.Net: Kernel function arguments cannot be complex type (e.g., array)

[ameier38]

Describe the bug
I am trying to create a kernel function to sum an array of numbers however if I use an array as the function argument I get the error Function failed. Error: Object of type 'System.String' cannot be converted to type 'System.Double[]'.

To Reproduce
From the logs it looks like openai function call is correct.

{"function":{"name":"MathPlugin_Sum","description":"Sum an array of numbers.","parameters":{"type":"object","required":["numbers"],"properties":{"numbers":{"type":"array","items":{"type":"number"},"description":"The array of numbers to sum."}}}},"type":"function"}

"tool_calls": [
          {
            "id": "call_wj6NbjHTo1C4ErXMO0XyBU9e",
            "type": "function",
            "function": {
              "name": "MathPlugin_Sum",
              "arguments": "{\"numbers\": [1.1, 2.2, 3.3]}"
            }
          }
        ]

LogRecord.Severity:                Trace
LogRecord.SeverityText:            Trace
LogRecord.FormattedMessage:        Function call requests: MathPlugin_Sum({"numbers":[1.1,2.2,3.3]})
LogRecord.Body:                    Function call requests: {Requests}
LogRecord.Attributes (Key:Value):
    Requests: MathPlugin_Sum({"numbers":[1.1,2.2,3.3]})
    OriginalFormat (a.k.a Body): Function call requests: {Requests}

However later on it looks like the method is being called with a string.

LogRecord.Timestamp:               2024-01-22T16:57:32.0827729Z
LogRecord.TraceId:                 2f4f4d4f22bfdc2eba3093ee96725edb
LogRecord.SpanId:                  fd6afb6fd9204111
LogRecord.TraceFlags:              Recorded
LogRecord.CategoryName:            Sum
LogRecord.Severity:                Trace
LogRecord.SeverityText:            Trace
LogRecord.FormattedMessage:        Function arguments: {"numbers":"[1.1,2.2,3.3]"}
LogRecord.Body:                    Function arguments: {Arguments}
LogRecord.Attributes (Key:Value):
    Arguments: {"numbers":"[1.1,2.2,3.3]"}
    OriginalFormat (a.k.a Body): Function arguments: {Arguments}

Here is my F# script. Run with dotnet fsi script.fsx.

#r "nuget: OpenTelemetry"
#r "nuget: OpenTelemetry.Instrumentation.Http"
#r "nuget: OpenTelemetry.Exporter.Console"
#r "nuget: Microsoft.Extensions.Logging"
#r "nuget: Microsoft.Extensions.Logging.Console"
#r "nuget: Microsoft.SemanticKernel"

open Microsoft.Extensions.Logging
open Microsoft.Extensions.DependencyInjection
open Microsoft.SemanticKernel
open Microsoft.SemanticKernel.ChatCompletion
open Microsoft.SemanticKernel.Connectors.OpenAI
open OpenTelemetry
open OpenTelemetry.Resources
open OpenTelemetry.Logs
open OpenTelemetry.Trace
open System.ComponentModel
open System
open System.Diagnostics
open System.IO
open System.Net.Http

module Env =
    let variable key =
        match Environment.GetEnvironmentVariable(key) with
        | s when String.IsNullOrEmpty(s) -> failwith $"Environment variable {key} is not set"
        | value -> value

type MathPlugin(loggerFactory:ILoggerFactory) =
    let logger = loggerFactory.CreateLogger<MathPlugin>()

    [<KernelFunction>]
    [<Description("Sum an array of numbers.")>]
    member _.Sum
        ([<Description("The array of numbers to sum.")>] numbers:float[])
         : [<Description("The sum of the numbers.")>] float =
        logger.LogDebug("Summing numbers {numbers}", numbers)
        Array.sum(numbers)

let resourceBuilder = ResourceBuilder.CreateDefault().AddService("Scratch")

let enrichHttpRequest (activity:Activity) (req:HttpRequestMessage) =
    req.Content.LoadIntoBufferAsync().Wait()
    let ms = new MemoryStream()
    req.Content.CopyToAsync(ms).Wait()
    ms.Seek(0L, SeekOrigin.Begin) |> ignore
    use reader = new StreamReader(ms)
    let content = reader.ReadToEnd()
    activity.SetTag("requestBody", content) |> ignore

let enrichHttpResponse (activity:Activity) (res:HttpResponseMessage) =
    res.Content.LoadIntoBufferAsync().Wait()
    let ms = new MemoryStream()
    res.Content.CopyToAsync(ms).Wait()
    ms.Seek(0L, SeekOrigin.Begin) |> ignore
    use reader = new StreamReader(ms)
    let content = reader.ReadToEnd()
    activity.SetTag("responseBody", content) |> ignore

let tracerProvider =
    Sdk.CreateTracerProviderBuilder()
        .SetResourceBuilder(resourceBuilder)
        .AddSource("Scratch") // subscribe to Scratch resource (created above) traces
        .AddSource("Microsoft.SemanticKernel*") // subscribe to semantic kernel traces
        .AddHttpClientInstrumentation(fun opts ->
            opts.EnrichWithHttpRequestMessage <- Action<Activity,HttpRequestMessage>(enrichHttpRequest)
            opts.EnrichWithHttpResponseMessage <- Action<Activity,HttpResponseMessage>(enrichHttpResponse))
        .AddConsoleExporter()
        .Build()
let loggerFactory =
    LoggerFactory.Create(fun builder ->
        builder
            .SetMinimumLevel(LogLevel.Trace)
            .AddOpenTelemetry(fun opts ->
                opts.SetResourceBuilder(resourceBuilder) |> ignore
                opts.AddConsoleExporter() |> ignore // export logs to console
                opts.IncludeFormattedMessage <- true)
            |> ignore)
let apiKey = Env.variable "OPENAI_API_KEY"
let builder = Kernel.CreateBuilder()
builder.Services.AddSingleton(loggerFactory)
builder.Services.AddOpenAIChatCompletion("gpt-3.5-turbo-1106", apiKey)
builder.Plugins.AddFromType<MathPlugin>()
let kernel = builder.Build()

let tracer = tracerProvider.GetTracer("Scratch")
let settings = OpenAIPromptExecutionSettings(ToolCallBehavior=ToolCallBehavior.AutoInvokeKernelFunctions)
let chatService = kernel.Services.GetRequiredService<IChatCompletionService>()
let history = ChatHistory("You are a friendly analyst. You can add numbers.")

let span = tracer.StartActiveSpan("Solving math problem")
history.AddUserMessage("What is the sum of 1.1, 2.2, and 3.3?")
let res = chatService.GetChatMessageContentAsync(history, settings, kernel).Result
span.Dispose()
printfn $"Response: {res}"

Expected behavior
I am expecting the method to be called with an array of floats instead of a string.

Screenshots
If applicable, add screenshots to help explain your problem.

Platform

• OS: Windows
• IDE: VS Code
• Language: F#
• Source: nuget Micrsoft.SemanticKernel 1.1.0

[stephentoub]

cc: @SergeyMenshykh