SGd1l B cell None None None None 1 None 1 2025-03-10 11:53:23.385000+00:00 1 None 1
2 7gRvACvc T cell None None None None 1 None 1 2025-03-10 11:53:23.385000+00:00 1 None 1
Gene
uid symbol stable_id ensembl_gene_id ncbi_gene_ids biotype synonyms description space_id source_id organism_id run_id created_at created_by_id _aux _branch_code
id
4 iFxDa8hoEWuW CD38 None ENSG00000004468 952 protein_coding CADPR1 CD38 molecule 1 11 1 1 2025-03-10 11:53:29.196000+00:00 1 None 1
1 6Aqvc8ckDYeN CD8A None ENSG00000153563 925 protein_coding P32|CD8|CD8ALPHA CD8 subunit alpha 1 11 1 1 2025-03-10 11:53:26.661000+00:00 1 None 1
2 1j4At3x7akJU CD4 None ENSG00000010610 920 protein_coding T4|LEU-3 CD4 molecule 1 11 1 1 2025-03-10 11:53:26.661000+00:00 1 None 1
3 3bhNYquOnA4s CD14 None ENSG00000170458 929 protein_coding CD14 molecule 1 11 1 1 2025-03-10 11:53:26.661000+00:00 1 None 1
Organism
uid name ontology_id scientific_name synonyms description space_id source_id run_id created_at created_by_id _aux _branch_code
id
1 1dpCL6Td human NCBITaxon:9606 Homo sapiens None None 1 1 1 2025-03-10 11:53:23.999000+00:00 1 None 1
Source
uid entity organism name in_db currently_used description url md5 source_website space_id dataframe_artifact_id version run_id created_at created_by_id _aux _branch_code
id
53 5Xov8Lap bionty.Disease all mondo False False Mondo Disease Ontology http://purl.obolibrary.org/obo/mondo/releases/... None https://mondo.monarchinitiative.org 1 None 2024-02-06 None 2025-03-10 11:53:13.739000+00:00 1 None 1
54 69lnSXfR bionty.Disease all mondo False False Mondo Disease Ontology http://purl.obolibrary.org/obo/mondo/releases/... None https://mondo.monarchinitiative.org 1 None 2024-01-03 None 2025-03-10 11:53:13.739000+00:00 1 None 1
55 4ss2Hizg bionty.Disease all mondo False False Mondo Disease Ontology http://purl.obolibrary.org/obo/mondo/releases/... None https://mondo.monarchinitiative.org 1 None 2023-08-02 None 2025-03-10 11:53:13.739000+00:00 1 None 1
56 Hgw08Vk3 bionty.Disease all mondo False False Mondo Disease Ontology http://purl.obolibrary.org/obo/mondo/releases/... None https://mondo.monarchinitiative.org 1 None 2023-04-04 None 2025-03-10 11:53:13.739000+00:00 1 None 1
57 UUZUtULu bionty.Disease all mondo False False Mondo Disease Ontology http://purl.obolibrary.org/obo/mondo/releases/... None https://mondo.monarchinitiative.org 1 None 2023-02-06 None 2025-03-10 11:53:13.739000+00:00 1 None 1
58 7DH1aJIr bionty.Disease all mondo False False Mondo Disease Ontology http://purl.obolibrary.org/obo/mondo/releases/... None https://mondo.monarchinitiative.org 1 None 2022-10-11 None 2025-03-10 11:53:13.739000+00:00 1 None 1
59 4kswnHVF bionty.Disease human doid False True Human Disease Ontology http://purl.obolibrary.org/obo/doid/releases/2... None https://disease-ontology.org 1 None 2024-05-29 None 2025-03-10 11:53:13.739000+00:00 1 None 1

Auto-complete records

For registries with less than 100k records, auto-completing a Lookup object is the most convenient way of finding a record.

import bionty as bt

# query the database for all ulabels or all cell types
ulabels = ln.ULabel.lookup()
cell_types = bt.CellType.lookup()
Show me a screenshot

With auto-complete, we find a ulabel:

study1 = ulabels.candidate_marker_study_1
study1
Hide code cell output
ULabel(uid='jPS6tYAj', name='Candidate marker study 1', is_type=False, space_id=1, created_by_id=1, run_id=1, created_at=2025-03-10 11:53:22 UTC)

Get one record

get errors if more than one matching records are found.

print(study1.uid)

# by uid
ln.ULabel.get(study1.uid)

# by field
ln.ULabel.get(name="Candidate marker study 1")
Hide code cell output
jPS6tYAj
ULabel(uid='jPS6tYAj', name='Candidate marker study 1', is_type=False, space_id=1, created_by_id=1, run_id=1, created_at=2025-03-10 11:53:22 UTC)

Query multiple records

Filter for all artifacts annotated by a ulabel:

ln.Artifact.filter(ulabels=study1).df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1

To access the results encoded in a filter statement, execute its return value with one of:

  • df(): A pandas DataFrame with each record in a row.

