discourse/discourse-ai
1
0
Fork 0
mirror of https://github.com/discourse/discourse-ai.git synced 2025-06-29 19:12:15 +00:00
Code Issues Packages Projects Releases Wiki Activity

FIX: Clarify spam response expectations. (#1470)

Browse Source
This commit is contained in:
Roman Rizzi 2025-06-27 16:59:55 -03:00 committed by GitHub
parent 8d943fa29d
commit 57b00526f8
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
lib/personas/spam_detector.rb
View File

@ -44,13 +44,13 @@ module DiscourseAi
- Site description: {site_description} - Site description: {site_description}
- Site top 10 categories: {top_categories} - Site top 10 categories: {top_categories}
Format your response as a JSON object with a one key named "spam", which indicates if a post is spam or legitimate. Format your response as a JSON object with a one key named "spam", which is a boolean that indicates if a post is spam or legitimate.
Your output should be in the following format: Your output should be in the following format:
<output> <output>
{"spam": "xx"} {"spam": xx}
</output> </output>
Where "xx" is true if the post is spam, or false if it's legitimate. Where xx is true if the post is spam, or false if it's legitimate.
PROMPT PROMPT
end end