Update README.md
Browse files
README.md
CHANGED
|
@@ -1,31 +1,14 @@
|
|
| 1 |
---
|
| 2 |
-
title: "LLMGuard – Prompt
|
| 3 |
emoji: 🛡️
|
| 4 |
colorFrom: indigo
|
| 5 |
colorTo: blue
|
| 6 |
sdk: streamlit
|
| 7 |
sdk_version: 1.32.0
|
| 8 |
-
app_file: app.py
|
| 9 |
pinned: false
|
| 10 |
-
license: mit
|
| 11 |
---
|
| 12 |
|
| 13 |
-
# 🛡️ LLMGuard – Prompt
|
| 14 |
-
|
| 15 |
-
LLMGuard is a real-time LLM security and moderation toolkit designed to:
|
| 16 |
-
- Detect and block prompt injection attacks
|
| 17 |
-
- Moderate harmful, unsafe, or policy-violating content
|
| 18 |
-
- Log moderation events for auditing
|
| 19 |
-
|
| 20 |
-
**Features:**
|
| 21 |
-
- 🔍 Prompt Injection Detection
|
| 22 |
-
- ⚠️ Harmful Content Moderation
|
| 23 |
-
- 🗂 Moderation History Panel
|
| 24 |
-
- 🌐 Deployable via Docker / Hugging Face Spaces / Streamlit Cloud
|
| 25 |
-
|
| 26 |
-
## 🚀 How to run locally
|
| 27 |
-
|
| 28 |
-
```bash
|
| 29 |
-
pip install -r requirements.txt
|
| 30 |
-
streamlit run app.py
|
| 31 |
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
title: "LLMGuard – Prompt Moderation"
|
| 3 |
emoji: 🛡️
|
| 4 |
colorFrom: indigo
|
| 5 |
colorTo: blue
|
| 6 |
sdk: streamlit
|
| 7 |
sdk_version: 1.32.0
|
| 8 |
+
app_file: app/dashboard/streamlit_app.py
|
| 9 |
pinned: false
|
|
|
|
| 10 |
---
|
| 11 |
|
| 12 |
+
# 🛡️ LLMGuard – Prompt Moderation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
|
| 14 |
+
A real-time prompt moderation tool for LLM safety, powered by a custom classifier.
|