autographql 0.1.0__tar.gz

autographql-0.1.0/.gitignore

@@ -0,0 +1,243 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+*.lcov
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# uv
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi/*
+!.pixi/config.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule*
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs/Zensical documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore that
+#   can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, you
+#   could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml
+
+# ---------------------------------------------------------------------------
+# Project-specific
+# ---------------------------------------------------------------------------
+# Generated at build time by hatch-vcs from the git tag. Committing it makes the
+# tree dirty after every build, and setuptools_scm then reports a .dev version
+# instead of the tag.
+src/autographql/_version.py
+
+# CLI output: autographql-generate writes here by default.
+generated_queries/
+
+# Datasets live in https://github.com/nl2graphql-bench/datasets, not here.
+*.jsonl
+*.jsonl.gz
+*.xlsx
+
+# The 2,100-row hidden benchmark must never be committed anywhere, public or
+# private: it is what leaderboard submissions are scored against.
+secret_data.jsonl
+secret_dataset*
+secret_*
+*hidden*

autographql-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 NL2GraphQL Bench contributors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

autographql-0.1.0/PKG-INFO

@@ -0,0 +1,200 @@
+Metadata-Version: 2.5
+Name: autographql
+Version: 0.1.0
+Summary: Schema-driven generation of NL2GraphQL datasets from a GraphQL schema
+Project-URL: Homepage, https://nl2graphql-bench.github.io/
+Project-URL: Repository, https://github.com/nl2graphql-bench/generation
+Project-URL: Datasets, https://github.com/nl2graphql-bench/datasets
+Project-URL: Issues, https://github.com/nl2graphql-bench/generation/issues
+Author: Keya Battu, Parth Mehta, Harikrishnan Balagopal, Manish Kesarwani
+License-Expression: MIT
+License-File: LICENSE
+Keywords: benchmark,dataset-generation,graphql,nl2graphql,synthetic-data
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.9
+Requires-Dist: graphql-core<3.3,>=3.2
+Provides-Extra: datasets
+Requires-Dist: openpyxl>=3.1; extra == 'datasets'
+Requires-Dist: pandas>=2.0; extra == 'datasets'
+Provides-Extra: dev
+Requires-Dist: build>=1.0; extra == 'dev'
+Requires-Dist: pytest>=7; extra == 'dev'
+Requires-Dist: twine>=5.0; extra == 'dev'
+Provides-Extra: web
+Requires-Dist: fastapi>=0.100; extra == 'web'
+Requires-Dist: python-multipart>=0.0.6; extra == 'web'
+Requires-Dist: uvicorn[standard]>=0.22; extra == 'web'
+Description-Content-Type: text/markdown
+
+# AutoGraphQL
+
+[![EMNLP 2026 Industry Track](<https://img.shields.io/badge/EMNLP%202026-Industry%20Track-blue.svg>)](#)
+
+AutoGraphQL is a systematic, schema-driven framework for synthesizing GraphQL query datasets directly from GraphQL SDL schemas. It supports a broad range of GraphQL constructs, including fragments, inline fragments, directives, filters, pagination, aliases, and mutations, enabling the automated creation of diverse, executable datasets for fine-tuning LLMs and adapting them to domain or enterprise-specific schemas.
+
+Official implementation of our paper accepted at the **EMNLP 2026 Industry Track**.
+
+**[Paper](docs/autographql.pdf) | [Leaderboard](https://nl2graphql-bench.github.io/) | [Datasets](https://github.com/nl2graphql-bench/datasets) | [Index](https://github.com/nl2graphql-bench/index)**
+
+This is the **generation** component of NL2GraphQL Bench. The released
+train and public-test splits it produced are in
+[nl2graphql-bench/datasets](https://github.com/nl2graphql-bench/datasets);
+[nl2graphql-bench/index](https://github.com/nl2graphql-bench/index) links
+every component. Licensed MIT.
+
+## At a Glance
+
+- **17,621** NL2GraphQL instances
+- **173** GraphQL schemas
+- **7** query categories
+- Schema-disjoint training, public-test, and hidden-test splits
+- Automated schema and execution validation
