lmlite 0.2.1__tar.gz

lmlite-0.2.1/LICENSE

@@ -0,0 +1,201 @@
+                                 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.

lmlite-0.2.1/NOTICE

@@ -0,0 +1,6 @@
+lmLite
+
+This project includes code developed by Emmanuel Decitre.
+
+It uses Transformers.js (Apache License 2.0).
+Models loaded at runtime may be subject to their own licenses.

lmlite-0.2.1/PKG-INFO

@@ -0,0 +1,272 @@
+Metadata-Version: 2.4
+Name: lmlite
+Version: 0.2.1
+Summary: Browser-native LLM orchestration in JupyterLite
+Author-email: Emmanuel Decitre <590094+decitre@users.noreply.github.com>
+License-Expression: Apache-2.0
+Project-URL: repository, https://github.com/decitre/lmlite
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: WebAssembly :: Emscripten
+Classifier: Intended Audience :: Developers
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Dynamic: license-file
+
+# lmLite
+
+Browser-native LLM orchestration in JupyterLite - run language models entirely in your browser using WebAssembly.
+
+## Features
+
+- **Browser-native**: Run LLMs entirely in the browser, no server required
+- **Zero setup**: No installation, no API keys, works offline
+- **Privacy-first**: All computation happens locally in your browser
+- **Multiple models**: Support for GPT-2, DistilGPT-2, and more via Transformers.js
+- **Embeddings**: Generate text embeddings for semantic search
+- **Similarity search**: Built-in cosine similarity for RAG applications
+- **Model caching**: Download once, use offline forever
+- **Pythonic API**: Clean, async Python interface
+
+<!-- To re-introduce when the Actions page is up
+## Quick Start
+
+### Try the Demo (No Installation)
+
+**Recommended**: Visit the live demo with xeus-python kernel at:
+[https://decitre.github.io/lmlite/](https://decitre.github.io/lmlite/)
+
+**Alternative**: Pyodide kernel demo at:
+[https://decitre.github.io/lmlite/pyodide/](https://decitre.github.io/lmlite/pyodide/)
+
+Open the `demo.ipynb` notebook and run the cells to see LMLite in action.
+
+### Install from PyPI
+
+```bash
+pip install lmlite
+```
+
+**Note**: LMLite is designed to run in JupyterLite environments (xeus-python or pyodide kernels). For local development and testing, see the Development section below.
+
+-->
+
+## Usage
+
+```python
+from lmlite import LLM
+
+# Create LLM instance (downloads model on first run)
+llm = await LLM.create(generator_model="gpt2")
+
+# Generate text
+text = await llm.generate("Python is a great language because")
+print(text)
+
+# Generate embeddings
+embedding = await llm.embed("Hello world")
+print(embedding[:5])  # First 5 dimensions
+
+# Similarity search
+docs = [
+    "JupyterLite runs entirely in the browser.",
+    "Python is widely used for machine learning.",
+    "TypeScript is great for frontend applications.",
+]
+
+results = await llm.similarity_search(
+    "Where does JupyterLite run?",
+    docs
+)
+
+for doc, score in results:
+    print(f"{score:.3f} -> {doc}")
+```
+
+### Configuration Options
+
+```python
+llm = await LLM.create(
+    generator_model="gpt2",           # or "distilgpt2", etc.
+    embedding_model="all-MiniLM-L6-v2",
+    max_new_tokens=50,
+    temperature=0.7,
+    top_k=50,
+    do_sample=True,
+    use_local_models=False,           # Auto-detect local models
+    local_models_path="/drive/models"
+)
+```
+
+### Export Models for Offline Use
+
+After using models in the browser, you can export them for offline use:
+
+```python
+# Export to zip file (default)
+await llm.export_model_files("gpt2")
+
+# Export to directory
+await llm.export_model_files("gpt2", as_zip=False)
+```
+
+The exported files will be saved to `/drive/models/` and can be downloaded from JupyterLite.
+
+## Development
+
+### Prerequisites
+
+- [pixi](https://pixi.sh/) - Package manager (required)
+- [micromamba](https://mamba.readthedocs.io/en/latest/installation/micromamba-installation.html) - Conda package manager (required for JupyterLite builds)
+
