Initial commit

.gitignore

@@ -0,0 +1,162 @@
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.11
+
+ENV PYTHONUNBUFFERED=1
+
+ARG BUILD_ENVIRONMENT=dev
+
+WORKDIR /gaianet_rag_api_pipeline
+
+COPY requirements-common.txt requirements-common.txt
+COPY requirements-${BUILD_ENVIRONMENT}.txt requirements-${BUILD_ENVIRONMENT}.txt
+RUN pip install --no-cache-dir --upgrade -r /gaianet_rag_api_pipeline/requirements-${BUILD_ENVIRONMENT}.txt
+
+COPY . .
+CMD ["python", "run.py"]

README.md

@@ -0,0 +1,41 @@
+# GaiaNet RAG API Pipeline
+
+## System Requirements
+
+- Python 3.11.x
+
+## Local development
+
+Start with building your containers: `docker compose -f local.yml build`.
+
+You are ready to start developing your application!
+Define your custom logic in `gaianet_rag_api_pipeline/pipeline.py`. It already contains a sample code which sums all the input values.
+
+You can test it in the following modes:
+
+- [debug (batch mode)] run your Pathway app code with pytest with `docker compose -f local.yml run --rm pathway_app pytest`
+- [streaming] run your Pathway app `docker compose -f local.yml up`. Modify `InfiniteStream` in `gaianet_rag_api_pipeline/input.py` to feed it with different data. The results are streamed to the `output.csv` file (you can change this in `gaianet_rag_api_pipeline/output.py`)
+
+## Production environment
+
+Production environment streams data from `redpanda`.
+Build production containers with `docker compose -f prod.yml build`
+
+To run your application invoke:
+1. `docker compose -f prod.yml rm -svf` to clean the state so that `redpanda` can start without issues
+2. `docker compose -f prod.yml up`
+
+For test, you can push messages to redpanda by running
+`docker compose -f prod.yml exec redpanda rpk topic create gaianet_rag_api_pipeline` to make sure the topic is created
+and then `docker compose -f prod.yml exec redpanda rpk topic produce gaianet_rag_api_pipeline`
+
+and typing in the messages, e.g:
+`{"value":10}`
+
+
+## Configuration
+
+Supply configuration with environment variables.
+
+For ease of development, you can also use dotenv file in `config/.env` to specify configuration.
+Note that environment variables will take precedence over any configuration specified in `config/.env` file.