Merge pull request #1 from pamelafox/first

Initial demo files

Author: pamelafox

.devcontainer/devcontainer.json

@@ -4,18 +4,18 @@
     "name": "Python 3",
     "image": "mcr.microsoft.com/devcontainers/python:3.11-bullseye",
 
+    "features": {
+        "ghcr.io/devcontainers/features/azure-cli:latest": {},
+        "ghcr.io/azure/azure-dev/azd:latest": {}
+    },
     // Configure tool-specific properties.
     "customizations": {
         // Configure properties specific to VS Code.
         "vscode": {
             // Set *default* container specific settings.json values on container create.
             "settings": {
                 "python.defaultInterpreterPath": "/usr/local/bin/python",
-                "python.testing.pytestEnabled": true,
-                "python.testing.unittestEnabled": false,
                 "files.exclude": {
-                    ".coverage": true,
-                    ".pytest_cache": true,
                     "__pycache__": true
                 }
             },
@@ -33,7 +33,7 @@
     // "forwardPorts": [],
 
     // Use 'postCreateCommand' to run commands after the container is created.
-    "postCreateCommand": "pip3 install --user -r requirements-dev.txt && pre-commit install",
+    "postCreateCommand": "pip3 install --user -r requirements-dev.txt",
 
     // Comment out to connect as root instead. More info: https://aka.ms/vscode-remote/containers/non-root.
     "remoteUser": "vscode"

.env.sample

@@ -0,0 +1,12 @@
+# API_HOST can be either azure, ollama, or openai:
+API_HOST=azure
+# Needed for Azure:
+AZURE_OPENAI_ENDPOINT=https://YOUR-AZURE-OPENAI-SERVICE-NAME.openai.azure.com
+AZURE_OPENAI_DEPLOYMENT=YOUR-AZURE-DEPLOYMENT-NAME
+AZURE_OPENAI_VERSION=2024-03-01-preview
+# Needed for Ollama:
+OLLAMA_ENDPOINT=http://localhost:11434/v1
+OLLAMA_MODEL=llama2
+# Needed for OpenAI.com:
+OPENAI_KEY=YOUR-OPENAI-KEY
+OPENAI_MODEL=gpt-3.5-turbo

.github/workflows/python.yaml

@@ -23,6 +23,3 @@ jobs:
           run: ruff .
         - name: Check formatting with black
           run: black . --check --verbose
-        - name: Run unit tests
-          run: |
-            pytest

.gitignore

@@ -1,3 +1,142 @@
-.venv
-__pycache__
+# Azure az webapp deployment details
+.azure
+*_env
+
+# 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
+
+# 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/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/

README.md

@@ -1,78 +1,64 @@
-# Python project template
+# Python OpenAI demos
 
-This is a template repository for any Python project that comes with the following dev tools:
+This repository contains a collection of Python scripts that demonstrate how to use the OpenAI API to generate chat completions.
 
-* `ruff`: identifies many errors and style issues (`flake8`, `isort`, `pyupgrade`)
-* `black`: auto-formats code
+In increasing order of complexity, the scripts are:
 
-Those checks are run as pre-commit hooks using the `pre-commit` library.
+1. [`chat.py`](./chat.py): A simple script that demonstrates how to use the OpenAI API to generate chat completions.
+2. [`chat_stream.py`](./chat_stream.py): Adds `stream=True` to the API call to return a generator that streams the completion as it is being generated.
+3. [`chat_history.py`](./chat_history.py): Adds a back-and-forth chat interface using `input()` which keeps track of past messages and sends them with each chat completion call.
+4. [`chat_history_stream.py`](./chat_history_stream.py): The same idea, but with `stream=True` enabled.
 
-It includes `pytest` for testing plus the `pytest-cov` plugin to measure coverage.
+Plus these scripts to demonstrate additional features:
 
-The checks and tests are all run using Github actions on every pull request and merge to main.
+5. [`chat_safety.py`](./chat_safety.py): The simple script with exception handling for Azure AI Content Safety filter errors.
+6. [`chat_async.py`](./chat_async.py): Uses the async clients to make asynchronous calls, including an example of sending off multiple requests at once using `asyncio.gather`.
 
-This repository is setup for Python 3.11. To change the version:
-1. Change the `image` argument in `.devcontainer/devcontainer.json` (see [https://github.com/devcontainers/images/tree/main/src/python](https://github.com/devcontainers/images/tree/main/src/python#configuration) for a list of pre-built Docker images)
-1. Change the config options in `.precommit-config.yaml`
-1. Change the version number in `.github/workflows/python.yaml`
+## Setting up the environment
 
-## Development instructions
+If you open this up in a Dev Container or GitHub Codespaces, everything will be setup for you.
+If not, follow these steps:
 
-## With devcontainer
+1. Set up a Python virtual environment and activate it.
 