  • all(): A QuerySet.

  • one(): Exactly one record. Will raise an error if there is none. Is equivalent to the .get() method shown above.

  • one_or_none(): Either one record or None if there is no query result.

Note

filter() returns a QuerySet.

The registries in LaminDB are Django Models and any Django query works.

LaminDB re-interprets Django’s API for data scientists.

What does this have to do with SQL?

Under the hood, any .filter() call translates into a SQL select statement.

LaminDB’s registries are object relational mappers (ORMs) that rely on Django for all the heavy lifting.

Of note, .one() and .one_or_none() are the two parts of LaminDB’s API that are borrowed from SQLAlchemy. In its first year, LaminDB built on SQLAlchemy.

Search for records

You can search every registry via search(). For example, the Artifact registry.

ln.Artifact.search("iris").df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
3 pwwYvWhmnk23G1Qc0000 iris/iris_collection.parquet None .parquet dataset DataFrame 5088 8jtyI0r4o8fp7Gl7NayGjw None 150 md5 True False 1 1 None None True 1 2025-03-10 11:53:22.646000+00:00 1 None 1

Here is more background on search and examples for searching the entire cell type ontology: How does search work?

Filter operators

You can qualify the type of comparison in a query by using a comparator.

Below follows a list of the most import, but Django supports about two dozen field comparators field__comparator=value.

and

ln.Artifact.filter(suffix=".h5ad", ulabels=study1).df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1

less than/ greater than

Or subset to artifacts greater than 10kB. Here, we can’t use keyword arguments, but need an explicit where statement.

ln.Artifact.filter(ulabels=study1, size__gt=1e4).df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1

in

ln.Artifact.filter(suffix__in=[".jpg", ".fastq.gz"]).df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
1 U0FU6XhOkC20EtfV0000 images/my_image.jpg None .jpg None None 29358 r4tnqmKI_SjrkdLzpuWp4g None None md5 True False 1 1 None None True 1 2025-03-10 11:53:22.415000+00:00 1 None 1
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None .fastq.gz None None 20 hi7ZmAzz8sfMd3vIQr-57Q None None md5 True False 1 1 None None True 1 2025-03-10 11:53:22.425000+00:00 1 None 1

