feat: add e2e gen ai app starter kit

.github/CODEOWNERS

@@ -73,3 +73,4 @@
 /generative-ai/open-models/serving/vertex_ai_text_generation_inference_gemma.ipynb  @alvarobartt @philschmid @pagezyhf @jeffboudier
 /generative-ai/gemini/use-cases/applying-llms-to-data/semantic-search-in-bigquery/stackoverflow_questions_semantic_search.ipynb     @sethijaideep @GoogleCloudPlatform/generative-ai-devrel
 /generative-ai/gemini/use-cases/retrieval-augmented-generation/raw_with_bigquery.ipynb @jeffonelson @GoogleCloudPlatform/generative-ai-devrel
+/generative-ai/gemini/sample-apps/e2e-gen-ai-app-starter-kit       @eliasecchig @lspatarog @GoogleCloudPlatform/generative-ai-devrel

.github/actions/spelling/allow.txt

@@ -144,6 +144,7 @@ Kohli
 Kraizt
 Kubeflow
 Kudrow
+LangGraph
 LCEL
 LLMs
 LOOKBACK
@@ -202,6 +203,7 @@ Oort
 PDFs
 PEFT
 PLOTLYENV
+PYINK
 Parmar
 Persero
 Phaidon
@@ -270,6 +272,7 @@ Testables
 Tetsuo
 Tianli
 Topolino
+Traceloop
 Trapp
 Tribbiani
 Tricyle
@@ -360,13 +363,15 @@ cfbundle
 chatbots
 chromadb
 claude
+cicd
 clickable
 cmap
 codebase
 codebases
 codefile
 codelab
 codelabs
+codespell
 colab
 coldline
 coloraxis
@@ -473,6 +478,7 @@ gsutil
 gtk
 guanciale
 gunicorn
+hadolint
 hashtag
 hashtags
 hdlr
@@ -671,19 +677,23 @@ sxs
 tabular
 tagline
 tencel
+terraform
 termcolor
 terraform
 textno
 tfhub
 tfidf
+tfvars
 tgz
 thelook
 tiktoken
 timechart
 titlebar
 tobytes
 toself
+toset
 tqdm
+traceloop
 tritan
 tsv
 ubuntu
@@ -698,6 +708,7 @@ usernames
 uvb
 uvicorn
 vapo
+uvicorn
 vectordb
 vertexai
 vesselin

.github/workflows/_e2e_gen_ai_app_starter_kit__lint_and_test.yaml

@@ -0,0 +1,35 @@
+name: Conversational Gen AI template - Lint and Test
+
+on:
+  push:
+    paths:
+      - "gemini/sample-apps/e2e-gen-ai-app-starter-kit/**"
+  pull_request:
+    paths:
+      - "gemini/sample-apps/e2e-gen-ai-app-starter-kit/**"
+
+jobs:
+  lint-and-test:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        working-directory: gemini/sample-apps/e2e-gen-ai-app-starter-kit
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.10"
+      - name: Install Poetry and dependencies
+        run: |
+          pip install poetry==1.8.3 --user
+          python -m poetry install --with lint,streamlit
+      - name: Lint python code
+        run: |
+          poetry run codespell
+          poetry run ruff .
+          poetry run mypy .
+          poetry run black . --check
+      - name: Run tests
+        run: |
+          poetry run pytest tests/unit

.github/workflows/linter.yaml

@@ -52,7 +52,7 @@ jobs:
         env:
           DEFAULT_BRANCH: main
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-          FILTER_REGEX_EXCLUDE: 'gemini/sample-apps/finance-advisor-spanner/.*\.sql'
+          FILTER_REGEX_EXCLUDE: 'gemini/sample-apps/finance-advisor-spanner/.*\.sql|gemini/sample-apps/e2e-gen-ai-app-starter-kit/.*'
           JAVASCRIPT_DEFAULT_STYLE: prettier
           LOG_LEVEL: WARN
           SHELLCHECK_OPTS: -e SC1091 -e 2086

.gitignore

@@ -144,6 +144,7 @@ dmypy.json
 # User-specific files
 language/examples/prompt-design/train.csv
 README-TOC*.md
+gemini/sample-apps/e2e-gen-ai-app-starter-kit/deployment/terraform/terraform.tfstate*
 
