adds pdf-loader example

Author: edublancas

examples/flask/pdf-loader/.gitignore

@@ -0,0 +1,4 @@
+.env
+*.json
+*.db
+*.pdf

examples/flask/pdf-loader/Dockerfile

@@ -0,0 +1,45 @@
+# NOTE: could not get sqlite-vec to work on arm64
+# --platform=linux/amd64
+FROM python:3.12-slim
+
+WORKDIR /app
+
+# install pre-requisites
+RUN apt-get update && \
+    apt-get install -y \
+    supervisor \
+    && rm -rf /var/lib/apt/lists/*
+
+
+# install rabbitmq
+RUN apt-get update && \
+    apt-get install -y rabbitmq-server && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN python -m venv /venvs/app
+
+RUN /venvs/app/bin/pip install torch==2.5.1 torchvision==0.20.1 --index-url https://download.pytorch.org/whl/cpu
+
+COPY requirements.txt /app/requirements.txt
+RUN /venvs/app/bin/pip install -r /app/requirements.txt
+
+
+COPY pdf-loader/ /app/pdf-loader
+RUN /venvs/app/bin/pip install --editable /app/pdf-loader
+
+COPY settings.py /app/settings.py
+COPY entrypoint.py /app/entrypoint.py
+COPY supervisord.conf /etc/supervisord.conf
+
+# create tables
+RUN /venvs/app/bin/python -m pdf_loader.db
+
+# download models
+RUN /venvs/app/bin/python -m pdf_loader.background
+
+EXPOSE 80
+
+CMD ["/usr/bin/supervisord", "-c", "/etc/supervisord.conf"]
+
+
+

examples/flask/pdf-loader/README.md

@@ -0,0 +1,43 @@
+# PDF loader
+
+An app to parse and search over PDFs.
+
+```sh
+# create the environment and install the required dependencies
+conda create --name pdf-loader python=3.12 rabbitmq-server -c conda-forge -y
+
+# activate environment
+conda activate pdf-loader
+
+# install torch cpu
+pip install torch torchvision --index-url https://download.pytorch.org/whl/cpu
+
+
+# install the package and requirements
+pip install --editable pdf-loader
+pip install -r requirements.txt
+
+# create tables
+python -m pdf_loader.db
+
+# start app
+python -m pdf_loader.app
+# open: http://localhost:5000
+
+# to start celery
+rabbitmq-server
+
+celery --app pdf_loader.background worker --loglevel=INFO --pool=prefork --concurrency=1
+```
+
+With Docker:
+
+```sh
+docker build -t pdf-loader .
+
+# http://localhost:5000
+docker run -p 5000:80 --env-file .env pdf-loader
+
+docker run -it pdf-loader bash
+```
+

examples/flask/pdf-loader/entrypoint.py

@@ -0,0 +1 @@
+from pdf_loader.app import app

examples/flask/pdf-loader/pdf-loader/.gitignore

@@ -0,0 +1,139 @@
+# documentation builds
+doc/_build
+
+# vscode stuff
+.vscode
+.virtual_documents
+
+# macOS files
+.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/
+pip-wheel-metadata/
+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/
+
+# 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
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+.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
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__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/

examples/flask/pdf-loader/pdf-loader/MANIFEST.in

@@ -0,0 +1,7 @@
+# use this file if you wish to include non-python files
+# reference: https://packaging.python.org/en/latest/guides/using-manifest-in/
+include CHANGELOG.md
+include README.md
+graft src/pdf_loader/assets
+global-exclude __pycache__
+global-exclude *.py[co]

examples/flask/pdf-loader/pdf-loader/pyproject.toml

@@ -0,0 +1,2 @@
+[tool.pytest.ini_options]
+addopts = "--pdbcls=IPython.terminal.debugger:Pdb"

examples/flask/pdf-loader/pdf-loader/setup.cfg

@@ -0,0 +1,7 @@
+[metadata]
+description-file = README.md
+
+[flake8]
+max-line-length = 88
+extend-ignore = E203
+extend-exclude = build,node_modules

examples/flask/pdf-loader/pdf-loader/setup.py

@@ -0,0 +1,46 @@
+import re
+import ast
+from glob import glob
+from os.path import basename, splitext
+
+from setuptools import find_packages
+from setuptools import setup
+
+_version_re = re.compile(r"__version__\s+=\s+(.*)")
+
+with open("src/pdf_loader/__init__.py", "rb") as f:
+    VERSION = str(
+        ast.literal_eval(_version_re.search(f.read().decode("utf-8")).group(1))
+    )
+
+REQUIRES = []
+
+DEV = [
+    "pytest",
+    "flake8",
+    "invoke",
+    "twine",
+]
+
+setup(
+    name="pdf-loader",
+    version=VERSION,
+    description=None,
+    license=None,
+    author=None,
+    author_email=None,
+    url=None,
+    packages=find_packages("src"),
+    package_dir={"": "src"},
+    py_modules=[splitext(basename(path))[0] for path in glob("src/*.py")],
+    include_package_data=True,
+    classifiers=[],
+    keywords=[],
+    install_requires=REQUIRES,
+    extras_require={
+        "dev": DEV,
+    },
+    entry_points={
+        # 'console_scripts': ['pdf-loader=pdf_loader.cli:cli'],
+    },
+)

examples/flask/pdf-loader/pdf-loader/src/pdf_loader/__init__.py

@@ -0,0 +1,5 @@
+from pdf_loader._settings import Settings
+
+SETTINGS = Settings()
+
+__version__ = "0.1dev"