Add address parser app

.gitignore

@@ -0,0 +1,173 @@
+data/
+data*/
+_data/
+_data*/
+.joblib_cache/
+.joblib_cache*/
+
+.idea/
+.vscode/
+log/
+*.log
+.DS_Store
+
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$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
+.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
+
+# 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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.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
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs 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/

Makefile

@@ -0,0 +1,33 @@
+venv:
+	python3 -m venv .venv
+	source .venv/bin/activate ; pip install --upgrade pip ; python3 -m pip install -r requirements-dev.txt
+	source .venv/bin/activate ; pip freeze > requirements_freeze.txt
+
+which-python:
+	source .venv/bin/activate ; which python
+
+clean:
+	rm -rf .venv
+
+run:
+	source .venv/bin/activate ; python address_parser.py
+
+black-check:
+	source .venv/bin/activate ; black . --check --verbose --line-length 120
+
+black:
+	source .venv/bin/activate ; black . --line-length 120
+
+ruff-check:
+	source .venv/bin/activate ; ruff check .
+
+ruff:
+	source .venv/bin/activate ; ruff check . --fix
+
+test:
+	source .venv/bin/activate ; PYTHONPATH='./src' pytest -vv --capture=no tests
+
+.DEFAULT_GOAL := help
+.PHONY: help
+help:
+	@LC_ALL=C $(MAKE) -pRrq -f $(lastword $(MAKEFILE_LIST)) : 2>/dev/null | awk -v RS= -F: '/^# File/,/^# Finished Make data base/ {if ($$1 !~ "^[#.]") {print $$1}}' | sort | egrep -v -e '^[^[:alnum:]]' -e '^$@$$'

address_parser.py

@@ -0,0 +1,87 @@
+import torch
+from transformers import pipeline
+import gradio as gr
+import json
+
+# Initialize model pipeline
+model_id = "dylanhogg/gnaf-structured-address-v0.1-75a1791-20250921-063650"
+
+pipe = pipeline(
+    "text-generation",
+    model=model_id,
+    dtype=torch.bfloat16,
+    device_map="auto",
+)
+
+
+def parse_address(user_address: str) -> tuple[str, str]:
+    """Parse address and return both raw response and JSON"""
+    user_content = f"Translate a text address into structured json.\n{user_address}"
+    messages = [
+        {"role": "system", "content": "Translate a text address into structured json."},
+        {"role": "user", "content": user_content},
+    ]
+
+    outputs = pipe(
+        messages,
+        max_new_tokens=256,
+        do_sample=False,
+    )
+
+    response = outputs[0]["generated_text"]
+    last_content = response[-1]["content"]
+
+    # Try to extract JSON from the response
+    try:
+        # Find first '{' and last '}' to extract JSON
+        start = last_content.find("{")
+        end = last_content.rfind("}") + 1
+        if start != -1 and end > start:
+            json_str = last_content[start:end]
+            parsed = json.loads(json_str)
+            formatted_json = json.dumps(parsed, indent=2)
+        else:
+            formatted_json = "No JSON found in response"
+    except Exception as e:
+        formatted_json = f"Error parsing JSON: {str(e)}\n\nRaw output:\n{last_content}"
+
+    return formatted_json, last_content
+
+
+# Create Gradio interface
+with gr.Blocks(title="Address Parser") as demo:
+    gr.Markdown("# 🏠 Structured Address Parser")
+    gr.Markdown("This model converts text addresses into structured JSON format.")
+
+    with gr.Row():
+        with gr.Column():
+            input_text = gr.Textbox(
+                label="Input Address", placeholder="Enter an address...", value="48a Pirrama Rd Pyrmont NSW 2009"
+            )
+            submit_btn = gr.Button("Parse Address", variant="primary")
+
+        with gr.Column():
+            json_output = gr.Textbox(label="Structured JSON", interactive=False, lines=10)
+            raw_output = gr.Textbox(label="Raw Model Output", interactive=False, lines=5)
+
+    # Examples
+    gr.Examples(
+        examples=[
+            "48a Pirrama Rd Pyrmont NSW 2009",
+            "Floor 3, 152-156 Clarence St, Sydney NSW 2000",
+            "Aptt 16, 400 Bondi Rd, Bondi NSW 2026",
+            "Unit 18/14-18 Flood St, Bondi, NSW 2026",
+            "Lvl 15/333 George St Sydney NSW 2000",
+            "Check out: 44 Ulm St, Maroubra NSW 2035",
+            "44 Ulm St, Maroubra NSW 2035 is where it's at!",
+        ],
+        inputs=input_text,
+    )
+
+    # Handle events
+    submit_btn.click(fn=parse_address, inputs=input_text, outputs=[json_output, raw_output])
+    input_text.submit(fn=parse_address, inputs=input_text, outputs=[json_output, raw_output])
+
+# Launch the app
+if __name__ == "__main__":
+    demo.launch()

requirements-dev.txt

@@ -0,0 +1,4 @@
+-r requirements.txt
+pytest
+black
+ruff

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+transformers
+torch
+accelerate

requirements_freeze.txt

@@ -0,0 +1,75 @@
+accelerate==1.10.1
+aiofiles==24.1.0
+annotated-types==0.7.0
+anyio==4.11.0
+audioop-lts==0.2.2
+black==25.9.0
+Brotli==1.1.0
+certifi==2025.10.5
+charset-normalizer==3.4.4
+click==8.3.0
+fastapi==0.119.0
+ffmpy==0.6.3
+filelock==3.20.0
+fsspec==2025.9.0
+gradio==5.49.1
+gradio_client==1.13.3
+groovy==0.1.2
+h11==0.16.0
+hf-xet==1.1.10
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.35.3
+idna==3.11
+iniconfig==2.1.0
+Jinja2==3.1.6
+markdown-it-py==4.0.0
+MarkupSafe==3.0.3
+mdurl==0.1.2
+mpmath==1.3.0
+mypy_extensions==1.1.0
+networkx==3.5
+numpy==2.3.4
+orjson==3.11.3
+packaging==25.0
+pandas==2.3.3
+pathspec==0.12.1
+pillow==11.3.0
+platformdirs==4.5.0
+pluggy==1.6.0
+psutil==7.1.0
+pydantic==2.11.10
+pydantic_core==2.33.2
+pydub==0.25.1
+Pygments==2.19.2
+pytest==8.4.2
+python-dateutil==2.9.0.post0
+python-multipart==0.0.20
+pytokens==0.2.0
+pytz==2025.2
+PyYAML==6.0.3
+regex==2025.9.18
+requests==2.32.5
+rich==14.2.0
+ruff==0.14.1
+safehttpx==0.1.6
+safetensors==0.6.2
+semantic-version==2.10.0
+setuptools==80.9.0
+shellingham==1.5.4
+six==1.17.0
+sniffio==1.3.1
+starlette==0.48.0
+sympy==1.14.0
+tokenizers==0.22.1
+tomlkit==0.13.3
+torch==2.9.0
+tqdm==4.67.1
+transformers==4.57.1
+typer==0.19.2
+typing-inspection==0.4.2
+typing_extensions==4.15.0
+tzdata==2025.2
+urllib3==2.5.0
+uvicorn==0.37.0
+websockets==15.0.1