Update session 9 to latest version of openai

09-building-image-applications/README.md

@@ -48,7 +48,7 @@
 
 Let's start with DALL-E, which is a Generative AI model that generates images from text descriptions.
 
 > [DALL-E is a combination of two models, CLIP and diffused attention](https://towardsdatascience.com/openais-dall-e-and-clip-101-a-brief-introduction-3a4367280d4e?WT.mc_id=academic-105485-koreyst).
 
 - **CLIP**, is a model that generates embeddings, which are numerical representations of data, from images and text.
 
@@ -78,14 +78,22 @@
 - **pillow**, to work with images in Python.
 - **requests**, to help you make HTTP requests.
 
+## Create and deploy an Azure OpenAI model
+
+If not done already, follow the instructions on the [Microsoft Learn](https://learn.microsoft.com/azure/ai-foundry/openai/how-to/create-resource?pivots=web-portal) page
+to create an Azure OpenAI resource and model. Select DALL-E 3 as model.  
+
+## Create the app
+
 1. Create a file _.env_ with the following content:
 
    ```text
    AZURE_OPENAI_ENDPOINT=<your endpoint>
    AZURE_OPENAI_API_KEY=<your key>
+   AZURE_OPENAI_DEPLOYMENT="dall-e-3"
    ```
 
-   Locate this information in Azure Portal for your resource in the "Keys and Endpoint" section.
+   Locate this information in Azure OpenAI Foundry Portal for your resource in the "Deployments" section.
 
 1. Collect the above libraries in a file called _requirements.txt_ like so:
 
@@ -113,57 +121,54 @@
 
 1. Add the following code in file called _app.py_:
 
-   ```python
-   import openai
-   import os
-   import requests
-   from PIL import Image
-   import dotenv
-
-   # import dotenv
-   dotenv.load_dotenv()
-
-   # Get endpoint and key from environment variables
-   openai.api_base = os.environ['AZURE_OPENAI_ENDPOINT']
-   openai.api_key = os.environ['AZURE_OPENAI_API_KEY']
-
-   # Assign the API version (DALL-E is currently supported for the 2023-06-01-preview API version only)
-   openai.api_version = '2023-06-01-preview'
-   openai.api_type = 'azure'
-
-
-   try:
-       # Create an image by using the image generation API
-       generation_response = openai.Image.create(
-           prompt='Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils',    # Enter your prompt text here
-           size='1024x1024',
-           n=2,
-           temperature=0,
-       )
-       # Set the directory for the stored image
-       image_dir = os.path.join(os.curdir, 'images')
-
-       # If the directory doesn't exist, create it
-       if not os.path.isdir(image_dir):
-           os.mkdir(image_dir)
-
-       # Initialize the image path (note the filetype should be png)
-       image_path = os.path.join(image_dir, 'generated-image.png')
-
-       # Retrieve the generated image
-       image_url = generation_response["data"][0]["url"]  # extract image URL from response
-       generated_image = requests.get(image_url).content  # download the image
-       with open(image_path, "wb") as image_file:
-           image_file.write(generated_image)
-
-       # Display the image in the default image viewer
-       image = Image.open(image_path)
-       image.show()
-
-   # catch exceptions
-   except openai.InvalidRequestError as err:
-       print(err)
-
+    ```python
+    import openai
+    import os
+    import requests
+    from PIL import Image
+    import dotenv
+    from openai import OpenAI, AzureOpenAI
+
+    # import dotenv
+    dotenv.load_dotenv()
+
+    # configure Azure OpenAI service client 
+    client = AzureOpenAI(
+      azure_endpoint = os.environ["AZURE_OPENAI_ENDPOINT"],
+      api_key=os.environ['AZURE_OPENAI_API_KEY'],
+      api_version = "2024-02-01"
+      )
+    try:
+        # Create an image by using the image generation API
+        generation_response = client.images.generate(
+                                prompt='Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils',
+                                size='1024x1024', n=1,
+                                model=os.environ['AZURE_OPENAI_DEPLOYMENT']
+                              )
+
+        # Set the directory for the stored image
+        image_dir = os.path.join(os.curdir, 'images')
+
+        # If the directory doesn't exist, create it
+        if not os.path.isdir(image_dir):
+            os.mkdir(image_dir)
+
+        # Initialize the image path (note the filetype should be png)
+        image_path = os.path.join(image_dir, 'generated-image.png')
+
+        # Retrieve the generated image
+        image_url = generation_response.data[0].url  # extract image URL from response
+        generated_image = requests.get(image_url).content  # download the image
+        with open(image_path, "wb") as image_file:
+            image_file.write(generated_image)
+
+        # Display the image in the default image viewer
+        image = Image.open(image_path)
+        image.show()
+
+    # catch exceptions
+    except openai.InvalidRequestError as err:
+        print(err)
    ```
 