+- Support for complex GraphQL constructs
+- Web interface for query generation and dataset creation
+
+## Framework
+
+AutoGraphQL takes a GraphQL SDL schema as input and systematically generates diverse GraphQL queries while enforcing schema validity and execution correctness. Generated queries can subsequently be paired with natural-language descriptions to construct NL2GraphQL datasets and evaluate language models.
+
+<p align="center">
+  <img src="docs/figures/toolkit.png" alt="AutoGraphQL framework overview" width="900"/>
+</p>
+
+<p align="center">
+  <em>Figure 1. Overview of the AutoGraphQL framework.</em>
+</p>
+
+The framework consists of the following main stages:
+
+1. **Schema Processing**: parses and analyzes the input GraphQL SDL schema.
+2. **Query Generation**: synthesizes queries across multiple GraphQL constructs and query categories.
+3. **Validation**: checks generated queries for schema validity and executable correctness.
+4. **Deduplication**: removes structurally redundant queries.
+5. **Dataset Construction**: organizes validated queries into datasets for downstream NL2GraphQL research.
+
+## Repository Structure
+
+```
+autographql/
+├── pyproject.toml          # packaging: deps, extras, console script
+├── src/autographql/        # the package
+│   ├── query_generator_app.py   # GraphQLQueryGeneratorApp, the entry API
+│   ├── cli.py                   # autographql-generate
+│   ├── generators/              # one generator per query category
+│   └── utils/                   # schema introspection, variable generation
+├── schemas/                # GraphQL schemas used for generation
+├── docs/
+│   ├── autographql.pdf     # Paper
+│   └── figures/
+│       └── toolkit.png     # Framework overview
+└── website/                # Dataset Generator and Dataset Explorer UI
+```
+
+## The interactive UI
+
+`website/` is a FastAPI backend and a Next.js frontend serving two views:
+
+- **Dataset Generator** — pick or upload `.graphql` schemas, choose categories,
+  queries per category and max hops, then generate. Each query is validated
+  against the schema and by executing it, and deduplicated by canonical hash.
+- **Dataset Explorer** — browse what came out by split, schema and category, and
+  inspect the natural-language utterance, the query, its variables and the
+  schema side by side.
+
+This is where validation happens: it is part of this framework rather than a
+separate component.
+
+## Install
+
+```bash
+pip install -e .
+```
+
+Add extras as needed: `.[datasets]` to write xlsx, `.[web]` for the UI,
+`.[dev]` for the build and test tools.
+
+## Use as a library
+
+```python
+from autographql import GraphQLQueryGeneratorApp
+```
+
+## Generate from the command line
+
+```bash
+autographql-generate --schema schemas/academic/index.graphql \
+                     --category aliases --count 10 --max-hops 2
+```
+
+`--category` takes any of aliases, directives, external_fragments,
+inline_fragments, filters, pagination, mutations, or `all`. Output is written to
+`generated_queries/<schema>/`.
+
+## Running the UI locally
+
+### Backend
+
+```bash
+python3 -m venv venv
+source venv/bin/activate
+pip install -e ".[web,datasets]"
+uvicorn website.backend.main:app --reload --port 8000
+```
+
+### Frontend
+
+```bash
+cd website/frontend
+npm install
+npm run dev
+```
+
+Open `http://localhost:3000`.
+
+### CLI
+
+```bash
+source venv/bin/activate
+autographql-generate --schema schemas/academic/index.graphql --category all --count 5
+```
+
+## Datasets
+
+The training corpus (9118 NL2GraphQL instances) and the schema-disjoint public benchmark test set (6403 instances) are available for download at`datasets/`.
+
+## Citation
+
+Please cite the repo if you think our work is helpful to you.
+
+```bibtex
+@inproceedings{autographql2026,
+  title={},
+  author={},
+  booktitle={},
+  year={2026}
+}
+```
+
+## License
+
+MIT License
+
+## Publishing
+
+```bash
+pip install build twine
+python -m build
+twine check dist/*
+twine upload dist/*
+```
+
+Version lives in `pyproject.toml` and `src/autographql/__init__.py`; bump both.

