lamindb 1.11.1__py3-none-any.whl → 1.11.2__py3-none-any.whl

lamindb/__init__.py

@@ -114,7 +114,7 @@ Backwards compatibility.
 
 # ruff: noqa: I001
 # denote a release candidate for 0.1.0 with 0.1rc1, 0.1a1, 0.1b1, etc.
-__version__ = "1.11.1"
+__version__ = "1.11.2"
 
 import warnings as _warnings
 

lamindb/models/query_set.py

@@ -155,19 +155,29 @@ def process_expressions(queryset: QuerySet, expressions: dict) -> dict:
         expressions,
     )
     if issubclass(queryset.model, SQLRecord):
-        # branch_id is set to 1 unless expressions contains id or uid
-        if not (
-            "id" in expressions
-            or "uid" in expressions
-            or "uid__startswith" in expressions
-        ):
-            if not any(e.startswith("branch_id") for e in expressions):
-                expressions["branch_id"] = 1  # default branch_id
-            # if branch_id is None, do not apply a filter
-            # otherwise, it would mean filtering for NULL values, which doesn't make
-            # sense for a non-NULLABLE column
-            elif "branch_id" in expressions and expressions["branch_id"] is None:
-                expressions.pop("branch_id")
+        # branch_id is set to 1 unless expressions contains id, uid or hash
+        id_uid_hash = {"id", "uid", "hash", "id__in", "uid__in", "hash__in"}
+        if not any(expression in id_uid_hash for expression in expressions):
+            expressions_have_branch = False
+            branch_branch_id = {"branch", "branch_id"}
+            branch_branch_id__ = ("branch__", "branch_id__")
+            for expression in expressions:
+                if expression in branch_branch_id or expression.startswith(
+                    branch_branch_id__
+                ):
+                    expressions_have_branch = True
+                    break
+            if not expressions_have_branch:
+                # TODO: should be set to the current default branch
+                expressions["branch_id"] = 1
+            else:
+                # if branch_id is None, do not apply a filter
+                # otherwise, it would mean filtering for NULL values, which doesn't make
+                # sense for a non-NULLABLE column
+                if "branch_id" in expressions and expressions["branch_id"] is None:
+                    expressions.pop("branch_id")
+                if "branch" in expressions and expressions["branch"] is None:
+                    expressions.pop("branch")
     if queryset._db is not None:
         # only check for database mismatch if there is a defined database on the
         # queryset
@@ -226,8 +236,6 @@ def get(
     else:
         assert idlike is None  # noqa: S101
         expressions = process_expressions(qs, expressions)
-        # don't want branch_id here in .get(), only in .filter()
-        expressions.pop("branch_id", None)
         # inject is_latest for consistency with idlike
         is_latest_was_not_in_expressions = "is_latest" not in expressions
         if issubclass(registry, IsVersioned) and is_latest_was_not_in_expressions:
@@ -241,7 +249,7 @@ def get(
                 result = qs.filter(**expressions).order_by("-created_at").first()
                 if result is not None:
                     return result
-            raise registry.DoesNotExist from e
+            raise e
 
 
 class SQLRecordList(UserList, Generic[T]):

lamindb/models/save.py

@@ -234,7 +234,15 @@ def check_and_attempt_upload(
             try:
                 copy_or_move_to_cache(artifact, storage_path, cache_path)
             except Exception as e:
-                logger.warning(f"A problem with cache on saving: {e}")
+                if not str(e).startswith(
+                    "[WinError 32] The process cannot access the file "
+                    "because it is being used by another process"
+                ):
+                    # ignore WinError 32 error, this just means that the file is still open on save
+                    # it is saved at this point, so not a big deal if copy or move to cache fails
+                    # this mostly happens for run logs
+                    # just ignore without a warning
+                    logger.warning(f"A problem with cache on saving: {e}")
         # after successful upload, we should remove the attribute so that another call
         # call to save won't upload again, the user should call replace() then
         del artifact._local_filepath
@@ -269,7 +277,9 @@ def copy_or_move_to_cache(
     # non-local storage_path further
     if local_path != cache_path:
         if cache_path.exists():
-            logger.warning(f"replacing the existing cache path {cache_path.as_posix()}")
+            logger.important_hint(
+                f"replacing the existing cache path {cache_path.as_posix()}"
+            )
             if cache_path.is_dir():
                 shutil.rmtree(cache_path)
             else:

lamindb/models/sqlrecord.py

@@ -350,7 +350,7 @@ def delete_record(record: BaseSQLRecord, is_soft: bool = True):
             with transaction.atomic():
                 new_latest.save()
                 delete()
-            logger.warning(f"new latest version is: {new_latest}")
+            logger.important_hint(f"new latest version is: {new_latest}")
             return None
     # deal with all other cases of the nested if condition now
     delete()

lamindb-1.11.2.dist-info/METADATA

@@ -0,0 +1,180 @@
+Metadata-Version: 2.3
+Name: lamindb
+Version: 1.11.2
+Summary: A data framework for biology.
+Author-email: Lamin Labs <open-source@lamin.ai>
+Requires-Python: >=3.10,<3.14
+Description-Content-Type: text/markdown
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: lamin_utils==0.15.0
+Requires-Dist: lamin_cli==1.7.1
+Requires-Dist: lamindb_setup[aws]==1.10.1
+Requires-Dist: bionty>=1.7a1
+Requires-Dist: wetlab>=1.5a1
+Requires-Dist: nbproject==0.11.1
+Requires-Dist: jupytext
+Requires-Dist: nbconvert>=7.2.1
+Requires-Dist: mistune!=3.1.0
+Requires-Dist: pyyaml
+Requires-Dist: pyarrow
+Requires-Dist: pandera>=0.24.0
+Requires-Dist: typing_extensions!=4.6.0
+Requires-Dist: python-dateutil
+Requires-Dist: pandas>=2.0.0
+Requires-Dist: scipy<1.15.0
+Requires-Dist: anndata>=0.8.0,<=0.12.1
+Requires-Dist: fsspec
+Requires-Dist: graphviz
+Requires-Dist: psycopg2-binary
+Requires-Dist: tomlkit ; extra == "dev"
+Requires-Dist: line_profiler ; extra == "dev"
+Requires-Dist: pre-commit ; extra == "dev"
+Requires-Dist: nox ; extra == "dev"
+Requires-Dist: laminci>=0.3 ; extra == "dev"
+Requires-Dist: pytest>=6.0 ; extra == "dev"
+Requires-Dist: coverage ; extra == "dev"
+Requires-Dist: pytest-cov<7.0.0 ; extra == "dev"
+Requires-Dist: mudata ; extra == "dev"
+Requires-Dist: nbproject_test>=0.6.0 ; extra == "dev"
+Requires-Dist: faker-biology ; extra == "dev"
+Requires-Dist: pronto ; extra == "dev"
+Requires-Dist: readfcs>=2.0.1 ; extra == "fcs"
+Requires-Dist: lamindb_setup[gcp] ; extra == "gcp"
+Requires-Dist: numcodecs<0.16.0 ; extra == "zarr"
+Requires-Dist: zarr>=2.16.0,<3.0.0a0 ; extra == "zarr"
+Project-URL: Home, https://github.com/laminlabs/lamindb
+Provides-Extra: dev
+Provides-Extra: fcs
+Provides-Extra: gcp
+Provides-Extra: zarr
+
+[![Stars](https://img.shields.io/github/stars/laminlabs/lamindb?logo=GitHub)](https://github.com/laminlabs/lamindb)
+[![codecov](https://codecov.io/gh/laminlabs/lamindb/branch/main/graph/badge.svg?token=VKMRJ7OWR3)](https://codecov.io/gh/laminlabs/lamindb)
+[![Docs](https://img.shields.io/badge/docs-humans-yellow)](https://docs.lamin.ai)
+[![DocsLLMs](https://img.shields.io/badge/docs-LLMs-yellow)](https://docs.lamin.ai/summary.md)
+[![pypi](https://img.shields.io/pypi/v/lamindb?color=blue&label=pypi%20package)](https://pypi.org/project/lamindb)
+[![PyPI Downloads](https://img.shields.io/pepy/dt/lamindb?logo=pypi)](https://pepy.tech/project/lamindb)
+
+# LaminDB - A data lakehouse for biology
+
+LaminDB is an open-source data lakehouse to enable learning at scale in biology.
+It organizes datasets through validation & annotation and provides data lineage, queryability, and reproducibility on top of [FAIR](https://en.wikipedia.org/wiki/FAIR_data) data.
+
+<details>
+<summary>Why?</summary>
+
+Reproducing analytical results or understanding how a dataset or model was created can be a pain.
+Let alone training models on historical data, LIMS & ELN systems, orthogonal assays, or datasets generated by other teams.
+Even maintaining a mere overview of a project's or team's datasets & analyses is harder than it sounds.
+
+Biological datasets are typically managed with versioned storage systems, GUI-focused community or SaaS platforms, structureless data lakes, rigid data warehouses (SQL, monolithic arrays), and data lakehouses for tabular data.
+
+LaminDB extends the lakehouse architecture to biological registries & datasets beyond tables (`DataFrame`, `AnnData`, `.zarr`, `.tiledbsoma`, ...) with enough structure to enable queries and enough freedom to keep the pace of R&D high.
+Moreover, it provides context through data lineage -- tracing data and code, scientists and models -- and abstractions for biological domain knowledge and experimental metadata.
+
+</details>
+
+**Highlights.**
+
+- **data lineage:** track inputs & outputs of notebooks, scripts, functions & pipelines with a single line of code
+- **unified infrastructure:** access diverse storage locations (local, S3, GCP, ...), SQL databases (Postgres, SQLite) & ontologies
