Updated Python & openai-python to 3.7.1+ & 0.22.1, minor updates to Python and Codex proper name usage

Author: DenKenMSFT

articles/cognitive-services/openai/concepts/models.md

@@ -25,7 +25,7 @@ The service provides access to many different models. Models describe a family o
 
 ## Naming convention
 
-Azure OpenAI's models follow a standard naming convention: `{task}-{model name}-{version #}`. For example, our most powerful natural language model is called `text-davinci-001` and a codex series model would look like `code-cushman-001`.
+Azure OpenAI's models follow a standard naming convention: `{task}-{model name}-{version #}`. For example, our most powerful natural language model is called `text-davinci-001` and a Codex series model would look like `code-cushman-001`.
 
 > Older versions of the GPT-3 models are available as `ada`, `babbage`, `curie`, `davinci` and do not follow these conventions. These models are primarily intended to be used for fine-tuning and search.
 
@@ -80,7 +80,7 @@ The Codex models are descendants of our base GPT-3 models that can understand an
 
 They’re most capable in Python and proficient in over a dozen languages including JavaScript, Go, Perl, PHP, Ruby, Swift, TypeScript, SQL, and even Shell.
 
-Currently we only offer one codex model: `code-cushman-001`.
+Currently we only offer one Codex model: `code-cushman-001`.
 
 ## Embeddings Models
 

articles/cognitive-services/openai/how-to/fine-tuning.md

@@ -24,7 +24,7 @@ The Azure OpenAI Service lets you tailor our models to your personal datasets us
 
 - An Azure subscription - [Create one for free](https://azure.microsoft.com/free/cognitive-services)
 - Access granted to service in the desired Azure subscription. This service is currently invite only. You can fill out a new use case request here: <https://aka.ms/oai/access>. Please open an issue on this repo to contact us if you have an issue
-- The following python libraries: os, requests, json
+- The following Python libraries: os, requests, json
 - An Azure OpenAI Service resource with a model deployed. If you don't have a resource/model the process is documented in our [resource deployment guide](../how-to/create-resource.md)
 
 ## Fine-tuning workflow
@@ -40,7 +40,7 @@ The fine-tuning workflow requires the following steps:
 
 Your training data set consists of input & output examples for how you would like the model perform.
 
-The training dataset you use **must** be a JSON lines (JSONL) document where each line is a prompt-completion pair and a single example. The OpenAI python CLI provides a useful data preparation tool to easily convert your data into this file format.
+The training dataset you use **must** be a JSON lines (JSONL) document where each line is a prompt-completion pair and a single example. The OpenAI Python CLI provides a useful data preparation tool to easily convert your data into this file format.
 
 Here's an example of the format:
 
@@ -89,7 +89,7 @@ Once you've prepared your dataset, you can upload your files to the service. We
 
 For large data files, we recommend you import from Azure Blob. Large files can become unstable when uploaded through multipart forms because the requests are atomic and can't be retried or resumed.
 
-The following python code will create a sample dataset and show how to upload a file and print the returned ID. Make sure to save the IDs returned as you'll need them for the fine-tuning training job creation.
+The following Python code will create a sample dataset and show how to upload a file and print the returned ID. Make sure to save the IDs returned as you'll need them for the fine-tuning training job creation.
 
 > [!IMPORTANT]
 > Remember to remove the key from your code when you're done, and never post it publicly. For production, use a secure way of storing and accessing your credentials like [Azure Key Vault](../../../key-vault/general/overview.md). See the Cognitive Services [security](../../cognitive-services-security.md) article for more information.
@@ -146,7 +146,7 @@ while train_status not in ["succeeded", "failed"] or valid_status not in ["succe
 
 After you've uploaded the training and (optional) validation file, you wish to use for your training job you're ready to start the process. You can use the [Models API](../reference.md#models) to identify which models are fine-tunable.
 
