The Azure Open AI Connector enables developers to seamlessly connect and leverage the advanced artificial intelligence capabilities of Azure OpenAI.

The component allows to use the following operations:

• Completions
• Chat Completions
• Embeddings

To use this connector it is necessary to have a Microsoft Azure account with the service Azure OpenAI activated. 

Using the Azure OpenAI service will have cost that will be billed in your Azure Account. Check the Azure OpenAI pricing page.

Completions

With the Completions operation, the model will generate one or more predicted completions based on a provided prompt.

The connector offers two actions to generate completions:

• GetCompletion - a server action that will create a request for Azure OpenAI and retrieves the answer synchronously.
• StreamCompletion - a client action that will create a request for Azure OpenAI and will stream the result as the Azure OpenAI service is creating the answer, showing the result in a target widget asynchronously. 

Chat Completions

Create completions for chat messages with the ChatGPT and GPT-4 models.

The connector offers two actions to generate chat completions:

• GetChatCompletion - a server action that will create a request for Azure OpenAI and retrieves the answer synchronously.
• StreamChatCompletion - a client action that will create a request for Azure OpenAI and will stream the result as the Azure OpenAI service is creating the answer, showing the result in a target widget asynchronously.

Embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and other algorithms.

Instructions

Authentication is done using API Key authentication that can be found in the Azure Portal under Resource Management > Keys and Endpoint.

In order to use the connector it is necessary to deploy models using the Azure AI Studio. 

Some models are suitable for completion like text-davinci-003, others for chat completion like gpt-35-turbo and others for embeddings like text-embedding-ada-002.

This connector requires these configurations:

Settings

ApiKey - API Key configured in Azure Portal for the Open AI Service

ApiVersion - The API version to use for this operation. This follows the YYYY-MM-DD format. Default is 2023-05-15.

AzureOpenAIEndpoint - The endpoint from the Azure Open AI Endpoint, can be found in Azure Portal. Only necessary in case of StreamCompletion and StreamChatCompletion.

ChatCompletionDeploymentId - The deployment name you chose when you deployed the model for Chat Completions. Only necessary in case of StreamChatCompletion and GetChatCompletion.

CompletionDeploymentId - The deployment name you chose when you deployed the model for Completions. Only necessary in case of StreamCompletion and GetCompletion.

EmbeddingDeploymentId - The deployment name you chose when you deployed the model for Embedding. Only necessary in case of CreateEmbedding.

Consumed REST APIs

AzureOpenAIServiceAPI - The endpoint from the Azure Open AI Endpoint, can be found in Azure Portal. Only necessary in case of GetCompletion, GetChatCompletion and CreateEmbedding.

The Azure Open AI Connector enables developers to seamlessly connect and leverage the advanced artificial intelligence capabilities of Azure OpenAI.

The component allows to use the following operations:

• Completions
• Chat Completions
• Embeddings

To use this connector it is necessary to have a Microsoft Azure account with the service Azure OpenAI activated. 

Using the Azure OpenAI service will have cost that will be billed in your Azure Account. Check the Azure OpenAI pricing page.

Completions

With the Completions operation, the model will generate one or more predicted completions based on a provided prompt.

The connector offers two actions to generate completions:

• GetCompletion - a server action that will create a request for Azure OpenAI and retrieves the answer synchronously.
• StreamCompletion - a client action that will create a request for Azure OpenAI and will stream the result as the Azure OpenAI service is creating the answer, showing the result in a target widget.

Chat Completions

Create completions for chat messages with the ChatGPT and GPT-4 models.

The connector offers two actions to generate chat completions:

• GetChatCompletion - a server action that will create a request for Azure OpenAI and retrieves the answer synchronously.
• StreamChatCompletion - a client action that will create a request for Azure OpenAI and will stream the result as the Azure OpenAI service is creating the answer, showing the result in a target widget.

Embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and other algorithms.

Instructions

Authentication is done using API Key authentication that can be found in the Azure Portal under Resource Management > Keys and Endpoint.

