text2model 0.1.0__tar.gz → 1.1.0__tar.gz

text2model-1.1.0/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.

text2model-1.1.0/PKG-INFO

@@ -0,0 +1,287 @@
+Metadata-Version: 2.4
+Name: text2model
+Version: 1.1.0
+Summary: LLM Modeling Copilots for Text-to-Model Translation
+License: Apache-2.0
+Keywords: minizinc,constraint-programming,LLM,text-to-model
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openai
+Requires-Dist: datasets
+Requires-Dist: tqdm
+Requires-Dist: langchain-ollama
+Requires-Dist: flet==0.21.2
+Requires-Dist: pytest
+Dynamic: license-file
+
+[![Tests](https://github.com/skadio/text2model/actions/workflows/tests.yml/badge.svg)](https://github.com/skadio/text2model/actions/workflows/tests.yml)
+[![PyPI version](https://img.shields.io/pypi/v/text2model.svg?cacheSeconds=1)](https://pypi.org/project/text2model/)
+[![PyPI license](https://img.shields.io/pypi/l/text2model.svg?cacheSeconds=1)](https://pypi.python.org/pypi/text2model/)
+[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square)](http://makeapullrequest.com)
+[![Downloads](https://static.pepy.tech/personalized-badge/text2model?period=total&units=international_system&left_color=grey&right_color=orange&left_text=Downloads)](https://pepy.tech/project/text2model)
+
+---
+
+<div align="center"><a name="menu"></a>
+  <h3>
+    <a href="https://github.com/skadio/text2model?tab=readme-ov-file#text-mode">Text Mode</a> •
+    <a href="https://github.com/skadio/text2model?tab=readme-ov-file#text2zinc-mode">Text2Zinc Mode</a> •
+    <a href="https://github.com/skadio/text2model?tab=readme-ov-file#interactive-mode">Interactive Mode</a> •
+    <a href="https://github.com/skadio/text2model?tab=readme-ov-file#copilots">Copilots</a> •
+    <a href="https://github.com/skadio/text2model?tab=readme-ov-file#installation">Installation</a> •
+    <a href="https://github.com/skadio/text2model?tab=readme-ov-file#dataset-editor">Dataset Editor</a> •
+    <a href="https://github.com/skadio/text2model?tab=readme-ov-file#evaluation">Evaluation</a> •
+    <a href="https://github.com/skadio/text2model?tab=readme-ov-file#leaderboard">Leaderboard</a>
+  </h3>
+</div>
+
+---
+
+# Text2Model: LLM Modeling Copilots for Text-to-Model Translation
+
+[Text2Model](https://skadio.github.io/text2model/) is a suite of LLM modeling copilots, datasets, fined-tuned models, demos, interactive editor, and online leaderboard for translating natural language text into formal combinatorial constraint models.
+
+Text2Model uses MiniZinc as the target modeling language which makes our copilots both **paradigm- and solver-agnostic**. Our copilots generate models that can be solved by any MiniZinc compatible solver including Gecode, Chuffed, OR-Tools, CBC, Gurobi, Cplex, HiGH. This covers a wide range of paradigms including CP, CP-SAT, and MIP. As such, Text2Model can address **both combinatorial satisfaction and optimization problems.**
+
+Please visit [Text2Model](https://skadio.github.io/text2model/) for latest publications and resources.
+
+## Quick Start
+
+Text2Model supports translating given problem descriptions (**Text mode**), specific problems from our dataset (**Text2Zinc mode**), or running interactively using the [editor](https://github.com/skadio/text2model?tab=readme-ov-file#dataset-editor) (**Editor mode**).
+
+### Text Mode
+
+```bash
+# Translate a given problem description
+text2model --problem "A country produces fighter jets each year. Some of these jets must be set aside for pilot training instead of combat use. Year 1 production is 10 jets, and Year 2 production is 15 jets. Each training jet can train 5 pilots per year. Training runs for 2 years, starting in Year 1. Determine how many pilots will be trained in total by the end of Year 2."
+
+# Translate a given problem file
+text2model --problem my_problem.txt
+
+# Choose the copilot strategy and the model
+# Note that `knowledge_graph` is not available for text-mode as it requires pre-built TTL files
+text2model --problem my_problem.txt --strategies agents_with_code_validation --model gpt-4o
+
+# Redirect the output to a MiniZinc model
+text2model --problem my_problem.txt > my_model.mzn
+```
+
+### Text2Zinc Mode
+
+```bash
+# Translate specific problems from Text2Zinc
+text2model --problem-ids 0 1 2 --strategies cot --model gpt-4 --output-dir my_results
+
+# Run multiple strategies on all Text2Zinc problems
+text2model --strategies cot --model gpt-4 --output-dir my_results
+
+# Run all strategies
+text2model --strategies all --model gpt-4 --output-dir my_results
+
+# Run on specific source of Text2Zinc problems
+text2model --source nlp4lp --strategies cot --model gpt-4 --output-dir my_results
+
+# List all available data sources
+text2model --list-sources
+
+# List all available --model options (which need OPENAI_API_KEY vs. run locally through Ollama)
+text2model --list-models
+
+# Advanced options
+text2model --strategies agents --model gpt-4 \
+  --output-dir my_results \
+  --temperature 0.7 \
+  --max-tokens 8192 \
+  --sleep-time 2 \
+  --include-unverified
+
+# Use a local dataset (e.g. one saved by `text2model --editor`) instead of the
+# default skadio/text2zinc HuggingFace dataset
+text2model --strategies cot --model gpt-4 --output-dir my_results \
+  --dataset-path text2zinc_edited.csv
+```
+
+### Interactive Mode
+
+```bash
+text2model --editor
+text2model --editor --dataset-path text2zinc_edited.csv
+```
+
+See [Dataset Editor](https://github.com/skadio/text2model?tab=readme-ov-file#dataset-editor) for details.
+
+## Copilots
+
+Text2Model offers different copilot strategies, ranging from simple single-call approaches to sophisticated multi-agent systems. Each makes different trade-offs between speed and accuracy.
+
+| Strategy | Description                                                                                                                                                   |
+|----------|---------------------------------------------------------------------------------------------------------------------------------------------------------------|
+| `baseline` | Direct code generation from problem description. No special prompting. Good for simple problems or establishing a baseline.                                   |
+| `cot` | **Chain-of-Thought** prompting with guiding principles. The LLM reasons through the problem step-by-step before generating code.                              |
+| `knowledge_graph` | First extracts structured information (entities, relationships) from the problem, then generates code from this intermediate representation.                  |
+| `cot_with_code_validation` | Generates code with CoT, then validates and fixes any compilation errors. Good default choice.                                                                |
+| `cot_with_grammar_validation` | Generates code with CoT, then checks against MiniZinc grammar rules.                                                                                          |
+| `cot_with_code_and_grammar_validation` | Combines CoT generation with both grammar checking and code validation.                                                                                       |
+| `agents` | Decomposes the task into specialized agents: (1) parameters & variables, (2) constraints, (3) objective, (4) assembler that stitches everything together.     |
+| `agents_with_code_validation` | Agents approach plus a final validation/fix step.                                                                                                            |
+| `gala` | Global Agents for different constraint types (all_different, cumulative, etc.) plus an assembler. See the [GALA paper](https://arxiv.org/abs/2509.08970).|
+
+> **Want to use `knowledge_graph` on your own problems?** It requires a pre-built `.ttl` knowledge-graph file per problem. See [`text2model/generate_knowledge_graph.py`](text2model/generate_knowledge_graph.py) and any example file under [`text2model/knowledge_graphs/`](text2model/knowledge_graphs/) (e.g. `nlp4lp_1.ttl`) and do similar — either adapt the script to your problem or hand-write a `.ttl` following the same structure.
+
+### Adding a Custom Copilot
+
+Every strategy in the table above follows the same shape, so plugging in a new one is mechanical:
+
+1. **Add prompt(s)** under [`text2model/prompts/`](text2model/prompts/) (`.txt` files with `{problem_description}`, `{input_data}`, etc. placeholders — see any existing prompt for the pattern).
+2. **Write a `run_<name>_strategy(client, model, problem, problem_identifier, output_dir)` function** in [`text2model/main.py`](text2model/main.py). Use `utils.prepare_problem_data`, `utils.get_effective_input_data`, and `utils.load_file` to build your prompt(s), call `utils.call_api(client, model, prompt)` to get code back, and stitch/combine calls the way `run_agents_strategy` does if your copilot needs multiple LLM calls. Finish with `utils.save_solution(output_dir, problem_identifier, code)`.
+3. **Register it** by adding `'<name>': run_<name>_strategy` to `_STRATEGY_MAP` in `main.py`, and add `'<name>'` to the `--strategies` argparse `choices` list (and to the `'all'` expansion list if it should run as part of `--strategies all`).
+
+That's it — your strategy is now available via `--strategies <name>` in both `--problem` and batch modes.
+
+## Installation
+
+Text2Model requires **Python 3.8+** and can be installed from PyPI or by building from source.
+
+### Set Your API Key
+
+```bash
+export OPENAI_API_KEY="your-api-key-here"
+```
+
+### Install from PyPI
+```bash
+pip install text2model
+```
+
+### Install from Source
+```bash
+git clone https://github.com/skadio/text2model.git
+cd text2model
+pip install -e .
+```
+
+## Dataset Editor
+
+Text2Model ships a GUI editor (built with [Flet](https://flet.dev)) for browsing and editing Text2Zinc problems (input.json, data.dzn, model.mzn, output.json), running them through MiniZinc, and chatting with an AI assistant for help rephrasing descriptions or fixing model code.
+
+### Launch
+
+```bash
+text2model --editor
+```
+
+By default the editor opens, in order: a previous editing session (`text2zinc_edited.csv` in the current directory), otherwise the dataset bundled with the package. Use the **"Load from HuggingFace"** button inside the editor to instead start from a fresh copy of `skadio/text2zinc`, or open any other local dataset with **"Open CSV..."** — or non-interactively:
+
+```bash
+text2model --editor --dataset-path my_dataset.csv
+```
+
+### Save and Benchmark
+
+- **Save** (or Ctrl+S) quick-saves your edits to `text2zinc_edited.csv` in the current directory.