-This repository comes with a devcontainer (a Dockerized Python environment). If you open it in Codespaces, it should automatically initialize the devcontainer.
+2. Install the required packages:
 
-Locally, you can open it in VS Code with the Dev Containers extension installed.
-
-## Without devcontainer
-
-If you can't or don't want to use the devcontainer, then you should first create a virtual environment:
-
-```
-python3 -m venv .venv
-source .venv/bin/activate
-```
-
-Then install the dev tools and pre-commit hooks:
-
-```
-python3 -m pip install --user -r requirements-dev.txt
-pre-commit install
+```bash
+pip install -r requirements.txt
 ```
 
-## Adding code and tests
+## Configuring the OpenAI environment variables
 
-This repository starts with a very simple `main.py` and a test for it at `tests/main_test.py`.
-You'll want to replace that with your own code, and you'll probably want to add additional files
-as your code grows in complexity.
+These scripts can be run against an Azure OpenAI account, an OpenAI.com account, or a local Ollama server,
+depending on the environment variables you set.
 
-When you're ready to run tests, run:
+1. Copy the `.env.sample file to a new file called `.env`:
 
-```
-python3 -m pytest
-```
+    ```bash
+    cp .env.sample .env
+    ```
 
-# File breakdown
+2. For Azure OpenAI, create an Azure OpenAI gpt-3.5 or gpt-4 deployment, and customize the `.env` file with your Azure OpenAI endpoint and deployment id.
 
-Here's a short explanation of each file/folder in this template:
+    ```bash
+    API_HOST=azure
+    AZURE_OPENAI_ENDPOINT=https://YOUR-AZURE-OPENAI-SERVICE-NAME.openai.azure.com
+    AZURE_OPENAI_DEPLOYMENT=YOUR-AZURE-DEPLOYMENT-NAME
+    AZURE_OPENAI_VERSION=2024-03-01-preview
+    ```
 
-* `.devcontainer`: Folder containing files used for setting up a devcontainer
-  * `devcontainer.json`: File configuring the devcontainer, includes VS Code settings
-* `.github`: Folder for Github-specific files and folders
-  * `workflows`: Folder containing Github actions config files
-    * `python.yaml`: File configuring Github action that runs tools and tests
-* `tests`: Folder containing Python tests
-  * `main_test.py`: File with pytest-style tests of main.py
-* `.gitignore`: File describing what file patterns Git should never track
-* `.pre-commit-config.yaml`: File listing all the pre-commit hooks and args
-* `main.py`: The main (and currently only) Python file for the program
-* `pyproject.toml`: File configuring most of the Python dev tools
-* `README.md`: You're reading it!
-* `requirements-dev.txt`: File listing all PyPi packages required for development
-* `requirements.txt`: File listing all PyPi packages required for production
+3. For OpenAI.com, customize the `.env` file with your OpenAI API key and desired model name.
 
-For a longer explanation, read [this blog post](http://blog.pamelafox.org/2022/09/how-i-setup-python-project.html).
+    ```bash
+    API_HOST=openai
+    OPENAI_KEY=YOUR-OPENAI-API-KEY
+    OPENAI_MODEL=gpt-3.5-turbo
+    ```
 
-# 🔎 Found an issue or have an idea for improvement?
+4. For Ollama, customize the `.env` file with your Ollama endpoint and model name (any model you've pulled).
 
-Help me make this template repository better by letting us know and opening an issue!
+    ```bash
+    API_HOST=ollama
+    OLLAMA_ENDPOINT=http://localhost:11434/v1
+    OLLAMA_MODEL=llama2
+    ```

chat.py

@@ -0,0 +1,43 @@
+import os
+
+import azure.identity
+import openai
+from dotenv import load_dotenv
+
+# Setup the OpenAI client to use either Azure, OpenAI.com, or Ollama API
+load_dotenv()
+API_HOST = os.getenv("API_HOST")
+
+if API_HOST == "azure":
+    token_provider = azure.identity.get_bearer_token_provider(
+        azure.identity.DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+    )
+    client = openai.AzureOpenAI(
+        api_version=os.getenv("AZURE_OPENAI_VERSION"),
+        azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
+        azure_ad_token_provider=token_provider,
+    )
+    MODEL_NAME = os.getenv("AZURE_OPENAI_DEPLOYMENT")
+elif API_HOST == "ollama":
+    client = openai.OpenAI(
+        base_url="http://localhost:11434/v1",
+        api_key="nokeyneeded",
+    )
+    MODEL_NAME = os.getenv("OLLAMA_MODEL")
+else:
+    client = openai.OpenAI(api_key=os.getenv("OPENAI_KEY"))
+    MODEL_NAME = os.getenv("OPENAI_MODEL")
+
+
+response = client.chat.completions.create(
+    model=MODEL_NAME,
+    temperature=0.7,
+    n=1,
+    messages=[
+        {"role": "system", "content": "You are a helpful assistant that makes lots of cat references and uses emojis."},
+        {"role": "user", "content": "Write a haiku about a hungry cat who wants tuna"},
+    ],
+)
+
+print("Response: ")
+print(response.choices[0].message.content)