Skip to main content

OpenAI Chat Feature

Feature NameOpenAI Chat
Feature IDCrestApps.OrchardCore.OpenAI

Provides a way to interact with the OpenAI service provider.

Overview​

The OpenAI AI Chat feature enhances the AI Services functionality by integrating OpenAI-compatible models. It provides a suite of services to interact with these models, enabling advanced AI capabilities.

Configuration​

The OpenAI AI Chat feature allows you to connect to any AI provider that adheres to OpenAI API standards, such as DeepSeek, Google Gemini, Together AI, vLLM, Cloudflare Workers AI, and more.

To configure a connection, add the following settings to the appsettings.json file:

{
  "OrchardCore": {
    "CrestApps_AI": {
      "Providers": {
        "OpenAI": {
          "DefaultConnectionName": "openai-cloud",
          "Connections": {
            "openai-cloud": {
              "ApiKey": "<!-- Your API Key Goes Here -->",
              "Deployments": [
                { "Name": "gpt-4o", "Type": "Chat", "IsDefault": true },
                { "Name": "gpt-4o-mini", "Type": "Utility", "IsDefault": true },
                { "Name": "text-embedding-3-large", "Type": "Embedding", "IsDefault": true },
                { "Name": "dall-e-3", "Type": "Image", "IsDefault": true }
              ]
            }
          }
        }
      }
    }
  }
}
Legacy Format (Deprecated)

The following format using ChatDeploymentName, UtilityDeploymentName, etc. is still supported but deprecated. Existing configurations will be auto-migrated at runtime.

{
  "Connections": {
    "openai-cloud": {
      "ApiKey": "...",
      "ChatDeploymentName": "gpt-4o",
      "UtilityDeploymentName": "gpt-4o-mini",
      "EmbeddingDeploymentName": "text-embedding-3-large",
      "ImagesDeploymentName": "dall-e-3"
    }
  }
}

Using AI Deployments​

If the AI Deployments feature is enabled, you can create multiple typed deployments under the same connection. Each deployment has a Type (Chat, Utility, Embedding, Image, SpeechToText) and an optional IsDefault flag. This allows different AI profiles to utilize different models while sharing the same connection. UI dropdowns display deployments grouped by connection for easy selection.

Configuring Other AI Providers​

The OpenAI AI Chat feature supports multiple AI providers that adhere to OpenAI API standards, such as:

Configuring a Provider Example: DeepSeek​

You can configure the DeepSeek connection either through the configuration provider or via the UI using the AI Connection Management feature.

Configuration Using appsettings.json​

To configure DeepSeek, add the following settings:

{
  "OrchardCore": {
    "CrestApps_AI": {
      "Providers": {
        "OpenAI": {
          "DefaultConnectionName": "deepseek",
          "Connections": {
            "deepseek": {
              "Endpoint": "https://api.deepseek.com/v1",
              "ApiKey": "<!-- Your API Key Goes Here -->",
              "Deployments": [
                { "Name": "deepseek-chat", "Type": "Chat", "IsDefault": true }
              ]
            }
          }
        }
      }
    }
  }
}

The DefaultConnectionName under the OpenAI node is required only if you want to set the deepseek connection as the default OpenAI connection when AI profiles use the default setting.

Configuration via AI Connection Management​

If you are using the AI Connection Management feature, you can configure DeepSeek through the UI or by executing the following recipe:

{
  "steps": [
    {
      "name": "AIProviderConnections",
      "connections": [
        {
          "Source": "OpenAI",
          "Name": "deepseek",
          "IsDefault": false,
          "DisplayText": "DeepSeek",
          "Deployments": [
            { "Name": "deepseek-chat", "Type": "Chat", "IsDefault": true }
          ],
          "Properties": {
            "OpenAIConnectionMetadata": {
              "Endpoint": "https://api.deepseek.com/v1",
              "ApiKey": "<!-- DeepSeek API Key -->"
            }
          }
        }
      ]
    }
  ]
}

Configuring Other AI Providers​

To connect to Google Gemini, Together AI, vLLM, or any other supported provider, modify the Endpoint and ApiKey fields accordingly. For example, configuring Google Gemini would look like this:

{
  "OrchardCore": {
    "CrestApps_AI": {
      "Providers": {
        "OpenAI": {
          "DefaultConnectionName": "google-gemini",
          "Connections": {
            "google-gemini": {
              "Endpoint": "https://generativelanguage.googleapis.com/v1",
              "ApiKey": "<!-- Your Google Gemini API Key -->",
              "Deployments": [
                { "Name": "gemini-pro", "Type": "Chat", "IsDefault": true }
              ]
            }
          }
        }
      }
    }
  }
}

You can replace Endpoint with the appropriate URL for each provider.

Configuring Multiple Models​

If you need access to multiple DeepSeek models, you can execute the following recipe to add typed deployments:

{
  "steps": [
    {
      "name": "AIDeployment",
      "deployments": [
        {
          "Name": "deepseek-chat",
          "Type": "Chat",
          "IsDefault": true,
          "ProviderName": "OpenAI",
          "ConnectionName": "deepseek"
        },
        {
          "Name": "deepseek-reasoner",
          "Type": "Chat",
          "ProviderName": "OpenAI",
          "ConnectionName": "deepseek"
        }
      ]
    }
  ]
}

This configuration allows you to access multiple models provided by DeepSeek, such as deepseek-chat (set as the default Chat deployment) and deepseek-reasoner.

By following these steps, you can seamlessly integrate DeepSeek into your AI chat feature, either as a default provider or alongside other AI models.