+- **lakehouse capabilities**: manage, monitor & validate features, labels & dataset schemas; perform distributed queries and batch loading
+- **biological data formats:** validate & annotate formats like `DataFrame`, `AnnData`, `MuData`, ... backed by `parquet`, `zarr`, HDF5, LanceDB, DuckDB, ...
+- **biological entities**: organize experimental metadata & extensible ontologies in registries based on the Django ORM
+- **reproducible & auditable:** auto-version & timestamp execution reports, source code & compute environments, attribute records to users
+- **zero lock-in & scalable:** runs in your infrastructure; is _not_ a client for a rate-limited REST API
+- **extendable:** create custom plug-ins for your own applications based on the Django ecosystem
+- **integrations:** visualization tools like [vitessce](https://docs.lamin.ai/vitessce), workflow managers like [nextflow](https://docs.lamin.ai/nextflow) & [redun](https://docs.lamin.ai/redun), and [other tools](https://docs.lamin.ai/integrations)
+- **production-ready:** used in BigPharma, BioTech, hospitals & top labs
+
+LaminDB can be connected to LaminHub to serve as a [LIMS](https://en.wikipedia.org/wiki/Laboratory_information_management_system) for wetlab scientists, closing the drylab-wetlab feedback loop: [lamin.ai](https://lamin.ai)
+
+## Docs
+
+Copy [summary.md](https://docs.lamin.ai/summary.md) into an LLM chat and let AI explain or read the [docs](https://docs.lamin.ai).
+
+## Setup
+
+<!-- copied from quick-setup-lamindb.md -->
+
+Install the `lamindb` Python package:
+
+```shell
+pip install lamindb
+```
+
+Create a LaminDB instance:
+
+```shell
+lamin init --storage ./quickstart-data  # or s3://my-bucket, gs://my-bucket
+```
+
+Or if you have write access to an instance, connect to it:
+
+```shell
+lamin connect account/name
+```
+
+## Quickstart
+
+<!-- copied from preface.md -->
+
+Track a script or notebook run with source code, inputs, outputs, logs, and environment.
+
+<!-- copied from py-quickstart.py -->
+
+```python
+import lamindb as ln
+
+ln.track()  # track a run
+open("sample.fasta", "w").write(">seq1\nACGT\n")
+ln.Artifact("sample.fasta", key="sample.fasta").save()  # create an artifact
+ln.finish()  # finish the run
+```
+
+<!-- from here on, slight deviation from preface.md, where all this is treated in the walk through in more depth -->
+
+This code snippet creates an artifact, which can store a dataset or model as a file or folder in various formats.
+Running the snippet as a script (`python create-fasta.py`) produces the following data lineage.
+
+```python
+artifact = ln.Artifact.get(key="sample.fasta")  # query artifact by key
+artifact.view_lineage()
+```
+
+<img src="https://lamin-site-assets.s3.amazonaws.com/.lamindb/EkQATsQL5wqC95Wj0005.png" width="250">
+
+You'll know how that artifact was created and what it's used for ([interactive visualization](https://lamin.ai/laminlabs/lamindata/artifact/8incOOgjn6F0K1TS)) in addition to capturing basic metadata:
+
+```python
+artifact.describe()
+```
+
+<img src="https://lamin-site-assets.s3.amazonaws.com/.lamindb/BOTCBgHDAvwglN3U0002.png" width="550">
+
+You can organize datasets with validation & annotation of any kind of metadata to then access them via queries & search. Here is a more [comprehensive example](https://lamin.ai/laminlabs/lamindata/artifact/9K1dteZ6Qx0EXK8g).
+
+<img src="https://lamin-site-assets.s3.amazonaws.com/.lamindb/6sofuDVvTANB0f480002.png" width="850">
+
+To annotate an artifact with a label, use:
+
+```python
+my_experiment = ln.ULabel(name="My experiment").save()  # create a label in the universal label ontology
+artifact.ulabels.add(my_experiment)  # annotate the artifact with the label
+```
+
+To query for a set of artifacts, use the `filter()` statement.
+
+```python
+ln.Artifact.filter(ulabels=my_experiment, suffix=".fasta").to_dataframe()  # query by suffix and the ulabel we just created
+ln.Artifact.filter(transform__key="create-fasta.py").to_dataframe()  # query by the name of the script we just ran
+```
+
+If you have a structured dataset like a `DataFrame`, an `AnnData`, or another array, you can validate the content of the dataset (and parse annotations).
+Here is an example for a dataframe: [docs.lamin.ai/introduction#validate-an-artifact](https://docs.lamin.ai/introduction#validate-an-artifact).
+
+With a large body of validated datasets, you can then access data through distributed queries & batch streaming, see here: [docs.lamin.ai/arrays](https://docs.lamin.ai/arrays).
+

