Metadata-Version: 2.4
Name: xorq
Version: 0.3.3
Summary: Data processing library built on top of Ibis and DataFusion to write multi-engine data workflows.
Project-URL: Homepage, https://www.xorq.dev/
Project-URL: Repository, https://github.com/xorq-labs/xorq/
Project-URL: Issues, https://github.com/xorq-labs/xorq/issues
Project-URL: Changelog, https://github.com/xorq-labs/xorq/blob/main/CHANGELOG.md
Project-URL: Documentation, https://docs.xorq.dev/
Author-email: Hussain Sultan <hussain@letsql.com>
Maintainer-email: Dan Lovell <dan@letsql.com>, Daniel Mesejo <mesejo@letsql.com>
License:                                  Apache License
                                   Version 2.0, January 2004
                                http://www.apache.org/licenses/
        
           TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
        
           1. Definitions.
        
              "License" shall mean the terms and conditions for use, reproduction,
              and distribution as defined by Sections 1 through 9 of this document.
        
              "Licensor" shall mean the copyright owner or entity authorized by
              the copyright owner that is granting the License.
        
              "Legal Entity" shall mean the union of the acting entity and all
              other entities that control, are controlled by, or are under common
              control with that entity. For the purposes of this definition,
              "control" means (i) the power, direct or indirect, to cause the
              direction or management of such entity, whether by contract or
              otherwise, or (ii) ownership of fifty percent (50%) or more of the
              outstanding shares, or (iii) beneficial ownership of such entity.
        
              "You" (or "Your") shall mean an individual or Legal Entity
              exercising permissions granted by this License.
        
              "Source" form shall mean the preferred form for making modifications,
              including but not limited to software source code, documentation
              source, and configuration files.
        
              "Object" form shall mean any form resulting from mechanical
              transformation or translation of a Source form, including but
              not limited to compiled object code, generated documentation,
              and conversions to other media types.
        
              "Work" shall mean the work of authorship, whether in Source or
              Object form, made available under the License, as indicated by a
              copyright notice that is included in or attached to the work
              (an example is provided in the Appendix below).
        
              "Derivative Works" shall mean any work, whether in Source or Object
              form, that is based on (or derived from) the Work and for which the
              editorial revisions, annotations, elaborations, or other modifications
              represent, as a whole, an original work of authorship. For the purposes
              of this License, Derivative Works shall not include works that remain
              separable from, or merely link (or bind by name) to the interfaces of,
              the Work and Derivative Works thereof.
        
              "Contribution" shall mean any work of authorship, including
              the original version of the Work and any modifications or additions
              to that Work or Derivative Works thereof, that is intentionally
              submitted to Licensor for inclusion in the Work by the copyright owner
              or by an individual or Legal Entity authorized to submit on behalf of
              the copyright owner. For the purposes of this definition, "submitted"
              means any form of electronic, verbal, or written communication sent
              to the Licensor or its representatives, including but not limited to
              communication on electronic mailing lists, source code control systems,
              and issue tracking systems that are managed by, or on behalf of, the
              Licensor for the purpose of discussing and improving the Work, but
              excluding communication that is conspicuously marked or otherwise
              designated in writing by the copyright owner as "Not a Contribution."
        
              "Contributor" shall mean Licensor and any individual or Legal Entity
              on behalf of whom a Contribution has been received by Licensor and
              subsequently incorporated within the Work.
        
           2. Grant of Copyright License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              copyright license to reproduce, prepare Derivative Works of,
              publicly display, publicly perform, sublicense, and distribute the
              Work and such Derivative Works in Source or Object form.
        
           3. Grant of Patent License. Subject to the terms and conditions of
              this License, each Contributor hereby grants to You a perpetual,
              worldwide, non-exclusive, no-charge, royalty-free, irrevocable
              (except as stated in this section) patent license to make, have made,
              use, offer to sell, sell, import, and otherwise transfer the Work,
              where such license applies only to those patent claims licensable
              by such Contributor that are necessarily infringed by their
              Contribution(s) alone or by combination of their Contribution(s)
              with the Work to which such Contribution(s) was submitted. If You
              institute patent litigation against any entity (including a
              cross-claim or counterclaim in a lawsuit) alleging that the Work
              or a Contribution incorporated within the Work constitutes direct
              or contributory patent infringement, then any patent licenses
              granted to You under this License for that Work shall terminate
              as of the date such litigation is filed.
        
