Initialize Imara project

This project showcases GenAI application development in Google Cloud.

.cloudbuild/cloudbuild.yaml

@@ -0,0 +1,103 @@
+# Copyright 2024 Google LLC
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#      http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+substitutions:
+  _GCS_BUCKET: gs://rlhf-artifacts
+  _PIPELINE_REGISTRY: rlhf-pipelines
+  _REGION: us-central1
+
+steps:
+  - id: install requirements
+    name: python:3.11
+    entrypoint: bash
+    args:
+    - -c
+    - |
+      python -m pip install -U -r requirements.txt --user
+
+  - id: run unit tests
+    name: python:3.11
+    entrypoint: bash
+    args:
+    - -c
+    - |
+      python -m pytest
+
+  - id: copy data to bucket
+    name: gcr.io/cloud-builders/gsutil
+    entrypoint: bash
+    args:
+    - -c
+    - |
+      gsutil cp -r data ${_GCS_BUCKET}
+
+  - id: compile tuning pipeline
+    name: python:3.11
+    entrypoint: python
+    args:
+    - -c
+    - |
+      from kfp import compiler
+      from pkg.tuner import rlhf, metadata
+
+      compiler.Compiler().compile(
+        pipeline_func=rlhf.tune, package_path=metadata.COMPILED_PIPELINE_PATH
+      )
+
+  - id: upload tuning pipeline
+    name: python:3.11
+    entrypoint: python
+    args:
+    - -c
+    - |
+      from pkg.tuner import registry, metadata
+
+      registry.upload(
+        project_id='${PROJECT_ID}',
+        region='${_REGION}',
+        pipeline_registry='${_PIPELINE_REGISTRY}',
+        compiled_pipeline_path=metadata.COMPILED_PIPELINE_PATH
+      )
+
+  - id: tune foundation model
+    name: python:3.11
+    entrypoint: python
+    args:
+    - -c
+    - |
+      import google.cloud.aiplatform as aiplatform
+      from pkg.tuner import steps, registry, metadata, parameters
+
+      REWARD_MODEL_TRAIN_STEPS = steps.get_reward_model_train_steps()
+      REINFORCEMENT_LEARNING_TRAIN_STEPS = steps.get_reinforcement_learning_train_steps()
+      PIPELINE_TEMPLATE_URI = 'https://${_REGION}-kfp.pkg.dev/$PROJECT_ID/${_PIPELINE_REGISTRY}/rlhf-tune-pipeline/latest'
+    
+      job = aiplatform.PipelineJob(
+          display_name=metadata.MODEL_DISPLAY_NAME,
+          pipeline_root=metadata.PIPELINE_ROOT,
+          template_path=PIPELINE_TEMPLATE_URI,
+          parameter_values=parameters.get_values(
+              preference_dataset=metadata.PREFERENCE_DATASET,
+              prompt_dataset=metadata.PROMPT_DATASET,
+              eval_dataset=metadata.EVALUATION_DATASET,
+              reward_model_train_steps=REWARD_MODEL_TRAIN_STEPS,
+              reinforcement_learning_train_steps=REINFORCEMENT_LEARNING_TRAIN_STEPS
+          )
+      )
+
+      job.run()
+
+  #...add cloud deploy steps
+
+timeout: 86400s

.github/workflows/hello.yaml

@@ -0,0 +1,18 @@
+name: GitHub Actions Demo
+run-name: ${{ github.actor }} is testing out GitHub Actions 🚀
+on: [push]
+jobs:
+  Explore-GitHub-Actions:
+    runs-on: ubuntu-latest
+    steps:
+      - run: echo "🎉 The job was automatically triggered by a ${{ github.event_name }} event."
+      - run: echo "🐧 This job is now running on a ${{ runner.os }} server hosted by GitHub!"
+      - run: echo "🔎 The name of your branch is ${{ github.ref }} and your repository is ${{ github.repository }}."
+      - name: Check out repository code
+        uses: actions/checkout@v4
+      - run: echo "💡 The ${{ github.repository }} repository has been cloned to the runner."
+      - run: echo "🖥️ The workflow is now ready to test your code on the runner."
+      - name: List files in the repository
+        run: |
+          ls ${{ github.workspace }}
+      - run: echo "🍏 This job's status is ${{ job.status }}."

.gitignore

@@ -0,0 +1,160 @@
+# 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/