Merge pull request #560 from ryubidragonfire/chyam/06

06, added githubmodels-app.py, updated githubmodels-assignment.ipynb
microsoft · Sep 3, 2024 · 9b579dc · 9b579dc
2 parents a0e94d6 + 1f75679
commit 9b579dc
Show file tree

Hide file tree

Showing 5 changed files with 66 additions and 11 deletions.
diff --git a/.devcontainer/environment.yml b/.devcontainer/environment.yml
@@ -0,0 +1,7 @@
+name: <environment-name>
+channels:
+ - defaults
+dependencies:
+- python=3.12
+- openai
+- python-dotenv
diff --git a/00-course-setup/README.md b/00-course-setup/README.md
@@ -38,6 +38,7 @@ cd generative-ai-for-beginners
 Once you have everything checked out, you can get started!
 
 ### Installing Miniconda (optional step)
+
 [Miniconda](https://conda.io/en/latest/miniconda.html?WT.mc_id=academic-105485-koreyst) is a lightweight installer for installing [Conda](https://docs.conda.io/en/latest?WT.mc_id=academic-105485-koreyst), Python, as well as a few packages.
 Conda itself is a package manager, that makes it easy to setup and switch between different Python [**virtual environments**](https://docs.python.org/3/tutorial/venv.html?WT.mc_id=academic-105485-koreyst) and packages. It also comes in handy for installing packages that are not available via `pip`.
 
@@ -48,6 +49,7 @@ With Miniconda installed, you need to clone the [repository](https://github.com/
 Next, you need to create a virtual environment. To do this with Conda, go ahead and create a new environment file (_environment.yml_). If you are following along using Codespaces, create this within the `.devcontainer` directory, thus `.devcontainer/environment.yml`.
 
 Go ahead and populate your environment file with the snippet below:
+
 ```yml
 name: <environment-name>
 channels:
@@ -56,13 +58,14 @@ dependencies:
 - python=<python-version>
 - openai
 - python-dotenv
+- azure-ai-inference
+
 ```
 
 The environment file specifies the dependencies we need. `<environment-name>` refers to the name you would like to use for your Conda environment, and `<python-version>` is the version of Python you would like to use, for example, `3` is the latest major version of Python.
 
 With that done, you can  go ahead and create your Conda environment by running the commands below in your command line/terminal
 
-
 ```bash
 conda env create --name ai4beg --file .devcontainer/environment.yml # .devcontainer sub path applies to only Codespace setups
 conda activate ai4beg
@@ -78,7 +81,7 @@ We recommend using the [Visual Studio Code (VS Code)](http://code.visualstudio.c
 
 > **Note**: Once you clone and open the directory in VS Code, it will automatically suggest you install a Python support extension.
 
-> **Note**: If VS Code suggests you re-open the repository in a container, decline this request in order to use the locally installed version of Python. 
+> **Note**: If VS Code suggests you re-open the repository in a container, decline this request in order to use the locally installed version of Python.
 
 ### Using Jupyter in the Browser
 

diff --git a/06-text-generation-apps/python/githubmodels-app.py b/06-text-generation-apps/python/githubmodels-app.py
@@ -0,0 +1,36 @@
+import os
+from azure.ai.inference import ChatCompletionsClient
+from azure.ai.inference.models import SystemMessage, UserMessage
+from azure.core.credentials import AzureKeyCredential
+
+token = os.environ["GITHUB_TOKEN"]
+endpoint = "https://models.inference.ai.azure.com"
+
+model_name = "gpt-4o"
+
+client = ChatCompletionsClient(
+    endpoint=endpoint,
+    credential=AzureKeyCredential(token),
+)
+
+prompt = "Show me 5 recipes for a dish with the following ingredients: chicken, potatoes, and carrots. Per recipe, list all the ingredients used"
+
+response = client.complete(
+    messages=[
+        {
+            "role": "system",
+            "content": "You are a helpful assistant.",
+        },
+        {
+            "role": "user",
+            "content": prompt,
+        },
+    ],
+    model=model_name,
+    # Optional parameters
+    temperature=1.,
+    max_tokens=1000,
+    top_p=1.    
+)
+
+print(response.choices[0].message.content)
diff --git a/06-text-generation-apps/python/githubmodels-assignment.ipynb b/06-text-generation-apps/python/githubmodels-assignment.ipynb
@@ -123,14 +123,10 @@
     "* From the 'Get started' window choose Codespaces\n",
     "* Create a new codespace (or use an existing)\n",
     "* VS Code will open in your browser with a set of sample notebooks in multiple languages you can try\n",
-    "* Under ```samples/python/azure_ai_inference``` select ```getting_started.ipynb``` - run through the sample. \n",
+    "* Run the sample ```./githubmodels-app.py```. \n",
     "\n",
     "> Note: In codespaces there is no need to set the Github Token variable, skip this step\n",
     "\n",
-    "* Once you have run through all the capabilities and sample code in the notebook lets take the ```basic.py``` and start editing for your own example. Navigate to ```samples/python/azure_ai_inference/``` and enter ```python basic.py``` into the bash terminal\n",
-    "\n",
-    "![Codespaces showing running basic.py file and output](../images/codespaces-basicpy.png?WT.mc_id=academic-105485-koreyst)\n",
-    "\n",
     "**Now move to 'Generate Text' section below to continue this assignment**\n",
     "\n",
     "### 2. VS Code (or any favorite IDE)\n",
@@ -161,7 +157,7 @@
     "## Generate text with ChatCompletions\n",
     "\n",
     "The way to generate text is to use the `ChatCompletionsClient` class. \n",
-    "In your code file update the response for the user role by changing the content parameter to below:\n",
+    "In `samples/python/azure_ai_inference/basic.py`, in the response section of code, update the code the user role by changing the content parameter to below:\n",
     "\n",
     "```python\n",
     "\n",
@@ -367,9 +363,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'azure'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[1], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mimport\u001b[39;00m \u001b[38;5;21;01mos\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mazure\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mai\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01minference\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m ChatCompletionsClient\n\u001b[1;32m      3\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mazure\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mai\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01minference\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodels\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m SystemMessage, UserMessage\n\u001b[1;32m      4\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mazure\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcredentials\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AzureKeyCredential\n",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'azure'"
+     ]
+    }
+   ],
    "source": [
     "import os\n",
     "from azure.ai.inference import ChatCompletionsClient\n",

diff --git a/requirements.txt b/requirements.txt
@@ -5,4 +5,5 @@ pandas==1.5.3
 tqdm==4.66.3
 python-dotenv==1.0.0
 openai>=0.28.0
-tiktoken
+tiktoken
+azure-ai-inference