 Let's explain this code:
@@ -185,28 +190,26 @@
   dotenv.load_dotenv()
   ```
 
-- After that, we set the endpoint, key for the OpenAI API, version and type.
+- After that, we configure Azure OpenAI service client 
 
   ```python
   # Get endpoint and key from environment variables
-  openai.api_base = os.environ['AZURE_OPENAI_ENDPOINT']
-  openai.api_key = os.environ['AZURE_OPENAI_API_KEY']
-
-  # add version and type, Azure specific
-  openai.api_version = '2023-06-01-preview'
-  openai.api_type = 'azure'
+  client = AzureOpenAI(
+      azure_endpoint = os.environ["AZURE_OPENAI_ENDPOINT"],
+      api_key=os.environ['AZURE_OPENAI_API_KEY'],
+      api_version = "2024-02-01"
+      )
   ```
 
 - Next, we generate the image:
 
   ```python
   # Create an image by using the image generation API
-  generation_response = openai.Image.create(
-      prompt='Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils',    # Enter your prompt text here
-      size='1024x1024',
-      n=2,
-      temperature=0,
-  )
+  generation_response = client.images.generate(
+                        prompt='Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils',
+                        size='1024x1024', n=1,
+                        model=os.environ['AZURE_OPENAI_DEPLOYMENT']
+                      )
   ```
 
   The above code responds with a JSON object that contains the URL of the generated image. We can use the URL to download the image and save it to a file.
@@ -222,14 +225,13 @@
 
 Let's look at the code that generates the image in more detail:
 
-```python
-generation_response = openai.Image.create(
-        prompt='Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils',    # Enter your prompt text here
-        size='1024x1024',
-        n=2,
-        temperature=0,
-    )
-```
+    ```python
+      generation_response = client.images.generate(
+                                prompt='Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils',
+                                size='1024x1024', n=1,
+                                model=os.environ['AZURE_OPENAI_DEPLOYMENT']
+                            )
+    ```
 
 - **prompt**, is the text prompt that is used to generate the image. In this case, we're using the prompt "Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils".
 - **size**, is the size of the image that is generated. In this case, we're generating an image that is 1024x1024 pixels.
@@ -244,20 +246,29 @@
 
 You can also do the following:
 
-- **Perform edits**. By providing an existing image a mask and a prompt, you can alter an image. For example, you can add something to a portion of an image. Imagine our bunny image, you can add a hat to the bunny. How you would do that is by providing the image, a mask (identifying the part of the area for the change) and a text prompt to say what should be done.
+- **Perform edits**. By providing an existing image a mask and a prompt, you can alter an image. For example, you can add something to a portion of an image. Imagine our bunny image, you can add a hat to the bunny. How you would do that is by providing the image, a mask (identifying the part of the area for the change) and a text prompt to say what should be done. 
+> Note: this is not supported in DALL-E 3. 
+
+Here is an example using GPT Image:
+
+    ```python
+    response = client.images.edit(
+        model="gpt-image-1",
+        image=open("sunlit_lounge.png", "rb"),
+        mask=open("mask.png", "rb"),
+        prompt="A sunlit indoor lounge area with a pool containing a flamingo"
+    )
+    image_url = response.data[0].url
+    ```
 