+**Supported Platforms**: macOS (Intel/Apple Silicon) and Linux. Windows is not currently supported for development.
+
+### Setup
+
+```bash
+# Clone the repository
+git clone https://github.com/decitre/lmlite.git
+cd lmlite
+pixi install
+```
+
+### Development Tasks
+
+```bash
+# Run tests
+pixi run test
+
+# Quick tests (skip notebook tests)
+pixi run quick-test
+
+# Run linter
+pixi run lint
+
+# Check linting without fixing
+pixi run lint-check
+
+# Run tests with coverage
+pixi run coverage
+
+# Build wheel
+pixi run wheel
+```
+
+### Build JupyterLite Demo
+
+```bash
+pixi run lite-build
+```
+
+Follow the instructions provided by the command.
+
+### Run Tests in Different Python Versions
+
+```bash
+pixi run --environment py311 test
+pixi run --environment py312 test
+pixi run --environment py313 test
+```
+
+## How It Works
+
+LMLite bridges Python (via xeus-python or pyodide) and JavaScript (via Transformers.js):
+
+1. **JavaScript Layer**: Uses [@huggingface/transformers](https://www.npmjs.com/package/@xenova/transformers) to run ONNX models in the browser
+2. **Python Bridge**: Exposes JavaScript functionality through a Pythonic async API
+3. **Kernel Support**:
+   - **xeus-python** (recommended): Full CPython in WebAssembly via emscripten
+   - **pyodide**: Alternative WebAssembly Python runtime
+4. **Model Loading**:
+   - First run: Downloads models from HuggingFace CDN
+   - Cached: Uses browser's Cache API or IndexedDB
+   - Local: Reads from virtual filesystem if available
+5. **Execution**: Models run entirely in-browser using WebAssembly (WASM)
+
+## Supported Models
+
+### Text Generation
+- `gpt2` - GPT-2 (124M parameters)
+- `distilgpt2` - Smaller, faster GPT-2 variant
+
+### Embeddings
+- `all-MiniLM-L6-v2` - Sentence embeddings (384 dimensions)
+
+For other models, check [Xenova's model list](https://huggingface.co/Xenova).
+
+## Architecture
+
+```
+┌─────────────────────────────────────┐
+│   Python (JupyterLite)              │
+│   ├─ xeus-python (recommended)      │
+│   └─ pyodide (alternative)          │
+│                                     │
+│   from lmlite import LLM            │
+│   llm = await LLM.create()          │
+│   text = await llm.generate(...)    │
+└─────────────┬───────────────────────┘
+              │ Bridge
+              │ (pyodide.ffi / pjs)
+┌─────────────▼───────────────────────┐
+│   JavaScript (Browser)              │
+│                                     │
+│   Transformers.js                   │
+│   ├─ Model loading                  │
+│   ├─ ONNX Runtime (WASM)            │
+│   └─ WebGPU (optional)              │
+└─────────────────────────────────────┘
+```
+
+
+## License
+
+This project is licensed under the Apache License 2.0 - see the LICENSE file for details.
+
+**Dependencies:**
+- [Transformers.js](https://github.com/xenova/transformers.js) - Apache 2.0
+
+**Note**: Individual model licenses may vary. Check the model card on HuggingFace before use.
+
+## Acknowledgments
+
+- [Transformers.js](https://github.com/xenova/transformers.js) by [@xenova](https://github.com/xenova)
+- [JupyterLite](https://jupyterlite.readthedocs.io/) team
+- [Pyodide](https://pyodide.org/) project
+- [Hugging Face](https://huggingface.co/) for model hosting
+- [LLMs running in the browser](https://thekevinscott.com/llms-in-the-browser/)
+
+## Troubleshooting
+
+### Models downloading every time?
+
+Check browser console for Cache API availability. Some privacy settings may disable caching.
+
+### Out of memory errors?
+
+Try smaller models like `distilgpt2` or reduce `max_new_tokens`.
+
+### CORS errors?
+
+Ensure you're running from `http://localhost` or a proper HTTPS domain, not `file://`.
+
+## Citation
+
+If you use LMLite in your research, please cite:
+
+```bibtex
+@software{lmlite2026,
+  author = {Decitre, Emmanuel},
+  title = {LMLite: Browser-native LLM orchestration in JupyterLite},
+  year = {2026},
+  url = {https://github.com/decitre/lmlite}
+}
+```