-Once you have the model, you want to fine-tune you need to create a job. The following python code shows an example of how to create a new job:
+Once you have the model, you want to fine-tune you need to create a job. The following Python code shows an example of how to create a new job:
 
 ```python
 create_args = {
@@ -220,7 +220,7 @@ az cognitiveservices account deployment create
 
 ## Use a fine-tuned model
 
-Once your model has been deployed, you can use it like any other model. Reference the deployment name you specified in the previous step. You can use either the REST API or python SDK and can continue to use all the other Completions parameters like temperature, frequency_penalty, presence_penalty, etc., on these requests to fine-tuned models.
+Once your model has been deployed, you can use it like any other model. Reference the deployment name you specified in the previous step. You can use either the REST API or Python SDK and can continue to use all the other Completions parameters like temperature, frequency_penalty, presence_penalty, etc., on these requests to fine-tuned models.
 
 ```python
 print('Sending a test completion job')
@@ -316,4 +316,4 @@ That said, tweaking the hyperparameters used for fine-tuning can often lead to a
 ## Next Steps
 
 - Explore the full REST API Reference documentation to learn more about all the fine-tuning capabilities. You can find the [full REST documentation here](../reference.md).
-- Explore more of the [python SDK operations here](https://github.com/openai/openai-python/blob/main/examples/azure/finetuning.ipynb).
+- Explore more of the [Python SDK operations here](https://github.com/openai/openai-python/blob/main/examples/azure/finetuning.ipynb).

articles/cognitive-services/openai/how-to/managed-identity.md

@@ -23,7 +23,7 @@ In the following sections, you'll use  the Azure CLI to assign roles, and obtain
 - An Azure subscription
 - Access granted to service in the desired Azure subscription. 
 - Azure CLI. [Installation Guide](/cli/azure/install-azure-cli)
-- The following python libraries: os, requests, json
+- The following Python libraries: os, requests, json
 
 ## Sign into the Azure CLI
 

articles/cognitive-services/openai/how-to/work-with-code.md

@@ -101,7 +101,7 @@ When you show Codex the database schema, it's able to make an informed guess abo
 