           4. Redistribution. You may reproduce and distribute copies of the
              Work or Derivative Works thereof in any medium, with or without
              modifications, and in Source or Object form, provided that You
              meet the following conditions:
        
              (a) You must give any other recipients of the Work or
                  Derivative Works a copy of this License; and
        
              (b) You must cause any modified files to carry prominent notices
                  stating that You changed the files; and
        
              (c) You must retain, in the Source form of any Derivative Works
                  that You distribute, all copyright, patent, trademark, and
                  attribution notices from the Source form of the Work,
                  excluding those notices that do not pertain to any part of
                  the Derivative Works; and
        
              (d) If the Work includes a "NOTICE" text file as part of its
                  distribution, then any Derivative Works that You distribute must
                  include a readable copy of the attribution notices contained
                  within such NOTICE file, excluding those notices that do not
                  pertain to any part of the Derivative Works, in at least one
                  of the following places: within a NOTICE text file distributed
                  as part of the Derivative Works; within the Source form or
                  documentation, if provided along with the Derivative Works; or,
                  within a display generated by the Derivative Works, if and
                  wherever such third-party notices normally appear. The contents
                  of the NOTICE file are for informational purposes only and
                  do not modify the License. You may add Your own attribution
                  notices within Derivative Works that You distribute, alongside
                  or as an addendum to the NOTICE text from the Work, provided
                  that such additional attribution notices cannot be construed
                  as modifying the License.
        
              You may add Your own copyright statement to Your modifications and
              may provide additional or different license terms and conditions
              for use, reproduction, or distribution of Your modifications, or
              for any such Derivative Works as a whole, provided Your use,
              reproduction, and distribution of the Work otherwise complies with
              the conditions stated in this License.
        
           5. Submission of Contributions. Unless You explicitly state otherwise,
              any Contribution intentionally submitted for inclusion in the Work
              by You to the Licensor shall be under the terms and conditions of
              this License, without any additional terms or conditions.
              Notwithstanding the above, nothing herein shall supersede or modify
              the terms of any separate license agreement you may have executed
              with Licensor regarding such Contributions.
        
           6. Trademarks. This License does not grant permission to use the trade
              names, trademarks, service marks, or product names of the Licensor,
              except as required for reasonable and customary use in describing the
              origin of the Work and reproducing the content of the NOTICE file.
        
           7. Disclaimer of Warranty. Unless required by applicable law or
              agreed to in writing, Licensor provides the Work (and each
              Contributor provides its Contributions) on an "AS IS" BASIS,
              WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
              implied, including, without limitation, any warranties or conditions
              of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
              PARTICULAR PURPOSE. You are solely responsible for determining the
              appropriateness of using or redistributing the Work and assume any
              risks associated with Your exercise of permissions under this License.
        
           8. Limitation of Liability. In no event and under no legal theory,
              whether in tort (including negligence), contract, or otherwise,
              unless required by applicable law (such as deliberate and grossly
              negligent acts) or agreed to in writing, shall any Contributor be
              liable to You for damages, including any direct, indirect, special,
              incidental, or consequential damages of any character arising as a
              result of this License or out of the use or inability to use the
              Work (including but not limited to damages for loss of goodwill,
              work stoppage, computer failure or malfunction, or any and all
              other commercial damages or losses), even if such Contributor
              has been advised of the possibility of such damages.
        
           9. Accepting Warranty or Additional Liability. While redistributing
              the Work or Derivative Works thereof, You may choose to offer,
              and charge a fee for, acceptance of support, warranty, indemnity,
              or other liability obligations and/or rights consistent with this
              License. However, in accepting such obligations, You may act only
              on Your own behalf and on Your sole responsibility, not on behalf
              of any other Contributor, and only if You agree to indemnify,
              defend, and hold each Contributor harmless for any liability
              incurred by, or claims asserted against, such Contributor by reason
              of your accepting any such warranty or additional liability.
        
