(Visual FoxPro) Conversation with Streaming Responses

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 loSbEventName
LOCAL loSbDelta
LOCAL loSbFullResponse
LOCAL lnFinished
LOCAL lnAbortFlag
LOCAL lnMaxWaitMs
LOCAL lnResult
LOCAL lnResult

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"

* Indicate streaming mode is to be used.
loAi.Streaming = 1

* 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 creative storyteller"
lcDeveloperMsg = ""
lcConversationName = "test_conversation"
loAi.NewConvo(lcConversationName,lcSystemMsg,lcDeveloperMsg)

* Add a text input.
loAi.InputAddText("Write a detailed story about a turtle who decides to run a bakery.  Describe the setting, the kinds of pastries, how the turtle feels, and include at least three paragraphs.")

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

loSbEventName = CreateObject('Chilkat.StringBuilder')
loSbDelta = CreateObject('Chilkat.StringBuilder')
loSbFullResponse = CreateObject('Chilkat.StringBuilder')
lnFinished = 0
lnAbortFlag = 0
lnMaxWaitMs = 5000

DO WHILE NOT lnFinished

    lnResult = loAi.PollAi(lnAbortFlag)
    IF (lnResult = 1) THEN
        * We have output waiting.  It should be instantly available.  The maxWaitMs is just-in-case.
        lnSuccess = loAi.NextAiEvent(lnMaxWaitMs,loSbEventName,loSbDelta)
        IF (lnSuccess = 0) THEN
            ? loAi.LastErrorText
            RELEASE loAi
            RELEASE loSbEventName
            RELEASE loSbDelta
            RELEASE loSbFullResponse
            CANCEL
        ENDIF

        * Some AI providers send many "empty" events.  Just ignore them.
        IF (NOT loSbEventName.ContentsEqual("empty",1)) THEN

            * The delta contains the new output.  This could be emitted to a display or the terminal
            * as real-time output.
            IF (loSbEventName.ContentsEqual("delta",1)) THEN
                * This example will emit each delta to its own line.
                ? loSbDelta.GetAsString()

                * Accumulate the delta's so we can show the full response later.
                loSbFullResponse.AppendSb(loSbDelta)
            ELSE
                * A streaming AI response is always terminated by a single "null_terminator" event.
                lnFinished = loSbEventName.ContentsEqual("null_terminator",1)
            ENDIF

        ENDIF

    ELSE
        IF (lnResult = 0) THEN
            * Nothing is immediately available. Sleep for 1/10 of a second before polling again.
            loAi.SleepMs(100)
        ELSE
            * Something failed..
            ? loAi.LastErrorText
            lnFinished = 1
        ENDIF

    ENDIF

ENDDO

* -------------------------------------------------------------
* The response is in markdown format.
* Also see Markdown to HTML Conversion Examples.
* -------------------------------------------------------------

* Show the accumulated (full) response.
? "----"
? loSbFullResponse.GetAsString()
? "----"

* ----------------------------------------------------------------------------------------------------------
* For the 2nd request in this conversation, ask for a shorter version of the story.
loAi.InputAddText("Rewrite the story, but this time make it shorter, about one third as long.")
lnSuccess = loAi.Ask("text")
IF (lnSuccess = 0) THEN
    ? loAi.LastErrorText
    RELEASE loAi
    RELEASE loSbEventName
    RELEASE loSbDelta
    RELEASE loSbFullResponse
    CANCEL
ENDIF

loSbFullResponse.Clear()
lnFinished = 0

DO WHILE NOT lnFinished

    lnResult = loAi.PollAi(lnAbortFlag)
    IF (lnResult = 1) THEN
        * We have output waiting.  It should be instantly available.  The maxWaitMs is just-in-case.
        lnSuccess = loAi.NextAiEvent(lnMaxWaitMs,loSbEventName,loSbDelta)
        IF (lnSuccess = 0) THEN
            ? loAi.LastErrorText
            RELEASE loAi
            RELEASE loSbEventName
            RELEASE loSbDelta
            RELEASE loSbFullResponse
            CANCEL
        ENDIF

        * Some AI providers send many "empty" events.  Just ignore them.
        IF (NOT loSbEventName.ContentsEqual("empty",1)) THEN

            * The delta contains the new output.  This could be emitted to a display or the terminal
            * as real-time output.
            IF (loSbEventName.ContentsEqual("delta",1)) THEN
                * This example will emit each delta to its own line.
                ? loSbDelta.GetAsString()

                * Accumulate the delta's so we can show the full response later.
                loSbFullResponse.AppendSb(loSbDelta)
            ELSE
                * A streaming AI response is always terminated by a single "null_terminator" event.
                lnFinished = loSbEventName.ContentsEqual("null_terminator",1)
            ENDIF

        ENDIF

    ELSE
        IF (lnResult = 0) THEN
            * Nothing is immediately available. Sleep for 1/10 of a second before polling again.
            loAi.SleepMs(100)
        ELSE
            * Something failed..
            ? loAi.LastErrorText
            lnFinished = 1
        ENDIF

    ENDIF

ENDDO

? "----"
? loSbFullResponse.GetAsString()

RELEASE loAi
RELEASE loSbEventName
RELEASE loSbDelta
RELEASE loSbFullResponse