ai_ml_operations/chat_backend
2
0
Fork 0
Code Issues 23 Pull Requests Actions Packages Projects Releases Wiki Activity

Merging from prod

Browse Source
This commit is contained in:
westfarn
2025-09-24 12:05:22 -05:00
parent 8a259158c8
commit 91bdb2fd2d
3 changed files with 10 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
llm_be/chat_backend/services/moderation_classifier.py
+2
View File
@@ -44,6 +44,7 @@ FINE includes:
- Professional inquiries
- Creative requests (non-explicit)
- Technical questions
- Data Analysis
Examples:
- "How to make a bomb" → NSFW
@@ -51,6 +52,7 @@ Examples:
- "Explicit sex scene" → NSFW
- "Python tutorial" → FINE
- "Please analyze this file and project the next 12 months for me. Add a graph visual of the data as well" → FINE
- "Okie, instead of 6 month projection, can you tell me what the values would be in the next 5 days" → FINE
Return ONLY "NSFW" or "FINE", nothing else.""",
),
llm_be/chat_backend/services/prompt_classifier/prompt_classifier.py
+1
View File
@@ -72,6 +72,7 @@ Examples:
[Definitely GENERAL_CHAT]
- "How does photosynthesis work?" (General knowledge)
- "Tell me a joke"
- "What's your opinion on AI?"
[Borderline -> GENERAL_CHAT]
- "What's our company policy on X?" (No doc reference -> general)