khanh152010/AI_Emotional_Mirror
🪞 Reflect on your emotions with AI Emotional Mirror, a tool that gently clarifies thoughts without offering advice or judgment.
What's novel
🪞 Reflect on your emotions with AI Emotional Mirror, a tool that gently clarifies thoughts without offering advice or judgment.
Code Analysis
6 files read · 2 roundsA Streamlit app that takes user text, runs it through a pre-trained DistilRoBERTa emotion classifier, generates a basic word-frequency extractive summary, and calls the Groq Llama 3.1 API to produce a two-sentence calm reflection.
Strengths
Clean pipeline separation into small focused modules (text_utils, summarizer, emotion_model, reflector) makes the flow easy to follow. The emotion detection uses a legitimate pre-trained model and the reflection prompt engineering (no advice, no diagnosis, limited length) shows some thoughtfulness.
Weaknesses
No tests, dead imports (spacy, scikit-learn, requests), the Groq client crashes at import time if the API key is missing, and the summarizer is a trivial word-frequency approach. The README is heavily padded with marketing language and a suspicious download link, and claims features (save reflections, help section) that don't exist in the code.
Score Breakdown
Signal breakdown
Innovation
Craft
Traction
Scope
Evidence
Commits
9
Contributors
2
Files
10
Active weeks
3
Repository
Language
Python
Stars
1
Forks
0
License
—