from src.retriever import SparkSatchel

sparksatchel = SparkSatchel()
result = sparksatchel.retrieve("process this PDF")

User: "Process this PDF"
SparkSatchel: "I recommend pdf-skill because it specializes in PDF documents (92% historical success rate)"

User: "Create a document"
SparkSatchel: "I suggest docx-skill. pdf-skill is also available. Want me to compare them?"

User: "Process data"
SparkSatchel: "Found several matching skills. Which one fits best?
- xlsx-skill: Excel spreadsheet processing
- pandas-skill: Data analysis with Python
- csv-skill: CSV file handling"

# List available models
python scripts/download_model.py --list

# Download default model (already downloaded ✅)
python scripts/download_model.py default

# Download Chinese-optimized model
python scripts/download_model.py chinese

# Download high-accuracy multilingual model
python scripts/download_model.py large

# Download ultra-lightweight English model
python scripts/download_model.py english

# Option A: Use download script
python scripts/download_model.py chinese

# Option B: Manual download
pip install sentence-transformers
python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('shibing624/text2vec-base-chinese')"

# Option A: Use download script
python scripts/download_model.py english

# Option B: Manual download
pip install sentence-transformers
python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('all-MiniLM-L6-v2')"

# Download high-accuracy model
pip install sentence-transformers
python -c "from sentence_transformers import SentenceTransformer; SentenceTransformer('intfloat/multilingual-e5-large')"

# Use OpenAI API (requires API key)
pip install openai

class EmbeddingModel:
    # Change default model
    DEFAULT_MODEL = "shibing624/text2vec-base-chinese"  # Your choice

from src.models.embedding import EmbeddingModel
from src.retriever import SparkSatchel

# Use custom model
custom_model = EmbeddingModel(
    model_name="shibing624/text2vec-base-chinese",
    device="cpu"  # or "cuda" for GPU acceleration
)

# Pass to SparkSatchel
sparksatchel = SparkSatchel(embedding_model=custom_model)

import openai

def openai_embedding(text: str) -> list:
    response = openai.Embedding.create(
        model="text-embedding-3-small",
        input=text
    )
    return response['data'][0]['embedding']

SparkSatchel/
├── SKILL.md              # This file
├── requirements.txt      # Dependencies
├── src/
│   ├── retriever.py      # Main entry point
│   ├── models/           # Embedding models
│   ├── storage/          # Vector DB + history
│   ├── analysis/         # Intent + confidence
│   └── maintenance/      # Health + lifecycle + cache
└── data/                 # Data storage
    ├── collections/      # Vector databases
    └── history.db        # Call history

class SparkSatchel:
    def retrieve(self, user_request: str) -> RetrievalResult:
        """Search and recommend skills"""

    def feedback(self, skill_name: str, success: bool, feedback: str = ""):
        """Record user feedback"""

    def check_health(self) -> Dict:
        """Check system health"""

    def cleanup(self, strategy: dict = None):
        """Execute cache cleanup"""

@dataclass
class RetrievalResult:
    confidence: float              # 0-1
    recommended_skill: str         # Skill name
    reasoning: str                 # Explanation
    alternative_skills: List[str]  # For medium confidence
    candidate_skills: List[Dict]   # For low confidence
    requires_confirmation: bool    # Needs user input?

health = sparksatchel.check_health()
if health["cache"]["needs_cleanup"]:
    print(health["suggestion"])

from src.maintenance.cache import CleanupStrategy

# By age (delete records older than 30 days)
sparksatchel.cleanup(CleanupStrategy.by_age(days=30))

# By count (keep recent 1000 records)
sparksatchel.cleanup(CleanupStrategy.by_count(keep=1000))