Initial commit

.gitignore

@@ -0,0 +1,161 @@
+### Python template
+# 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/

.pre-commit-config.yaml

@@ -0,0 +1,72 @@
+repos:
+  # general checks (see here: https://pre-commit.com/hooks.html)
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    hooks:
+      - id: check-yaml
+        args: [--allow-multiple-documents]
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+
+  # ruff - linting + formatting
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: "v0.4.9"
+    hooks:
+      - id: ruff
+        name: ruff
+      - id: ruff-format
+        name: ruff-format
+
+  # mypy - lint-like type checking
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.10.0
+    hooks:
+      - id: mypy
+        name: mypy
+
+  # docformatter - formats docstrings to follow PEP 257
+  - repo: https://github.com/pycqa/docformatter
+    rev: v1.7.5
+    hooks:
+      - id: docformatter
+        name: docformatter
+        args:
+          [
+            -r,
+            -i,
+            --pre-summary-newline,
+            --make-summary-multi-line,
+            --wrap-summaries,
+            "120",
+            --wrap-descriptions,
+            "120",
+            medirag,
+            tests,
+          ]
+
+  # bandit - find common security issues
+  - repo: https://github.com/pycqa/bandit
+    rev: 1.7.9
+    hooks:
+      - id: bandit
+        name: bandit
+        exclude: ^tests/
+        args:
+          - -r
+          - medirag
+
+  #  - repo: local
+  #    hooks:
+  #      - id: pytest
+  #        name: pytest
+  #        entry: poetry run pytest --cov=medirag tests
+  #        language: system
+  #        types: [python]
+  #        pass_filenames: false
+
+  # prettier - formatting JS, CSS, JSON, Markdown, ...
+  - repo: https://github.com/pre-commit/mirrors-prettier
+    rev: v3.1.0
+    hooks:
+      - id: prettier
+        exclude: ^poetry.lock

pyproject.toml

@@ -0,0 +1,41 @@
+[tool.poetry]
+name = "medirag"
+version = "0.1.0"
+description = ""
+authors = ["Alvin Henrick <[email protected]>"]
+readme = "README.md"
+
+[tool.poetry.dependencies]
+python = "^3.10"
+llama-index = "^0.10.62"
+llama-index-vector-stores-faiss = "^0.1.2"
+llama-index-embeddings-huggingface = "^0.2.2"
+beautifulsoup4 = "^4.12.3"
+lxml = "^5.2.2"
+langchain = "^0.2.12"
+faiss-cpu = "^1.8.0.post1"
+sentence-transformers = "^3.0.1"
+
+
+[tool.poetry.group.dev.dependencies]
+pytest = "^8.3.2"
+pre-commit = "^3.8.0"
+pytest-cov = "^5.0.0"
+
+
+[tool.ruff]
+extend-exclude = [
+    "__pycache__",
+    "build",
+    "dist",
+]
+# Same as Black.
+line-length = 120
+
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+[tool.pytest.ini_options]
+addopts = "-vvv"
+testpaths = "tests"