autographql-0.1.0/README.md

@@ -0,0 +1,163 @@
+# AutoGraphQL
+
+[![EMNLP 2026 Industry Track](<https://img.shields.io/badge/EMNLP%202026-Industry%20Track-blue.svg>)](#)
+
+AutoGraphQL is a systematic, schema-driven framework for synthesizing GraphQL query datasets directly from GraphQL SDL schemas. It supports a broad range of GraphQL constructs, including fragments, inline fragments, directives, filters, pagination, aliases, and mutations, enabling the automated creation of diverse, executable datasets for fine-tuning LLMs and adapting them to domain or enterprise-specific schemas.
+
+Official implementation of our paper accepted at the **EMNLP 2026 Industry Track**.
+
+**[Paper](docs/autographql.pdf) | [Leaderboard](https://nl2graphql-bench.github.io/) | [Datasets](https://github.com/nl2graphql-bench/datasets) | [Index](https://github.com/nl2graphql-bench/index)**
+
+This is the **generation** component of NL2GraphQL Bench. The released
+train and public-test splits it produced are in
+[nl2graphql-bench/datasets](https://github.com/nl2graphql-bench/datasets);
+[nl2graphql-bench/index](https://github.com/nl2graphql-bench/index) links
+every component. Licensed MIT.
+
+## At a Glance
+
+- **17,621** NL2GraphQL instances
+- **173** GraphQL schemas
+- **7** query categories
+- Schema-disjoint training, public-test, and hidden-test splits
+- Automated schema and execution validation
+- Support for complex GraphQL constructs
+- Web interface for query generation and dataset creation
+
+## Framework
+
+AutoGraphQL takes a GraphQL SDL schema as input and systematically generates diverse GraphQL queries while enforcing schema validity and execution correctness. Generated queries can subsequently be paired with natural-language descriptions to construct NL2GraphQL datasets and evaluate language models.
+
+<p align="center">
+  <img src="docs/figures/toolkit.png" alt="AutoGraphQL framework overview" width="900"/>
+</p>
+
+<p align="center">
+  <em>Figure 1. Overview of the AutoGraphQL framework.</em>
+</p>
+
+The framework consists of the following main stages:
+
+1. **Schema Processing**: parses and analyzes the input GraphQL SDL schema.
+2. **Query Generation**: synthesizes queries across multiple GraphQL constructs and query categories.
+3. **Validation**: checks generated queries for schema validity and executable correctness.
+4. **Deduplication**: removes structurally redundant queries.
+5. **Dataset Construction**: organizes validated queries into datasets for downstream NL2GraphQL research.
+
+## Repository Structure
+
+```
+autographql/
+├── pyproject.toml          # packaging: deps, extras, console script
+├── src/autographql/        # the package
+│   ├── query_generator_app.py   # GraphQLQueryGeneratorApp, the entry API
+│   ├── cli.py                   # autographql-generate
+│   ├── generators/              # one generator per query category
+│   └── utils/                   # schema introspection, variable generation
+├── schemas/                # GraphQL schemas used for generation
+├── docs/
+│   ├── autographql.pdf     # Paper
+│   └── figures/
+│       └── toolkit.png     # Framework overview
+└── website/                # Dataset Generator and Dataset Explorer UI
+```
+
+## The interactive UI
+
+`website/` is a FastAPI backend and a Next.js frontend serving two views:
+
+- **Dataset Generator** — pick or upload `.graphql` schemas, choose categories,
+  queries per category and max hops, then generate. Each query is validated
+  against the schema and by executing it, and deduplicated by canonical hash.
+- **Dataset Explorer** — browse what came out by split, schema and category, and
+  inspect the natural-language utterance, the query, its variables and the
+  schema side by side.
+
+This is where validation happens: it is part of this framework rather than a
+separate component.
+
+## Install
+
+```bash
+pip install -e .
+```
+
+Add extras as needed: `.[datasets]` to write xlsx, `.[web]` for the UI,
+`.[dev]` for the build and test tools.
+
+## Use as a library
+
+```python
+from autographql import GraphQLQueryGeneratorApp
+```
+
+## Generate from the command line
+
+```bash
+autographql-generate --schema schemas/academic/index.graphql \
+                     --category aliases --count 10 --max-hops 2
+```
+
+`--category` takes any of aliases, directives, external_fragments,
+inline_fragments, filters, pagination, mutations, or `all`. Output is written to
+`generated_queries/<schema>/`.
+
+## Running the UI locally
+
+### Backend
+
+```bash
+python3 -m venv venv
+source venv/bin/activate
+pip install -e ".[web,datasets]"
+uvicorn website.backend.main:app --reload --port 8000
+```
+
+### Frontend
+
+```bash
+cd website/frontend
+npm install
+npm run dev
+```
+
+Open `http://localhost:3000`.
+
+### CLI
+
+```bash
+source venv/bin/activate
+autographql-generate --schema schemas/academic/index.graphql --category all --count 5
+```
+
+## Datasets
+
+The training corpus (9118 NL2GraphQL instances) and the schema-disjoint public benchmark test set (6403 instances) are available for download at`datasets/`.
+
+## Citation
+
+Please cite the repo if you think our work is helpful to you.
+
+```bibtex
+@inproceedings{autographql2026,
+  title={},
+  author={},
+  booktitle={},
+  year={2026}
+}
+```
+
+## License
+
+MIT License
+
+## Publishing
+
+```bash
+pip install build twine
+python -m build
+twine check dist/*
+twine upload dist/*
+```
+
+Version lives in `pyproject.toml` and `src/autographql/__init__.py`; bump both.

