is there a reason why sk vs-code plugin would output different / better response than python sk inline code? #5311
Answered
by
madsbolaris
selfishark
asked this question in
Q&A
-
|
Is there any reason why an ai model (for instance azure open ai gpt-4) will output an incomplete (with duplicate data) response when using inline code (semantic kernel plugin from directory) whereas when using the semantic kernel extension on vs-code the same prompt (from the plugin directory) output and clear and complete response without duplicates? |
Beta Was this translation helpful? Give feedback.
Answered by
madsbolaris
Apr 1, 2024
Replies: 1 comment 1 reply
-
|
They should behave the same. Can you confirm that you are using the same model? And can you share the code and prompt you are using to run the prompt using Semantic Kernel? |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
sophialagerkranspandey
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
They should behave the same. Can you confirm that you are using the same model? And can you share the code and prompt you are using to run the prompt using Semantic Kernel?