"""
Configuration for Hugging Face API integration.
Contains model IDs, API endpoints, and other configuration parameters.
"""

# Norwegian LLM options
LLM_MODELS = {
    "normistral": {
        "model_id": "norallm/normistral-7b-scratch",
        "description": "NorMistral 7B - Norwegian language model based on Mistral architecture"
    },
    "viking": {
        "model_id": "silo-ai/viking-7b",
        "description": "Viking 7B - Multilingual model for Nordic languages"
    },
    "norskgpt": {
        "model_id": "NbAiLab/NorskGPT",
        "description": "NorskGPT - Norwegian language model"
    }
}

# Default LLM model
DEFAULT_LLM_MODEL = "normistral"

# Norwegian embedding models
EMBEDDING_MODELS = {
    "nb-sbert": {
        "model_id": "NbAiLab/nb-sbert-base",
        "description": "NB-SBERT-BASE - Norwegian sentence embedding model"
    },
    "simcse": {
        "model_id": "FFI/SimCSE-NB-BERT-large",
        "description": "SimCSE-NB-BERT-large - Norwegian sentence embedding model"
    }
}

# Default embedding model
DEFAULT_EMBEDDING_MODEL = "nb-sbert"

# Hugging Face API endpoints
HF_API_ENDPOINTS = {
    "inference": "https://api-inference.huggingface.co/models/",
    "feature-extraction": "https://api-inference.huggingface.co/pipeline/feature-extraction/"
}

# API request parameters
API_PARAMS = {
    "max_length": 512,
    "temperature": 0.7,
    "top_p": 0.9,
    "top_k": 50,
    "repetition_penalty": 1.1
}

# Document processing parameters
CHUNK_SIZE = 512
CHUNK_OVERLAP = 100

# RAG parameters
MAX_CHUNKS_TO_RETRIEVE = 5
SIMILARITY_THRESHOLD = 0.75