order by

ln.Artifact.filter().order_by("created_at").df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
1 U0FU6XhOkC20EtfV0000 images/my_image.jpg None .jpg None None 29358 r4tnqmKI_SjrkdLzpuWp4g None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.415000+00:00 1 None 1
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None .fastq.gz None None 20 hi7ZmAzz8sfMd3vIQr-57Q None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.425000+00:00 1 None 1
3 pwwYvWhmnk23G1Qc0000 iris/iris_collection.parquet None .parquet dataset DataFrame 5088 8jtyI0r4o8fp7Gl7NayGjw None 150.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:22.646000+00:00 1 None 1
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1
5 ng55rLO99rXyzQGT0000 example_datasets/dataset2.h5ad None .h5ad dataset AnnData 22384 Th4l2amqbulAnwXuwp1yNg None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:29.261000+00:00 1 None 1
# reverse ordering
ln.Artifact.filter().order_by("-created_at").df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
5 ng55rLO99rXyzQGT0000 example_datasets/dataset2.h5ad None .h5ad dataset AnnData 22384 Th4l2amqbulAnwXuwp1yNg None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:29.261000+00:00 1 None 1
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1
3 pwwYvWhmnk23G1Qc0000 iris/iris_collection.parquet None .parquet dataset DataFrame 5088 8jtyI0r4o8fp7Gl7NayGjw None 150.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:22.646000+00:00 1 None 1
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None .fastq.gz None None 20 hi7ZmAzz8sfMd3vIQr-57Q None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.425000+00:00 1 None 1
1 U0FU6XhOkC20EtfV0000 images/my_image.jpg None .jpg None None 29358 r4tnqmKI_SjrkdLzpuWp4g None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.415000+00:00 1 None 1
ln.Artifact.filter().order_by("key").df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1
5 ng55rLO99rXyzQGT0000 example_datasets/dataset2.h5ad None .h5ad dataset AnnData 22384 Th4l2amqbulAnwXuwp1yNg None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:29.261000+00:00 1 None 1
1 U0FU6XhOkC20EtfV0000 images/my_image.jpg None .jpg None None 29358 r4tnqmKI_SjrkdLzpuWp4g None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.415000+00:00 1 None 1
3 pwwYvWhmnk23G1Qc0000 iris/iris_collection.parquet None .parquet dataset DataFrame 5088 8jtyI0r4o8fp7Gl7NayGjw None 150.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:22.646000+00:00 1 None 1
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None .fastq.gz None None 20 hi7ZmAzz8sfMd3vIQr-57Q None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.425000+00:00 1 None 1
# reverse ordering
ln.Artifact.filter().order_by("-key").df()
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None .fastq.gz None None 20 hi7ZmAzz8sfMd3vIQr-57Q None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.425000+00:00 1 None 1
3 pwwYvWhmnk23G1Qc0000 iris/iris_collection.parquet None .parquet dataset DataFrame 5088 8jtyI0r4o8fp7Gl7NayGjw None 150.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:22.646000+00:00 1 None 1
1 U0FU6XhOkC20EtfV0000 images/my_image.jpg None .jpg None None 29358 r4tnqmKI_SjrkdLzpuWp4g None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.415000+00:00 1 None 1
5 ng55rLO99rXyzQGT0000 example_datasets/dataset2.h5ad None .h5ad dataset AnnData 22384 Th4l2amqbulAnwXuwp1yNg None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:29.261000+00:00 1 None 1
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1

contains

ln.Transform.filter(name__contains="search").df().head(5)
Hide code cell output
uid id key description type source_code hash reference reference_type space_id _template_id version is_latest created_at created_by_id _aux _branch_code

And case-insensitive:

ln.Transform.filter(name__icontains="Search").df().head(5)
Hide code cell output
uid id key description type source_code hash reference reference_type space_id _template_id version is_latest created_at created_by_id _aux _branch_code

startswith

ln.Transform.filter(name__startswith="Research").df()
Hide code cell output
uid id key description type source_code hash reference reference_type space_id _template_id version is_latest created_at created_by_id _aux _branch_code

or

ln.Artifact.filter(ln.Q(suffix=".jpg") | ln.Q(suffix=".fastq.gz")).df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
1 U0FU6XhOkC20EtfV0000 images/my_image.jpg None .jpg None None 29358 r4tnqmKI_SjrkdLzpuWp4g None None md5 True False 1 1 None None True 1 2025-03-10 11:53:22.415000+00:00 1 None 1
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None .fastq.gz None None 20 hi7ZmAzz8sfMd3vIQr-57Q None None md5 True False 1 1 None None True 1 2025-03-10 11:53:22.425000+00:00 1 None 1

negate/ unequal

ln.Artifact.filter(~ln.Q(suffix=".jpg")).df()
Hide code cell output
uid key description suffix kind otype size hash n_files n_observations _hash_type _key_is_virtual _overwrite_versions space_id storage_id schema_id version is_latest run_id created_at created_by_id _aux _branch_code
id
2 YoVPew7vYF41DDWb0000 raw/my_fastq.fastq.gz None .fastq.gz None None 20 hi7ZmAzz8sfMd3vIQr-57Q None NaN md5 True False 1 1 None None True 1 2025-03-10 11:53:22.425000+00:00 1 None 1
3 pwwYvWhmnk23G1Qc0000 iris/iris_collection.parquet None .parquet dataset DataFrame 5088 8jtyI0r4o8fp7Gl7NayGjw None 150.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:22.646000+00:00 1 None 1
4 On8iqyOJ2RWip5UB0000 example_datasets/dataset1.h5ad None .h5ad dataset AnnData 25088 Z6Ya2rWrz-YlBwFixuFI3w None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:26.754000+00:00 1 None 1
5 ng55rLO99rXyzQGT0000 example_datasets/dataset2.h5ad None .h5ad dataset AnnData 22384 Th4l2amqbulAnwXuwp1yNg None 3.0 md5 True False 1 1 None None True 1 2025-03-10 11:53:29.261000+00:00 1 None 1