B4X Requires Chilkat v11.3.0+

XLSX Spreadsheet in AI Query

See more AI Examples

This example shows how to convert a .xlsx spreadsheet to CSV text for input in an AI query. Currently, most AIs can't handle Excel file inputs directly. If the spreadsheet is small, you can convert it to CSV text and use it as a text input. B4X

Dim success As Boolean = False

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

'  .xlsx files are Zip archives
Dim zip As ChilkatZip
zip.Initialize("zip")
success = zip.OpenZip("qa_data/excel/fakeCompanies.xlsx")
If success = False Then
    Log(zip.LastErrorText)
    Return
End If


Dim csv As ChilkatCsv
csv.Initialize
Dim sheetNames As ChilkatStringTable
sheetNames.Initialize
success = csv.XlsxGetSheets(zip, sheetNames)
If success = False Then
    Log(csv.LastErrorText)
    Return
End If


If sheetNames.Count = 0 Then
    Log("There are no sheets in the .xlsx")
    Return
End If


'  Get the name of the 1st sheet.
Dim sheetName As String = sheetNames.StringAt(0)

'  Load the 1st sheet into the CSV.
'  We could've also loaded the 1st sheet by passing an empty string for the sheet name.
success = csv.XlsxLoadSheet(zip, sheetName)
If success = False Then
    Log(zip.LastErrorText)
    Return
End If


Dim sbCsv As ChilkatStringBuilder
sbCsv.Initialize
csv.SaveToSb(sbCsv)

'  ------------------------------------------
Dim ai As ChilkatAi
ai.Initialize("ai")

ai.Provider = "openai"

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

'  Choose a model.
ai.Model = "gpt-5.6-terra"

'  Add text inputs
ai.InputAddText("Describe what is contained in the following CSV data.")
ai.InputAddTextSb(sbCsv)

'  Ask the AI for text output.
success = ai.Ask("text")
If success = False Then
    Log(ai.LastErrorText)
    Return
End If


'  Get the text response.
Dim sbResponse As ChilkatStringBuilder
sbResponse.Initialize
ai.GetOutputTextSb(sbResponse)
Log(sbResponse.GetAsString)

'  Sample output:

'  The CSV data contains information about five companies, including the following fields:
'  
'  1. **CompanyName**: The name of the company.
'  2. **Address**: The street address of the company.
'  3. **City**: The city where the company is located.
'  4. **State**: The state where the company is located, abbreviated.
'  5. **Zip**: The ZIP code for the company's location.
'  6. **Phone**: The phone number of the company.
'  
'  Each row in the dataset corresponds to a different company with details provided for each of these fields:
'  
'  ...
'  ...

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