+- **Save As New Dataset...** exports to any path you choose. That path is a complete Text2Zinc dataset you can pass to `--dataset-path` to generate or benchmark against your edits instead of the default HuggingFace dataset:
+
+```bash
+text2model --strategies cot --model gpt-4 --output-dir my_results --dataset-path my_dataset.csv
+python evals/evaluate.py --output-dir my_results --dataset-path my_dataset.csv
+```
+
+## Evaluation
+
+After generating models, evaluate their correctness via [`evals/evaluate.py`](evals/evaluate.py). This script compiles and runs each generated MiniZinc model against test instances, checking for both execution success and solution correctness.
+
+#### Prerequisite
+
+Install MiniZinc solver: https://www.minizinc.org/doc-2.5.5/en/installation.html
+
+#### Evals
+```bash
+# Evaluate all generated code
+# `--output-dir` is required. Point it at the directory produced by the batch-mode `text2model` run.
+python evals/evaluate.py --output-dir my_results
+
+# Evaluate against a local dataset (e.g. one saved by `text2model --editor`) instead
+# of the default skadio/text2zinc HuggingFace dataset
+python evals/evaluate.py --output-dir my_results --dataset-path text2zinc_edited.csv
+```
+
+Running the eval generates a JSON file (`evals/evaluation_results.json` by default, via `--output-json`) with your accuracy metrics. You can PR that file to the [Text2Model Leaderboard](https://huggingface.co/spaces/skadio/text2model-leaderboard) on Hugging Face to get your results added to the online leaderboard.
+
+#### Metrics
+
+| Metric | Description |
+|--------|-------------|
+| **Execution Accuracy** | % of models that compile and run without errors |
+| **Solution Accuracy** | % of models that produce correct solutions |
+| **Average Score** | Average of execution and solution accuracy |
+
+Results are broken down by problem type as satisfaction vs. optimization.
+
+## Leaderboard
+
+Text2Model hosts an online leaderboard tracking execution accuracy, solution accuracy, and average score across models and copilot strategies on the Text2Zinc benchmark:
+
+**[Text2Model Leaderboard](https://huggingface.co/spaces/skadio/text2model-leaderboard)** (Hugging Face Spaces)
+
+## Testing
+
+**Default tests** (`tests/test_main.py`, `tests/test_utils.py`) do not need an API key, network, or MiniZinc.
+They are pure logic tests with mocked API calls and is run by the CI:
+
+```bash
+pytest -m "not integration"
+```
+
+**Integration tests** (`tests/test_integration.py`) hit real external dependencies and are opt-in only.
+This is not to be used in CI:
+- MiniZinc tests run the real `minizinc` binary and are skipped unless it is on `PATH`.
+- The OpenAI test makes exactly one real, cheap, token-capped call (`gpt-4o-mini`, `max_tokens=20`) and is skipped unless `OPENAI_API_KEY` is set. It's intentionally not exhaustive to avoid API costs.
+
+To run everything locally (with `OPENAI_API_KEY` set and MiniZinc installed):
+
+```bash
+pytest -m ""
+```
+
+## Repository Structure
+```
+text2model/
+├── text2model/                  # Installable Python package
+│   ├── prompts/                 # Prompt templates for each strategy
+│   │   ├── cot_prompt.txt
+│   │   ├── code_validation_prompt.txt
+│   │   ├── global_constraint_prompts/
+│   │   └── ...
+│   ├── knowledge_graphs/        # KG files (.ttl) for knowledge_graph strategy
+│   ├── editor/                  # Dataset editor GUI (`text2model --editor`)
+│   │   ├── app.py               # Flet app: browse/edit/execute Text2Zinc problems, AI chat assistant
+│   │   └── data/text2zinc.csv   # Bundled default dataset the editor opens on first run
+│   ├── grammar.mzn              # MiniZinc grammar for validation
+│   ├── main.py                  # Copilot strategies and CLI entry point
+│   ├── generate_knowledge_graph.py  # Generates KGs for the knowledge_graph strategy
+│   └── utils.py                 # Shared utilities (API calls, validation, dataset loading)
+├── tests/                       # Unit and integration tests (pytest)
+├── evals/                       # Evaluation tooling
+│   ├── evaluate.py              # Evaluates generated MiniZinc models
+│   ├── evaluation_results.json  # Latest evaluation results (PR-able to the HF leaderboard)
+│   └── results/                 # Accuracy metrics and leaderboard from paper runs
+├── output/                      # Original outputs per strategy, kept for reproducing paper results
+│   └── [model]/[strategy]/      # e.g., gpt-4/cot/problem_1.mzn
+├── pyproject.toml               # Package metadata and install config
+├── CHANGELOG.txt                # Release history
+└── LICENSE                      # Apache License 2.0
+```
+
+## Support
+
+Please submit bug reports and feature requests as [Issues](https://github.com/skadio/text2model/issues).
+
+## License
+
+Text2Model is licensed under the [Apache License 2.0](LICENSE).
+
+<br>