           END OF TERMS AND CONDITIONS
        
           APPENDIX: How to apply the Apache License to your work.
        
              To apply the Apache License to your work, attach the following
              boilerplate notice, with the fields enclosed by brackets "[]"
              replaced with your own identifying information. (Don't include
              the brackets!)  The text should be enclosed in the appropriate
              comment syntax for the file format. We also recommend that a
              file or class name and description of purpose be included on the
              same "printed page" as the copyright notice for easier
              identification within third-party archives.
        
           Copyright [yyyy] [name of copyright owner]
        
           Licensed under the Apache License, Version 2.0 (the "License");
           you may not use this file except in compliance with the License.
           You may obtain a copy of the License at
        
               http://www.apache.org/licenses/LICENSE-2.0
        
           Unless required by applicable law or agreed to in writing, software
           distributed under the License is distributed on an "AS IS" BASIS,
           WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
           See the License for the specific language governing permissions and
           limitations under the License.
License-File: LICENSE
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Science/Research
Classifier: License :: OSI Approved :: Apache Software License
Classifier: Programming Language :: Python :: Implementation :: CPython
Classifier: Programming Language :: Rust
Classifier: Topic :: Database :: Database Engines/Servers
Classifier: Topic :: Software Development :: User Interfaces
Requires-Python: >=3.10
Requires-Dist: atpublic>=5.1
Requires-Dist: attrs<26,>=24.0.0; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: cityhash<1,>=0.4.7; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: cloudpickle>=3.1.1
Requires-Dist: cryptography>=45.0.3
Requires-Dist: dask==2025.1.0; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: envyaml>=1.10.211231
Requires-Dist: geoarrow-types<1,>=0.2; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: opentelemetry-exporter-otlp>=1.32.1
Requires-Dist: opentelemetry-exporter-prometheus>=0.55b1
Requires-Dist: opentelemetry-sdk>=1.32.1
Requires-Dist: pandas<3,>=1.5.3; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: parsy>=2
Requires-Dist: prometheus-client>=0.22.1
Requires-Dist: pyarrow-hotfix<1,>=0.4; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: pyarrow<22,>=13.0.0; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: pytest-mock<4,>=3.14.0; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: python-dateutil>=2.8.2
Requires-Dist: pythran>=0.17.0; sys_platform == 'darwin'
Requires-Dist: pytz>=2022.7
Requires-Dist: pyyaml>=6.0.2
Requires-Dist: rich>=13.9.4
Requires-Dist: sqlglot==25.20.2
Requires-Dist: strenum>=0.4.15; python_version <= '3.10'
Requires-Dist: structlog<26,>=24.2.0; python_version >= '3.10' and python_version < '4.0'
Requires-Dist: toolz>=0.11
Requires-Dist: typing-extensions>=4.3.0
Requires-Dist: uv>=0.7.20
Requires-Dist: xorq-datafusion==0.2.4
Provides-Extra: datafusion
Requires-Dist: datafusion<49,>=0.6; (python_version >= '3.10' and python_version < '4.0') and extra == 'datafusion'
Provides-Extra: duckdb
Requires-Dist: duckdb>=1.1.3; extra == 'duckdb'
Provides-Extra: examples
Requires-Dist: adbc-driver-postgresql>=1.4.0; extra == 'examples'
Requires-Dist: duckdb<2,>=0.10.3; (python_version >= '3.10' and python_version < '4.0') and extra == 'examples'
Requires-Dist: fsspec<2025.7.1,>=2024.6.1; (python_version >= '3.10' and python_version < '4.0') and extra == 'examples'
Requires-Dist: mcp>=1.5.0; extra == 'examples'
Requires-Dist: openai>=1.65.4; extra == 'examples'
Requires-Dist: pins[gcs]<1,>=0.8.3; (python_version >= '3.10' and python_version < '4.0') and extra == 'examples'
Requires-Dist: quickgrove>=0.1.2; extra == 'examples'
Requires-Dist: requests>=2.32.3; extra == 'examples'
Requires-Dist: scikit-learn<2.0.0,>=1.4.0; extra == 'examples'
Requires-Dist: xgboost>=1.6.1; (python_version >= '3.10' and python_version < '4.0') and extra == 'examples'
Requires-Dist: xorq-feature-utils; extra == 'examples'
Requires-Dist: xorq-weather-lib; extra == 'examples'
Provides-Extra: ibis
Requires-Dist: ibis-framework>=10.5.0; extra == 'ibis'
Provides-Extra: postgres
Requires-Dist: adbc-driver-postgresql>=1.4.0; extra == 'postgres'
Requires-Dist: psycopg-c>=3.2.10; extra == 'postgres'
Requires-Dist: psycopg>=3.2.0; extra == 'postgres'
Provides-Extra: pyiceberg
Requires-Dist: pyiceberg[sql-postgres,sql-sqlite]>=0.9.0; extra == 'pyiceberg'
Provides-Extra: quickgrove
Requires-Dist: quickgrove>=0.1.2; extra == 'quickgrove'
Provides-Extra: snowflake
Requires-Dist: adbc-driver-snowflake>=1.5.0; extra == 'snowflake'
Requires-Dist: snowflake-connector-python<4,>=3.10.1; (python_version >= '3.10' and python_version < '4.0') and extra == 'snowflake'
Provides-Extra: sqlite
Requires-Dist: adbc-driver-sqlite>=1.4.0; extra == 'sqlite'
Description-Content-Type: text/markdown

