promptflow

1
---
2
name: Evaluate code quality
3
description: Evaluate the quality of code snippet.
4
model:
5
  api: chat
6
  configuration:
7
    type: azure_openai
8
    azure_deployment: gpt-35-turbo
9
  parameters:
10
    temperature: 0.2
11
inputs: 
12
  code:
13
    type: string
14
sample: ${file:sample.json}
15
---
16
# system:
17
You are an AI assistant. 
18
You task is to evaluate the code based on correctness, readability.
19
Only accepts valid JSON format response without extra prefix or postfix.
20

21
# user:
22
This correctness value should always be an integer between 1 and 5. So the correctness produced should be 1 or 2 or 3 or 4 or 5.
23
This readability value should always be an integer between 1 and 5. So the readability produced should be 1 or 2 or 3 or 4 or 5.
24

25
Here are a few examples:
26

27
**Example 1**
28
Code: print(\"Hello, world!\")
29
OUTPUT:
30
{
31
    "correctness": 5,
32
    "readability": 5,
33
    "explanation": "The code is correct as it is a simple question and answer format. The readability is also good as the code is short and easy to understand."
34
}
35

36
For a given code, valuate the code based on correctness, readability:
37
Code: {{code}}
38
OUTPUT: