SETUP.md

# Setup Instructions for ClarityGuard Space

## Required Secrets

Set these secrets in your HuggingFace Space settings:

1. Go to: https://huggingface.co/spaces/CharlieBonito/ClarityGuardAgent/settings
2. Add these secrets:
   - `JINA_API_KEY`: Your Jina API key (optional, enables RAG)
   - `HF_TOKEN`: Not needed for inference, only for model upload

## Upload Steps

### Step 1: Create a Write Token
1. Go to https://huggingface.co/settings/tokens
2. Create a new token with **Write** permissions
3. Copy the token

### Step 2: Upload the Space Files
```bash
cd /home/charlie/charlielinux/hugginclarity/ClarityGuardAgent

# Login with write token
huggingface-cli login --token YOUR_WRITE_TOKEN --add-to-git-credential

# Push to Space
git add .
git commit -m "Add ClarityGuard implementation with RAG"
git push
```

### Step 3: Upload the Model
```bash
# Create model repository
python3 << 'EOF'
from huggingface_hub import HfApi
api = HfApi()
api.create_repo("CharlieBonito/clarity-guard-gemma4-7b", repo_type="model", exist_ok=True)
EOF

# Upload active ClarityGuard v2 model files (this will take ~30-60 minutes for 5GB)
huggingface-cli upload CharlieBonito/clarity-guard-gemma4-7b \
    /home/charlie/charlielinux/finalversion/models/ClarityGuard-v2.gguf \
    ClarityGuard-v2.gguf

huggingface-cli upload CharlieBonito/clarity-guard-gemma4-7b \
    /home/charlie/charlielinux/finalversion/models/mmproj-ClarityGuard-v2.gguf \
    mmproj-ClarityGuard-v2.gguf
```

### Step 4: Enable ZeroGPU
1. Go to Space settings
2. Enable ZeroGPU
3. The Space will automatically use GPU when available

## Architecture

```
User Input
    ↓
Gradio Interface
    ↓
ClarityGuard Prompt + RAG Context
    ↓
ClarityGuard v2 / Gemma 4 E4B IT checkpoint 750 (GPU Space)
    ↓
Structured Analysis (C.F.R.V.A.)
    ↓
User Response
```

## Competition Categories

- Digital Equity & Inclusivity ($10,000)
- Safety & Trust ($10,000)
- Unsloth Track ($10,000)
- llama.cpp Track ($10,000)