<div align="center">

![Xorq Logo](docs/images/Xorq_WordMark_RGB_Midnight.png#gh-light-mode-only)
![Xorq Logo](docs/images/Xorq_WordMark_RGB_BlueSky.png#gh-dark-mode-only)

![License](https://img.shields.io/github/license/xorq-labs/xorq)
![PyPI - Version](https://img.shields.io/pypi/v/xorq)
![CI Status](https://img.shields.io/github/actions/workflow/status/xorq-labs/xorq/ci-test.yml)

</div>

> **Xorq is a multi‑engine batch transformation framework built on Ibis,
> DataFusion and Arrow.**
> It ships a compute catalog and a multi-engine manifest you can run
> across DuckDB, Snowflake, DataFusion, and more.

---

## What Xorq gives you

- **Multi-engine manifest:** A single, typed plan captured as a YAML artifact
that can execute in DuckDB, Snowflake, DataFusion, etc.
- **Deterministic builds & caching:** Content hashes of the plan power
reproducible runs and cheap replays.
- **Lineage & Schemas:** Compile-time schema checks and end-to-end to end
column-level lineage.
- **Compute catalog:** Versioned registry that stores and operates on manifests
(run, cache, diff, serve-unbound).
- **Portable UDxFs:** Arbitrary python logic with schema-in/out contracts
portable via Arrow Flight.
- **Scikit-learn integration:** Model fitting pipeline captured in the predict
pipeline manifest for portable batch scoring and model training lineage

> **Not an orchestrator.** Use Xorq from Airflow, Dagster, GitHub Actions, etc.

> **Not streaming/online.** Xorq focuses on **batch**,**out-of-core**
> transformations.


## Quickstart

```bash
pip install xorq[examples]
xorq init -t penguins
```

Then follow the [Quickstart
Tutorial](https://docs.xorq.dev/tutorials/getting_started/quickstart) for a
full walk-through using the Penguins dataset.

## From `scikit-learn` to multi-engine manifest

The manifest is a collection of YAML files that captures the expression graph
and supporting files like memtables serialized to disk.