autographql-0.1.0/pyproject.toml

@@ -0,0 +1,70 @@
+[build-system]
+requires = ["hatchling>=1.21", "hatch-vcs>=0.4"]
+build-backend = "hatchling.build"
+
+[project]
+name = "autographql"
+# Version comes from the git tag via hatch-vcs, so a release cannot publish a
+# number that disagrees with the tag it was cut from. Do not hardcode it here.
+dynamic = ["version"]
+description = "Schema-driven generation of NL2GraphQL datasets from a GraphQL schema"
+readme = "README.md"
+requires-python = ">=3.9"
+license = "MIT"
+license-files = ["LICENSE"]
+authors = [
+  { name = "Keya Battu" },
+  { name = "Parth Mehta" },
+  { name = "Harikrishnan Balagopal" },
+  { name = "Manish Kesarwani" },
+]
+keywords = ["graphql", "nl2graphql", "dataset-generation", "synthetic-data", "benchmark"]
+classifiers = [
+  "Development Status :: 4 - Beta",
+  "Intended Audience :: Science/Research",
+  "License :: OSI Approved :: MIT License",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.9",
+  "Programming Language :: Python :: 3.10",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Scientific/Engineering :: Artificial Intelligence",
+]
+dependencies = [
+  # Schema parsing and query construction. Pinned below 3.3: from 3.3 a node's
+  # `directives` is None when absent where 3.2 returned [], which breaks AST
+  # walking shared with the evaluation package.
+  "graphql-core>=3.2,<3.3",
+]
+
+[project.optional-dependencies]
+# Writing generated datasets to xlsx.
+datasets = ["pandas>=2.0", "openpyxl>=3.1"]
+# The Dataset Generator and Dataset Explorer UI under website/.
+web = ["fastapi>=0.100", "uvicorn[standard]>=0.22", "python-multipart>=0.0.6"]
+dev = ["pytest>=7", "build>=1.0", "twine>=5.0"]
+
+[project.urls]
+Homepage = "https://nl2graphql-bench.github.io/"
+Repository = "https://github.com/nl2graphql-bench/generation"
+Datasets = "https://github.com/nl2graphql-bench/datasets"
+Issues = "https://github.com/nl2graphql-bench/generation/issues"
+
+[project.scripts]
+autographql-generate = "autographql.cli:main"
+
+[tool.hatch.version]
+source = "vcs"
+# Tags are v-prefixed: v0.1.0 -> 0.1.0
+tag-pattern = "v(?P<version>.+)"
+
+[tool.hatch.build.hooks.vcs]
+# Generated at build time; the package reads its version from here.
+version-file = "src/autographql/_version.py"
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/autographql"]
+
+[tool.hatch.build.targets.sdist]
+include = ["src/autographql", "README.md", "LICENSE", "pyproject.toml"]