 .terraform*
 .Terraform*

gemini/sample-apps/README.md

@@ -13,6 +13,7 @@
 | Description                                                                                                                                                                                                                                                                                                                                                                                                                              | Application Name                                       | Technologies Used                                                          |
 | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------ | -------------------------------------------------------------------------- |
 | Develop a Gemini application using [Streamlit](https://streamlit.io/) framework and Vertex AI Gemini API model.                                                                                                                                                                                                                                                                                                                          | [gemini-streamlit-cloudrun](gemini-streamlit-cloudrun) | Cloud Run, Streamlit, Python                                               |
 | Deploy a RAG + Gemini sample application to troubleshoot your car using the owner's manual.                                                                                                                                                                                                                                                                                                                                              | [fixmycar/](fixmycar/)                                 | Chat, Grounding, RAG, Java, Streamlit                                      |
 | Try Gemini image recognition in `bash` and see Text-to-Speech read the description to you in ~any language. All from CLI!                                                                                                                                                                                                                                                                                                                | [image-bash-jam/](image-bash-jam/)                     | Text-to-Speech, Bash                                                       |
 | This demo showcases how you can combine the data and documents you already have and the skills you already know with the power of [AlloyDB AI](https://cloud.google.com/alloydb/ai?hl=en), [Vertex AI](https://cloud.google.com/vertex-ai?hl=en), [Cloud Run](https://cloud.google.com/run?hl=en), and [Cloud Functions](https://cloud.google.com/functions?hl=en) to build trustworthy Gen AI features into your existing applications. | [GenWealth](genwealth/)                                | Vertex AI, AlloyDB, Document AI, Cloud Run, Cloud Functions, Cloud Storage |
+| E2E Gen AI App Starter kit: This folder provides a template starter kit for building a Generative AI application on Google Cloud. We provide a comprehensive set of resources to guide you through the entire development process, from prototype to production.                                                                                                                     | [e2e-gen-ai-app-starter-kit](e2e-gen-ai-app-starter-kit/) | Vertex AI, FastAPI, LangChain, Cloud Run, Cloud Build, Terraform, Streamlit |

gemini/sample-apps/e2e-gen-ai-app-starter-kit/.gitignore

@@ -0,0 +1,194 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*.pyc
+*$py.class
+**/dist
+/tmp
+/out-tsc
+/bazel-out
+
+# 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
+Pipfile
+
+# 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
+.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/
+
+# macOS
+.DS_Store
+
+# PyCharm
+.idea
+
+# User-specific files
+.terraform*
+.Terraform*
+
+
+tmp*
+
+# Node
+**/node_modules
+npm-debug.log
+yarn-error.log
+
+# IDEs and editors
+.idea/
+.project
+.classpath
+.c9/
+*.launch
+.settings/
+*.sublime-workspace
+
+# Visual Studio Code
+.vscode/*
+!.vscode/settings.json
+!.vscode/tasks.json
+!.vscode/launch.json
+!.vscode/extensions.json
+.history/*
+
+# Miscellaneous
+**/.angular/*
+/.angular/cache
+.sass-cache/
+/connect.lock
+/coverage
+/libpeerconnection.log
+testem.log
+/typings
+
+# System files
+.DS_Store
+Thumbs.db
+*.vscode*
+
+.persist_vector_store
+tests/load_test/.results/*.html
+tests/load_test/.results/*.csv
+locust_env
+my_env.tfvars
+.streamlit_chats
+.saved_chats

gemini/sample-apps/e2e-gen-ai-app-starter-kit/CONTRIBUTING.md

@@ -0,0 +1,47 @@
+# How to Contribute
+
+We'd love to accept your patches and contributions to this sample. There are
+just a few small guidelines you need to follow.
+
+## Contributor License Agreement
+
+Contributions to this project must be accompanied by a Contributor License Agreement. You (or your employer) retain the copyright to your contribution; this simply gives us permission to use and redistribute your contributions as part of the project. Head over to [Google Developers CLA](https://cla.developers.google.com/) to see your current agreements on file or to sign a new one.
+
+You generally only need to submit a CLA once, so if you've already submitted one (even if it was for a different project), you probably don't need to do it again.
+
+## Community Guidelines, Code Reviews, Contributor Guide
+
+Please refer to the [root repository CONTRIBUTING.md file](https://github.com/GoogleCloudPlatform/generative-ai/blob/main/CONTRIBUTING.md) for Community Guidelines, Code Reviews, Contributor Guide, or specific guidance for Google Employees.
+
+## Code Quality Checks
+
+To ensure code quality, we utilize automated checks. Before submitting a pull request, please run the following commands locally:
+
+```bash
+poetry install --with streamlit,jupyter,lint
+```
+
+This installs development dependencies, including linting tools.
+
+Then, execute the following Makefile targets:
+
+```bash
+make lint
+```
+
+This command runs the following linters to check for code style, potential errors, and type hints:
+
+- **codespell**: Detects common spelling mistakes in code and documentation.
+- **ruff**: A fast linter that combines the functionality of several popular tools like flake8, isort, pycodestyle, and others.
+- **mypy**: Performs static type checking to catch type errors before runtime.
+
+```bash
+make test
+```
+
+This command runs the test suite using pytest, covering both unit and integration tests:
+
+- **`poetry run pytest tests/unit`**: Executes unit tests located in the `tests/unit` directory.
+- **`poetry run pytest tests/integration`**: Executes integration tests located in the `tests/integration` directory.
+
+Your pull request will also be automatically checked by these tools using GitHub Actions. Ensuring your code passes these checks locally will help expedite the review process.