kerplunk-ai-prompts 0.1.27 → 0.1.29
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 677bab492e5ecea4dc08893d02d7fca538ba5efad725018ca491594958eb82da
|
4
|
+
data.tar.gz: 9c45c43f46042ec2b1b504d528e38a60cb19f94631aa5fceb23e1bb4c556cb01
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: e54f75633d9ddf8a5151da5dbb5f4cae05df1f87e7371fe721e32464d896c228405082631c8ba24db7963071f5995cf291005e940174e5ba956924678dcbc2db
|
7
|
+
data.tar.gz: 1c0a2680a6e55da9e709f157909fc4b99b1742fc7a784093ce00ea3bbb190a2dd37e5ec949b9e4e4eacace9f9a00834a87e06dcc0f68e504bf15a055ebbbae37
|
@@ -124,7 +124,8 @@ module Kerplunk
|
|
124
124
|
=== The Job Description
|
125
125
|
#{job_description}
|
126
126
|
|
127
|
-
=== The Interview Questions with the Transcript of the Interview Answers (some answers may have a score from a previous analysis, please aggregate these scores by category). Some Interview Questions will provide an array of suggested answers, please evaluate the Transcript answer against the suggested answers where each one could be the correct answer.
|
127
|
+
=== The Interview Questions with the Transcript of the Interview Answers (some answers may have a score from a previous analysis, please aggregate these scores by category). Some Interview Questions will provide an array of suggested answers, please evaluate the Transcript answer against the suggested answers where each one could be the correct answer. For yes/no questions without suggested answers, do not include them in the scoring.
|
128
|
+
|
128
129
|
|
129
130
|
#{question_answer_prompts.join("\n\n")}
|
130
131
|
PROMPT
|
@@ -36,14 +36,14 @@ module Kerplunk
|
|
36
36
|
"Comment 2",
|
37
37
|
"Comment 3"
|
38
38
|
],
|
39
|
-
"score": 4.5#{(question_type.downcase == "
|
39
|
+
"score": 4.5#{(question_type.downcase == "yes_no") ? ',
|
40
40
|
"answer": "Yes" or "No"' : ""}
|
41
41
|
}
|
42
42
|
|
43
43
|
Please remember that the question category is #{question_type} and the question is:
|
44
44
|
#{question}
|
45
45
|
|
46
|
-
#{if question_type.downcase == "
|
46
|
+
#{if question_type.downcase == "yes_no" && user_input
|
47
47
|
"The user selected: #{user_input}\n\n"
|
48
48
|
end}
|
49
49
|
|
@@ -56,7 +56,7 @@ module Kerplunk
|
|
56
56
|
private
|
57
57
|
|
58
58
|
def generate_scoring_instructions(question_type, suggested_answers)
|
59
|
-
if question_type.downcase == "
|
59
|
+
if question_type.downcase == "yes_no"
|
60
60
|
if suggested_answers
|
61
61
|
"Please provide a score from 1 to 100 based on the correctness of the answer, taking into account the user's selected answer. Also, provide three high-level bullet pointed comments about how the candidate did on the question as the `commentary` key. Additionally, please evaluate whether the candidate's answer matches the user's selected answer and provide a score for that as well."
|
62
62
|
else
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: kerplunk-ai-prompts
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.1.
|
4
|
+
version: 0.1.29
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Kyle Schutt
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2024-09-
|
11
|
+
date: 2024-09-27 00:00:00.000000000 Z
|
12
12
|
dependencies: []
|
13
13
|
description: A collection of AI prompt templates for use in Kerplunk
|
14
14
|
email:
|