semantic kernel execise - feedback

[LittleLittleCloud]

Sample 1

Spell error in initilization

Sample 2

• spell error: compilation -> completion

• spell error: whilw -> while

• resonse -> response

Sample 3

• The LLM invokes the funciton call before I even start asking my age when I use gpt-3.5-turbo

Sample 4

• initizing -> initializing and kerenel -> kernel

Sample 5

• Directoty -> Directory

• Whitespace missing and --prerelease tag is missing

• The highlighted using statement has already been added in previous steps

• Need to disable SKEXP warning between step 4 and 5

Sample 6

• Maksure -> make sure

• missing suppress skexp warning in source

• missing Kernel after Semantic

Sample 7

• The Complete sample project section is still for Sample 6

• Sevice -> Service

• kerel -> kernel

• Miss semi-colomn at the end of code snippet

• Not clear on how to invoke web api from console. Do we miss the setup for openapi page?

[zewditu]

Sample 4 does not have "using Microsoft.SemanticKernel.Connectors.OpenAI" these are using statements in sample 4

using Microsoft.Extensions.DependencyInjection;
using Microsoft.Extensions.Logging;
using Microsoft.SemanticKernel;
using Microsoft.SemanticKernel.ChatCompletion;

[zewditu]

For this I do not think you are not on latest

[zewditu]

The LLM invokes the funciton call before I even start asking my age when I use gpt-3.5-turbo

This is OpenAI model specific thing, if we add a persona like chatHistory.AddSystemMessage("Respond only to requested information. If the user says hi just respond greeting do not tell extra information"); It responds only greeting unless otherwise we ask age, but the main goal of this sample is to match Stephen's video not beyond that. Hence, I will update the prompt to the same prompt pattern of Stephen My name is Alice. How old am I? https://youtu.be/jrNfKeGSuCg?t=553

Naïve guess: the reason it responds age when name is provided because its calling behavior is set to AutoInvokeKernelFunctions.