{lamindb-1.11.1.dist-info → lamindb-1.11.2.dist-info}/RECORD

@@ -1,4 +1,4 @@
-lamindb/__init__.py,sha256=jO-XCxfKHm4hUoqFpHDOPFPoKbknvdkm0oImBWGod8A,3241
+lamindb/__init__.py,sha256=HGxNpCYe-NeHQHiQXY8bEEfDXbH0zN_ucGrXIEO7cBw,3241
 lamindb/_finish.py,sha256=4KkFyb9d-GEGjDw_zDrnGt_bq3auQ_OQu0hV-2U73AQ,21355
 lamindb/_tracked.py,sha256=fls9yd7EEGO9Ni51kA_pcBkeLpzm2HZrWtwYGQequNE,4395
 lamindb/_view.py,sha256=GOKTfwnEaly9fdeWo9SlhYRc3UWEyLDmTlIUzjFXMYY,4960
@@ -128,12 +128,12 @@ lamindb/models/feature.py,sha256=6kI3UZMp3gBi75NhXBp_jn-1tRlc42YdJOEJFNgjtNo,418
 lamindb/models/has_parents.py,sha256=Ok-Tsh4-oBDjkyevyMSuOCb0mzDiswiO_0ufTqWz8o4,20341
 lamindb/models/project.py,sha256=AhaY24iE8ilpS5dRFYzY6xQNVlqPHWMk72ib2OI_N8U,18732
 lamindb/models/query_manager.py,sha256=zjO31kbj1t08WTxeZB9-BPjooz6axh06EFu90dfvpSA,11358
-lamindb/models/query_set.py,sha256=y18mzqWUNbjOmcS1oW25ZxYtvEMtXYGB8c10OGxNZ4c,39117
+lamindb/models/query_set.py,sha256=zwMlYRfjvAQ4NjIKpk19ipiP43UhGiUoU2wxntnBDUY,39591
 lamindb/models/record.py,sha256=2eKEDqpiX5-aN2kUVXLuTVvQUspqQ5h10onbQM6Ta7g,13041
 lamindb/models/run.py,sha256=LVZ2z5QV4aVYYsqGcLmMfqvPpKj4EGGHVts_RR8_c-E,14443
-lamindb/models/save.py,sha256=gBt74RqfwgTa8PnTE153p17PruTAt6WGmGk9ZEBrojI,16719
+lamindb/models/save.py,sha256=CEifxocJuoLIuapqtiGk-eKvXfQSK4v389CWBo4FxOA,17264
 lamindb/models/schema.py,sha256=LQuPQhyLitloRGxq6DWZMHcR-xDZY1NctPHjrC6t1iw,49827
-lamindb/models/sqlrecord.py,sha256=L_-60qCyWuG00IZvGiXA_bcVbYd2GKv-ax2TDQcn8IA,72679
+lamindb/models/sqlrecord.py,sha256=kL2YS0lAENLXVMC5bzQuOZrRpujdLsBCJCf0sX_4PlE,72686
 lamindb/models/storage.py,sha256=n7jth0RQ19K0W8ICbrAO942d5jBm1-h7DsrSjMJgAB0,15551
 lamindb/models/transform.py,sha256=FcIPqmSk1hahg2Cr8q6lm1kKpbdvu2JUceSlPIV9Dww,12780
 lamindb/models/ulabel.py,sha256=UznidEEoiIns_KetWgCbDejXuM5hmzF6F49yqf2kLpQ,9495
@@ -142,7 +142,7 @@ lamindb/setup/_switch.py,sha256=njZJN__JOhVrBFGClQG1wobdhJJp6l_XzPGKtKSCrfU,434
 lamindb/setup/core/__init__.py,sha256=SevlVrc2AZWL3uALbE5sopxBnIZPWZ1IB0NBDudiAL8,167
 lamindb/setup/errors/__init__.py,sha256=bAHTxOUJW1rm4zpF0Pvqkftn8W6iMGnQ-uyNBu13Nfg,171
 lamindb/setup/types/__init__.py,sha256=ATaosOi6q-cDWB52T69_sRmLMqj8cHfc-vljzZsrJNw,169
-lamindb-1.11.1.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-lamindb-1.11.1.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
-lamindb-1.11.1.dist-info/METADATA,sha256=rrGmUwB5UIBBj-3k8HznNPlWCsAf2mHkQEK5aMSinUY,4865
-lamindb-1.11.1.dist-info/RECORD,,
+lamindb-1.11.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+lamindb-1.11.2.dist-info/WHEEL,sha256=CpUCUxeHQbRN5UGRQHYRJorO5Af-Qy_fHMctcQ8DSGI,82
+lamindb-1.11.2.dist-info/METADATA,sha256=69LKvBDk40m1gfwl-DIpwIxQqCxNt5zPWf0zuIz9pHc,8552
+lamindb-1.11.2.dist-info/RECORD,,