Once you xorq build your pipeline, you get:

- expr.yaml: a reproducible expression graph
- deferred_reads.yaml: source metadata
- SQL and metadata files for inspection and CI

Xorq makes it easy to bring your scikit-learn Pipeline and automatically
converts it into a deferred Xorq expression.

```python
import xorq.api as xo
from xorq.expr.ml.pipeline_lib import Pipeline


(train, test) = xo.test_train_splits(...)
sklearn_pipeline = make_pipeline(...)
xorq_pipeline = Pipeline.from_instance(sklearn_pipeline)
# still no work done: deferred fit expression
fitted_pipeline = xorq_pipeline.fit(train, features=features, target=target)
expr = fitted_pipeline.predict(test[features])
```

Here's a commented snippet from a YAML manifest

```bash
predicted:
  op: ExprScalarUDF            # predict(...)
  kwargs:
    bill_length_mm: ...        # features
    bill_depth_mm: ...
    flipper_length_mm: ...
    body_mass_g: ...
  meta:
    __config__:
      computed_kwargs_expr:
        op: AggUDF             # fit(...)
        kwargs:
          bill_length_mm: ...
          bill_depth_mm: ...
          flipper_length_mm: ...
          body_mass_g: ...
          species: ...         # target
```
The YAML format serializes the Expression graph and all its nodes, including
UDFs as pickled entries.

## From manifest to catalog

Once an expression is built, we can then catalog it and share across teams.

The compute catalog is a versioned registry of compute manifests. It can be
stored in Git, S3, GCS, or a database.

```bash
❯ xorq catalog add builds/{build-hash} --alias penguins-model
```

```
❯ xorq catalog ls
Aliases:
mortgage-test-predicted dbf90860-88b3-4b6c-830a-8518b3296e7c    r1
Entries:
dbf90860-88b3-4b6c-830a-8518b3296e7c    r1      52f987594254
```

You can then run, serve or cache the catalog entry, including unbinding nodes
that depend on external state (e.g. source tables). This is useful to serve a
trained pipeline with new data.

### Serve the same expression with new inputs (serve-unbound)

We can rerun an expression with new inputs by replacing an arbitrary node in
the expression defined by its node-hash.

```bash
xorq serve-unbound builds/7061dd65ff3c --host localhost --port 8001 --cache-dir penguins_example b2370a29c19df8e1e639c63252dacd0e
```
- `builds/7061dd65ff3c`: Your built expression manifest
- `--host localhost --port 8001`: Where to serve the UDxF from
- `--cache-dir penguins_example`: Directory for caching results
- `b2370a29c19df8e1e639c63252dacd0e`: The node-hash that represents the expression input to replace

To learn more on how to find the node hash, check out the [Serve Unbound](https://docs.xorq.dev/tutorials/getting_started/quickstart#finding-the-node-hash).

### Compose with the served expression:

```python
import xorq.api as xo

client = xo.flight.connect("localhost", 8001)
f = client.get_exchange("default") # currently all expressions get the default name in addition to their hash

new_expr = expr.pipe(f)

new_expr.execute()
```

## How Xorq works

Xorq uses Apache Arrow Flight RPC for zero-copy data transfer and leverages Ibis and
DataFusion under the hood for efficient computation.

![Xorq Architecture](docs/images/how-xorq-works-2.png)

## Use cases

A generic catalog that can be used to build new workloads:

- Lineage‑preserving, multi-engine feature stores (offline, reproducible)
- Composable data products (ship datasets as compute artifacts)
- Governed sharing of compute (catalog entries as the contract between teams)
- ML/data pipeline development (deterministic builds)


Also great for:

- Generating SQL from high-level DSLs (e.g. Semantic Layers)
- Batch model scoring across engines (same expr, different backends)
- Cross‑warehouse migrations (portability via Ibis + UDxFs)
- Data CI (compile‑time schema/lineage checks in PRs)


## Learn More

* [Why Xorq?](https://docs.xorq.dev/#why-xorq)
* [Caching Guide](https://docs.xorq.dev/core_concepts/caching)
* [Backend Profiles](https://docs.xorq.dev/api_reference/backend_configuration/profiles_api)
* [Scikit-learn Template](https://github.com/xorq-labs/xorq-template-sklearn)

## Status

Xorq is pre-1.0 and evolving fast. Expect breaking changes.

## Get Involved

* [Website](https://www.xorq.dev)
* [Discord](https://discord.gg/8Kma9DhcJG)
* [Contribute on GitHub](https://github.com/xorq-labs/xorq)