In order to use the connector it is necessary to deploy models using the Azure AI Studio. 

Some models are suitable for completion like text-davinci-003, others for chat completion like gpt-35-turbo and others for embeddings like text-embedding-ada-002.

This connector requires these configurations:

Settings

ApiKey - API Key configured in Azure Portal for the Open AI Service

ApiVersion - The API version to use for this operation. This follows the YYYY-MM-DD format. Default is 2023-05-15.

AzureOpenAIEndpoint - The endpoint from the Azure Open AI Endpoint, can be found in Azure Portal. Only necessary in case of StreamCompletion and StreamChatCompletion.

ChatCompletionDeploymentId - The deployment name you chose when you deployed the model for Chat Completions. Only necessary in case of StreamChatCompletion and GetChatCompletion.

CompletionDeploymentId - The deployment name you chose when you deployed the model for Completions. Only necessary in case of StreamCompletion and GetCompletion.

EmbeddingDeploymentId - The deployment name you chose when you deployed the model for Embedding. Only necessary in case of CreateEmbedding.

Consumed REST APIs

AzureOpenAIServiceAPI - The endpoint from the Azure Open AI Endpoint, can be found in Azure Portal. Only necessary in case of GetCompletion, GetChatCompletion and CreateEmbedding.

The Azure Open AI Connector enables developers to seamlessly connect and leverage the advanced artificial intelligence capabilities of Azure OpenAI.

The component allows to use the following operations:

• Completions
• Chat Completions
• Embeddings

To use this connector it is necessary to have a Microsoft Azure account with the service Azure OpenAI activated. 

Using the Azure OpenAI service will have cost that will be billed in your Azure Account. Check the Azure OpenAI pricing page.

Completions

With the Completions operation, the model will generate one or more predicted completions based on a provided prompt.

The connector offers two actions to generate completions:

• GetCompletion - a server action that will create a request for Azure OpenAI and retrieves the answer synchronously.
• StreamCompletion - a client action that will create a request for Azure OpenAI and will stream the result as the Azure OpenAI service is creating the answer, showing the result in a target widget.

Chat Completions

Create completions for chat messages with the ChatGPT and GPT-4 models.

The connector offers two actions to generate chat completions:

• GetChatCompletion - a server action that will create a request for Azure OpenAI and retrieves the answer synchronously.
• StreamChatCompletion - a client action that will create a request for Azure OpenAI and will stream the result as the Azure OpenAI service is creating the answer, showing the result in a target widget.

Embeddings

Get a vector representation of a given input that can be easily consumed by machine learning models and other algorithms.

Instructions

Authentication is done using API Key authentication that can be found in the Azure Portal under Resource Management > Keys and Endpoint.

In order to use the connector it is necessary to deploy models using the Azure AI Studio. 

Some models are suitable for completion like text-davinci-003, others for chat completion like gpt-35-turbo and others for embeddings like text-embedding-ada-002.

This connector requires these configurations:

Settings

ApiKey - API Key configured in Azure Portal for the Open AI Service

ApiVersion - The API version to use for this operation. This follows the YYYY-MM-DD format. Default is 2023-05-15.

AzureOpenAIEndpoint - The endpoint from the Azure Open AI Endpoint, can be found in Azure Portal. Only necessary in case of StreamCompletion and StreamChatCompletion.

ChatCompletionDeploymentId - The deployment name you chose when you deployed the model for Chat Completions. Only necessary in case of StreamChatCompletion and GetChatCompletion.

CompletionDeploymentId - The deployment name you chose when you deployed the model for Completions. Only necessary in case of StreamCompletion and GetCompletion.

EmbeddingDeploymentId - The deployment name you chose when you deployed the model for Embedding. Only necessary in case of CreateEmbedding.

Consumed REST APIs

AzureOpenAIServiceAPI - The endpoint from the Azure Open AI Endpoint, can be found in Azure Portal. Only necessary in case of GetCompletion, GetChatCompletion and CreateEmbedding.