lamindb-1.11.1.dist-info/METADATA

@@ -1,139 +0,0 @@
-Metadata-Version: 2.3
-Name: lamindb
-Version: 1.11.1
-Summary: A data framework for biology.
-Author-email: Lamin Labs <open-source@lamin.ai>
-Requires-Python: >=3.10,<3.14
-Description-Content-Type: text/markdown
-Classifier: Programming Language :: Python :: 3.10
-Classifier: Programming Language :: Python :: 3.11
-Classifier: Programming Language :: Python :: 3.12
-Classifier: Programming Language :: Python :: 3.13
-Requires-Dist: lamin_utils==0.15.0
-Requires-Dist: lamin_cli==1.7.1
-Requires-Dist: lamindb_setup[aws]==1.10.1
-Requires-Dist: bionty>=1.7a1
-Requires-Dist: wetlab>=1.5a1
-Requires-Dist: nbproject==0.11.1
-Requires-Dist: jupytext
-Requires-Dist: nbconvert>=7.2.1
-Requires-Dist: mistune!=3.1.0
-Requires-Dist: pyyaml
-Requires-Dist: pyarrow
-Requires-Dist: pandera>=0.24.0
-Requires-Dist: typing_extensions!=4.6.0
-Requires-Dist: python-dateutil
-Requires-Dist: pandas>=2.0.0
-Requires-Dist: scipy<1.15.0
-Requires-Dist: anndata>=0.8.0,<=0.12.1
-Requires-Dist: fsspec
-Requires-Dist: graphviz
-Requires-Dist: psycopg2-binary
-Requires-Dist: tomlkit ; extra == "dev"
-Requires-Dist: line_profiler ; extra == "dev"
-Requires-Dist: pre-commit ; extra == "dev"
-Requires-Dist: nox ; extra == "dev"
-Requires-Dist: laminci>=0.3 ; extra == "dev"
-Requires-Dist: pytest>=6.0 ; extra == "dev"
-Requires-Dist: coverage ; extra == "dev"
-Requires-Dist: pytest-cov<7.0.0 ; extra == "dev"
-Requires-Dist: mudata ; extra == "dev"
-Requires-Dist: nbproject_test>=0.6.0 ; extra == "dev"
-Requires-Dist: faker-biology ; extra == "dev"
-Requires-Dist: pronto ; extra == "dev"
-Requires-Dist: readfcs>=2.0.1 ; extra == "fcs"
-Requires-Dist: lamindb_setup[gcp] ; extra == "gcp"
-Requires-Dist: numcodecs<0.16.0 ; extra == "zarr"
-Requires-Dist: zarr>=2.16.0,<3.0.0a0 ; extra == "zarr"
-Project-URL: Home, https://github.com/laminlabs/lamindb
-Provides-Extra: dev
-Provides-Extra: fcs
-Provides-Extra: gcp
-Provides-Extra: zarr
-
-[![Stars](https://img.shields.io/github/stars/laminlabs/lamindb?logo=GitHub)](https://github.com/laminlabs/lamindb)
-[![codecov](https://codecov.io/gh/laminlabs/lamindb/branch/main/graph/badge.svg?token=VKMRJ7OWR3)](https://codecov.io/gh/laminlabs/lamindb)
-[![Docs](https://img.shields.io/badge/docs-humans-yellow)](https://docs.lamin.ai)
-[![DocsLLMs](https://img.shields.io/badge/docs-LLMs-yellow)](https://docs.lamin.ai/summary.md)
-[![pypi](https://img.shields.io/pypi/v/lamindb?color=blue&label=pypi%20package)](https://pypi.org/project/lamindb)