 ### Specify the programming language
 
-Codex understands dozens of different programming languages. Many share similar conventions for comments, functions and other programming syntax. By specifying the language and what version in a comment, Codex is better able to provide a completion for what you want. That said, Codex is fairly flexible with style and syntax. Here's an example for R and python.
+Codex understands dozens of different programming languages. Many share similar conventions for comments, functions and other programming syntax. By specifying the language and what version in a comment, Codex is better able to provide a completion for what you want. That said, Codex is fairly flexible with style and syntax. Here's an example for R and Python.
 
 ```r
 # R language

articles/cognitive-services/openai/includes/python.md

@@ -17,8 +17,8 @@ keywords:
 
 - An Azure subscription - <a href="https://azure.microsoft.com/free/cognitive-services" target="_blank">Create one for free</a>
 - Access granted to service in the desired Azure subscription. This service is currently invite only. You can fill out a new use case request here:<a href="https://aka.ms/oai/access" target="_blank">https://aka.ms/oai/access</a>
-- <a href="https://www.python.org/" target="_blank">Python 3.x</a>
-- The following python libraries: os, requests, json
+- <a href="https://www.python.org/" target="_blank">Python 3.7.1 or later version</a>
+- The following Python libraries: os, requests, json
 - An Azure OpenAI Service resource with a model deployed. If you don't have a resource/model the process is documented in our [resource deployment guide](../how-to/create-resource.md)
 
 ## Set up
@@ -45,7 +45,7 @@ Go to your resource in the Azure portal. The **Endpoint and Keys** can be found
 
 ## Create a new Python application
 
-1. Create a new python file called quickstart.py. Then open it up in your preferred editor or IDE.
+1. Create a new Python file called quickstart.py. Then open it up in your preferred editor or IDE.
 
 2. Replace the contents of quickstart.py with the following code. Modify the code to add your key, endpoint, and deployment name:
 

articles/cognitive-services/openai/includes/rest.md

@@ -15,8 +15,8 @@ keywords:
 
 - An Azure subscription - <a href="https://azure.microsoft.com/free/cognitive-services" target="_blank">Create one for free</a>
 - Access granted to service in the desired Azure subscription. This service is currently invite only. You can fill out a new use case request here:<a href="https://aka.ms/oai/access" target="_blank">https://aka.ms/oai/access</a>
-- <a href="https://www.python.org/" target="_blank">Python 3.x</a>
-- The following python libraries: os, requests, json
+- <a href="https://www.python.org/" target="_blank">Python 3.7.1 or later version</a>
+- The following Python libraries: os, requests, json
 - An Azure OpenAI Service resource with a model deployed. If you don't have a resource/model the process is documented in our [resource deployment guide](../how-to/create-resource.md)
 
 ## Retrieve key and endpoint
@@ -35,7 +35,7 @@ Go to your resource in the Azure portal. The **Endpoint and Keys** can be found
 
 ## Create a new Python application
 
-Create a new python file called quickstart.py. Then open it up in your preferred editor or IDE.
+Create a new Python file called quickstart.py. Then open it up in your preferred editor or IDE.
 
 1. Replace the contents of quickstart.py with the following code.
 

articles/cognitive-services/openai/includes/studio.md

@@ -36,7 +36,7 @@ From here, select the **create new deployment** button in the banner at the top.
 
 ## Deployments
 
-Before you can generate text or inference, you need to deploy a model. This is done by clicking the **create new deployment** on the deployments page. From here you can select from one of our many available models. For getting started we recommend `text-davinci-002` for users in South Central and `text-davinci-001` for users in West Europe (text-davinci-002 isn't available in this region).
+Before you can generate text or inference, you need to deploy a model. This is done by clicking the **create new deployment** on the deployments page. From here you can select from one of our many available models. For getting started we recommend `text-davinci-002` for users in South Central and `text-davinci-001` for users in West Europe (`text-davinci-002` isn't available in this region).
 
 Once this is complete, select the 'Playground' button on the left nav to start experimenting.
 
@@ -52,7 +52,7 @@ The best way to start exploring completions is through our Playground. It's simp
 - Selecting the Generate button will send the entered text to the completions API and stream the results back to the text box.
 - Select the 'undo' button to undo the prior generation call
 - Select the 'regenerate' button to do an undo & generation call together.
-- View the code you could use to make the same call with our python SDK, curl or other REST API client
+- View the code you could use to make the same call with our Python SDK, curl or other REST API client
 - Configure the parameters of the completions call to improve the performance of your task. You can read more about each parameter in our [REST API](../reference.md).
 
 1. Now that you've familiarized yourself with the playground, get started generating text by loading the **Summarize Text** example.

articles/cognitive-services/openai/reference.md

@@ -40,10 +40,10 @@ The Azure OpenAI service provides two methods for authentication. you can use  e
 The service APIs are versioned using the ```api-version``` query parameter. All versions follow the YYYY-MM-DD date structure, with a -preview suffix for a preview service. For example:
 
 ```
-POST https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME/completions?api-version=2021-11-01-preview
+POST https://YOUR_RESOURCE_NAME.openai.azure.com/openai/deployments/YOUR_DEPLOYMENT_NAME/completions?api-version=2022-06-01-preview
 ```
 
-We currently have the following versions available: ```2022-03-01-preview``` and ```2021-11-01-preview```
+We currently have the following versions available: ```2022-06-01-preview```
 
 ## Completions
 With the Completions operation, the model will generate one or more predicted completions based on a provided prompt. The service can also return the probabilities of alternative tokens at each position.
@@ -514,7 +514,7 @@ GET https://{your-resource-name}.openai.azure.com/openai/fine-tunes/{fine_tune_i
 
 **Supported versions**
 
-- `2022-03-01-preview`
+- `2022-06-01-preview`
 
 #### Example request