-  ```python
-  response = openai.Image.create_edit(
-    image=open("base_image.png", "rb"),
-    mask=open("mask.png", "rb"),
-    prompt="An image of a rabbit with a hat on its head.",
-    n=1,
-    size="1024x1024"
-  )
-  image_url = response['data'][0]['url']
-  ```
+  The base image would only contain the lounge with pool but the final image would have a flamingo:
+
+<div style="display: flex; justify-content: space-between; align-items: center; margin: 20px 0;">
+  <img src="./images/sunlit_lounge.png" style="width: 30%; max-width: 200px; height: auto;">
+  <img src="./images/mask.png" style="width: 30%; max-width: 200px; height: auto;">
+  <img src="./images/sunlit_lounge_result.png" style="width: 30%; max-width: 200px; height: auto;">
+</div>
 
-  The base image would only contain the rabbit but the final image would have the hat on the rabbit.
 
 - **Create variations**. The idea is that you take an existing image and ask that variations are created. To create a variation, you provide an image and a text prompt and code like so:
 
@@ -280,16 +291,16 @@
 
 > Prompt : "Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils"
 
-![Bunny on a horse holding a lollipop, version 1](./images/v1-generated-image.png?WT.mc_id=academic-105485-koreyst)
+![Bunny on a horse holding a lollipop, version 1](./images/v1-generated-image.png)
 
 Now let's run that same prompt just to see that we won't get the same image twice:
 
-![Generated image of bunny on horse](./images/v2-generated-image.png?WT.mc_id=academic-105485-koreyst)
+![Generated image of bunny on horse](./images/v2-generated-image.png)
 
 As you can see, the images are similar, but not the same. Let's try changing the temperature value to 0.1 and see what happens:
 
 ```python
- generation_response = openai.Image.create(
+ generation_response = client.images.create(
         prompt='Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils',    # Enter your prompt text here
         size='1024x1024',
         n=2
@@ -303,7 +314,7 @@
 Let's therefore change our code and set the temperature to 0, like so:
 
 ```python
-generation_response = openai.Image.create(
+generation_response = client.images.create(
         prompt='Bunny on horse, holding a lollipop, on a foggy meadow where it grows daffodils',    # Enter your prompt text here
         size='1024x1024',
         n=2,
@@ -313,8 +324,8 @@
 
 Now when you run this code, you get these two images:
 
-- ![Temperature 0, v1](./images/v1-temp-generated-image.png?WT.mc_id=academic-105485-koreyst)
-- ![Temperature 0 , v2](./images/v2-temp-generated-image.png?WT.mc_id=academic-105485-koreyst)
+- ![Temperature 0, v1](./images/v1-temp-generated-image.png)
+- ![Temperature 0 , v2](./images/v2-temp-generated-image.png)
 
 Here you can clearly see how the images resemble each other more.
 
@@ -394,17 +405,17 @@
 import requests
 from PIL import Image
 import dotenv
-
+from openai import AzureOpenAI
 # import dotenv
 dotenv.load_dotenv()
 
 # Get endpoint and key from environment variables
-openai.api_base = "<replace with endpoint>"
-openai.api_key = "<replace with api key>"
+client = AzureOpenAI(
+  azure_endpoint = os.environ["AZURE_OPENAI_ENDPOINT"],
+  api_key=os.environ['AZURE_OPENAI_API_KEY'],
+  api_version = "2024-02-01"
+  )
 
-# Assign the API version (DALL-E is currently supported for the 2023-06-01-preview API version only)
-openai.api_version = '2023-06-01-preview'
-openai.api_type = 'azure'
 
 disallow_list = "swords, violence, blood, gore, nudity, sexual content, adult content, adult themes, adult language, adult humor, adult jokes, adult situations, adult"
 
@@ -419,19 +430,19 @@
 The image needs to be in a 16:9 aspect ratio.
 
 Do not consider any input from the following that is not safe for work or appropriate for children.
-{disallow_list}"""
+{disallow_list}
+"""
 
 prompt = f"""{meta_prompt}
 Generate monument of the Arc of Triumph in Paris, France, in the evening light with a small child holding a Teddy looks on.
 """"
 
 try:
     # Create an image by using the image generation API
-    generation_response = openai.Image.create(
+    generation_response = client.images.generate(
         prompt=prompt,    # Enter your prompt text here
         size='1024x1024',
-        n=2,
-        temperature=0,
+        n=1,
     )
     # Set the directory for the stored image
     image_dir = os.path.join(os.curdir, 'images')
@@ -444,7 +455,7 @@
     image_path = os.path.join(image_dir, 'generated-image.png')
 
     # Retrieve the generated image
-    image_url = generation_response["data"][0]["url"]  # extract image URL from response
+    image_url = generation_response.data[0].url  # extract image URL from response
     generated_image = requests.get(image_url).content  # download the image
     with open(image_path, "wb") as image_file:
         image_file.write(generated_image)
@@ -454,7 +465,7 @@
     image.show()
 
 # catch exceptions
-except openai.InvalidRequestError as err:
+except openai.BadRequestError as err:
     print(err)
 ```