-[![PyPI Downloads](https://img.shields.io/pepy/dt/lamindb?logo=pypi)](https://pepy.tech/project/lamindb)
-
-# LaminDB - A data framework for biology
-
-<!-- first two sentences sync from preface.md -->
-
-LaminDB is an open-source data framework to enable learning at scale in computational biology.
-It lets you track data transformations, validate & annotate datasets, and query a built-in database for biological metadata & data structures.
-
-## Setup
-
-<!-- copied from quick-setup-lamindb.md -->
-
-Install the `lamindb` Python package:
-
-```shell
-pip install lamindb
-```
-
-Create a LaminDB instance:
-
-```shell
-lamin init --storage ./quickstart-data  # or s3://my-bucket, gs://my-bucket
-```
-
-Or if you have write access to an instance, connect to it:
-
-```shell
-lamin connect account/name
-```
-
-## Quickstart
-
-<!-- copied from preface.md -->
-
-Track a script or notebook run with source code, inputs, outputs, logs, and environment.
-
-<!-- copied from py-quickstart.py -->
-
-```python
-import lamindb as ln
-
-ln.track()  # track a run
-open("sample.fasta", "w").write(">seq1\nACGT\n")
-ln.Artifact("sample.fasta", key="sample.fasta").save()  # create an artifact
-ln.finish()  # finish the run
-```
-
-<!-- from here on, slight deviation from preface.md, where all this is treated in the walk through in more depth -->
-
-Running this code inside a script via `python create-fasta.py` produces the following data lineage.
-
-```python
-artifact = ln.Artifact.get(key="sample.fasta")  # query artifact by key
-artifact.view_lineage()
-```
-
-<img src="https://lamin-site-assets.s3.amazonaws.com/.lamindb/EkQATsQL5wqC95Wj0003.png" width="220">
-
-You'll know how that artifact was created.
-
-```python
-artifact.describe()
-```
-
-<img src="https://lamin-site-assets.s3.amazonaws.com/.lamindb/BOTCBgHDAvwglN3U0001.png" width="850">
-
-Conversely, you can query artifacts by the script that created them.
-
-```python
-ln.Artifact.get(transform__key="create-fasta.py")  # query artifact by transform key
-```
-
-Data lineage is just one type of metadata to help analysis and model training through queries, validation, and annotation. Here is a more [comprehensive example](https://lamin.ai/laminlabs/lamindata/artifact/9K1dteZ6Qx0EXK8g).
-
-<img src="https://lamin-site-assets.s3.amazonaws.com/.lamindb/6sofuDVvTANB0f480001.png" width="850">
-
-## Docs
-
-Copy [summary.md](https://docs.lamin.ai/summary.md) into an LLM chat and let AI explain or read the [docs](https://docs.lamin.ai).
-