(Visual FoxPro) Prove Stateful Multi-Turn Conversation

See more AI Examples

Note: This example requires Chilkat v11.2.0 or greater.

Chilkat ActiveX Downloads ActiveX for 32-bit and 64-bit Windows

LOCAL lnSuccess
LOCAL loAi
LOCAL lcSystemMsg
LOCAL lcDeveloperMsg
LOCAL lcConversationName
LOCAL loSbResponse
LOCAL loJson

lnSuccess = 0

* This example assumes the Chilkat API to have been previously unlocked.
* See Global Unlock Sample for sample code.

loAi = CreateObject('Chilkat.Ai')

* The provider can be "openai", "google", "claude", "deepseek", "xai", or "perplexity".
* Support for additional providers will be added in future versions of Chilkat.
loAi.Provider = "google"

* Use your provider's API key.
loAi.ApiKey = "MY_API_KEY"

* Choose a model.
loAi.Model = "gemini-2.5-flash"

* Create a new conversation to be maintained locally in memory.
* If the conversation is the first to be created, it is also automatically selected.
lcSystemMsg = "You are a helpful assistant"
lcDeveloperMsg = ""
lcConversationName = "test_conversation"
loAi.NewConvo(lcConversationName,lcSystemMsg,lcDeveloperMsg)

* -------------------------------------------------------------------------------------------
* Our first request will establish a secret that we'll ask for in the 2nd request.
* Add a text input.
loAi.InputAddText("Please remember this: The word I'll ask for later is BlubberFish.  What's the word?")

* Ask the AI for text output.
lnSuccess = loAi.Ask("text")
IF (lnSuccess = 0) THEN
    ? loAi.LastErrorText
    RELEASE loAi
    CANCEL
ENDIF

* Note: The inputs accumulated through one or more calls to Input* methods are cleared when the Ask method returns with success.

* Get the text response.
loSbResponse = CreateObject('Chilkat.StringBuilder')
loAi.GetOutputTextSb(loSbResponse)
? loSbResponse.GetAsString()
? "----"

* Sample output:

* The word is **BlubberFish**.

* -------------------------------------------------------------------------------------------
* Let's ask for the word. If this is a stateful conversation, the AI should respond correctly.
loAi.InputAddText("OK, I'm going to ask you again, what's the word?")
lnSuccess = loAi.Ask("text")
IF (lnSuccess = 0) THEN
    ? loAi.LastErrorText
    RELEASE loAi
    RELEASE loSbResponse
    CANCEL
ENDIF

* Get the text response.
loSbResponse.Clear()
loAi.GetOutputTextSb(loSbResponse)
? loSbResponse.GetAsString()

* Sample output:

* The word is **BlubberFish**.

* -------------------------------------------------------------------------------------------
* Look at the conversation so far...
* 
loJson = CreateObject('Chilkat.JsonObject')
loAi.ExportConvo(lcConversationName,loJson)
loJson.EmitCompact = 0
? loJson.Emit()

* Note: The conversation transcript format exported and imported by Chilkat is always the OpenAI format,
* regardless of the AI provider.  (Chilkat translates the format from OpenAI to whatever is needed by the actual AI provider being used.)

* {
*   "input": [
*     {
*       "role": "system",
*       "content": [
*         {
*           "type": "input_text",
*           "text": "You are a helpful assistant"
*         }
*       ]
*     },
*     {
*       "role": "user",
*       "content": [
*         {
*           "type": "input_text",
*           "text": "Please remember this: The word I'll ask for later is BlubberFish.  What's the word?"
*         }
*       ]
*     },
*     {
*       "role": "assistant",
*       "content": [
*         {
*           "type": "output_text",
*           "text": "The word is **BlubberFish**."
*         }
*       ]
*     },
*     {
*       "role": "user",
*       "content": [
*         {
*           "type": "input_text",
*           "text": "OK, I'm going to ask you again, what's the word?"
*         }
*       ]
*     },
*     {
*       "role": "assistant",
*       "content": [
*         {
*           "type": "output_text",
*           "text": "The word is **BlubberFish**."
*         }
*       ]
*     }
*   ]
* }

* -------------------------------------------------------------------------------------------
* If we unselect the conversation, so that no conversation is selected,
* then the same query results in the AI not knowing the word.

loAi.SelectedConvo = ""

loAi.InputAddText("OK, I'm going to ask you again, what's the word?")
lnSuccess = loAi.Ask("text")
IF (lnSuccess = 0) THEN
    ? loAi.LastErrorText
    RELEASE loAi
    RELEASE loSbResponse
    RELEASE loJson
    CANCEL
ENDIF

* Get the text response.
loSbResponse.Clear()
loAi.GetOutputTextSb(loSbResponse)
? loSbResponse.GetAsString()

* Sample output:

* I apologize, but I don't have the context of our previous interaction or what "the word" you're referring to might be.
* Could you please remind me or provide the clue again? I'm ready to help you figure it out!

RELEASE loAi
RELEASE loSbResponse
RELEASE loJson