OpenAI.ImageRecognition.GenerateNext

Method signature

 Function GenerateNext(Role As String, Content As String, Model As OpenAI.Model = Nil) As OpenAI.ImageRecognition
 Function GenerateNext(Role As String, Content As String, Images() As Picture, MaxTokens As Integer = 300, Model As OpenAI.Model = Nil) As OpenAI.ImageRecognition
 Function GenerateNext(Role As String, Content As String, Image As Picture, MaxTokens As Integer = 300, Model As OpenAI.Model = Nil) As OpenAI.ImageRecognition
 Function GenerateNext(Role As String, Content As String, ImageURLs() As String, MaxTokens As Integer = 300, Model As OpenAI.Model = Nil) As OpenAI.ImageRecognition
 Function GenerateNext(Role As String, Content As String, ImageURL As String, MaxTokens As Integer = 300, Model As OpenAI.Model = Nil) As OpenAI.ImageRecognition
 Function GenerateNext(Role As String, Content As String, Images() As FolderItem, MaxTokens As Integer = 300, Model As OpenAI.Model = Nil) As OpenAI.ImageRecognition
 Function GenerateNext(Role As String, Content As String, Image As FolderItem, MaxTokens As Integer = 300, Model As OpenAI.Model = Nil) As OpenAI.ImageRecognition

Parameters

`GenerateNext(String, String, OpenAI.Model)`

Name	Type	Comment
Role	String	One of "user", "assistant", or "system", identifying the speaker of the message.
Content	String	The message that the speaker is sending to the chat.
Model	Model	Optional. An AI model to use for the request. If not specified then `gpt-4-vision-preview` is used.

`GenerateNext(String, String, Picture(), Integer, OpenAI.Model)`

Name	Type	Comment
Role	String	One of "user", "assistant", or "system", identifying the speaker of the message.
Content	String	The message that the speaker is sending to the chat.
Images	Picture array	Two or more images to be interpreted according to the `Content`.
Model	Model	Optional. An AI model to use for the request. If not specified then `gpt-4-vision-preview` is used.

`GenerateNext(String, String, Picture, Integer, OpenAI.Model)`

Name	Type	Comment
Role	String	One of "user", "assistant", or "system", identifying the speaker of the message.
Content	String	The message that the speaker is sending to the chat.
Images	Picture	An image to be interpreted according to the `Content`.
Model	Model	Optional. An AI model to use for the request. If not specified then `gpt-4-vision-preview` is used.

`GenerateNext(String, String, String(), Integer, OpenAI.Model)`

Name	Type	Comment
Role	String	One of "user", "assistant", or "system", identifying the speaker of the message.
Content	String	The message that the speaker is sending to the chat.
ImageURLs	String array	Two or more images to be interpreted according to the `Content`.
Model	Model	Optional. An AI model to use for the request. If not specified then `gpt-4-vision-preview` is used.

`GenerateNext(String, String, String, Integer, OpenAI.Model)`

Name	Type	Comment
Role	String	One of "user", "assistant", or "system", identifying the speaker of the message.
Content	String	The message that the speaker is sending to the chat.
ImageURL	String	An image to be interpreted according to the `Content`.
Model	Model	Optional. An AI model to use for the request. If not specified then `gpt-4-vision-preview` is used.

`GenerateNext(String, String, FolderItem(), Integer, OpenAI.Model)`

Name	Type	Comment
Role	String	One of "user", "assistant", or "system", identifying the speaker of the message.
Content	String	The message that the speaker is sending to the chat.
Images	FolderItem array	Two or more images to be interpreted according to the `Content`.
Model	Model	Optional. An AI model to use for the request. If not specified then `gpt-4-vision-preview` is used.

`GenerateNext(String, String, FolderItem, Integer, OpenAI.Model)`

Name	Type	Comment
Role	String	One of "user", "assistant", or "system", identifying the speaker of the message.
Content	String	The message that the speaker is sending to the chat.
Image	FolderItem	An image to be interpreted according to the `Content`.
Model	Model	Optional. An AI model to use for the request. If not specified then `gpt-4-vision-preview` is used.

Return value

A new instance of ImageRecognition containing the AI's reply to the message.

Remarks

Pass the user's next image recognition message to generate the AI assistant's reply to that message. The AI is provided with a complete transcript of the chat so far to give it the necessary context.

Example

This example demonstrates how to use this method to carry on a chat conversation:

  OpenAI.APIKey = "YOUR API KEY"
  Dim url1 As String = "https://upload.wikimedia.org/wikipedia/commons/9/99/Aerial_view_of_the_White_House.jpg"
  Dim url2 As String = "https://upload.wikimedia.org/wikipedia/commons/b/bd/Taj_Mahal%2C_Agra%2C_India_edit3.jpg"
  
  Dim response As OpenAI.ImageRecognition = OpenAI.ImageRecognition.Create("What is this a photo of?", url1)
  Dim answer As String = response.GetResult() ' This is an aerial photo of the the White House in Washington, DC.
  
  response = response.GenerateNext("user", "What direction is the camera facing?")
  answer = response.GetResult() ' The camera is facing northward.
  
  response = response.GenerateNext("user",  "Is this a picture of the same building?", url2)
  answer = response.GetResult() ' No, this is a photo of the Taj Mahal located in Agra, India.

  ' etc.