__init__.py

import os
from langchain.document_loaders import (
    CSVLoader,
    EverNoteLoader,
    PDFMinerLoader,
    TextLoader,
    UnstructuredEPubLoader,
    UnstructuredHTMLLoader,
    UnstructuredMarkdownLoader,
    UnstructuredODTLoader,
    UnstructuredPowerPointLoader,
    UnstructuredWordDocumentLoader,
)


FAVICON_PATH: str = 'https://modishcard.com/app/assets/icons/ModishCard_Logo6-02.svg'
SYSTEM_PROMPT: str = "You are Saiga, a Englis-speaking automated assistant. You talk to people and help them."
SYSTEM_TOKEN: int = 1788
USER_TOKEN: int = 1404
BOT_TOKEN: int = 9225
LINEBREAK_TOKEN: int = 13

ROLE_TOKENS: dict = {
    "user": USER_TOKEN,
    "bot": BOT_TOKEN,
    "system": SYSTEM_TOKEN
}

LOADER_MAPPING: dict = {
    ".csv": (CSVLoader, {}),
    ".doc": (UnstructuredWordDocumentLoader, {}),
    ".docx": (UnstructuredWordDocumentLoader, {}),
    ".enex": (EverNoteLoader, {}),
    ".epub": (UnstructuredEPubLoader, {}),
    ".html": (UnstructuredHTMLLoader, {}),
    ".md": (UnstructuredMarkdownLoader, {}),
    ".odt": (UnstructuredODTLoader, {}),
    ".pdf": (PDFMinerLoader, {}),
    ".ppt": (UnstructuredPowerPointLoader, {}),
    ".pptx": (UnstructuredPowerPointLoader, {}),
    ".txt": (TextLoader, {"encoding": "utf8"}),
}


DICT_REPO_AND_MODELS: dict = {
    "https://huggingface.co/Qwen/Qwen2-0.5B-Instruct-GGUF/resolve/main/qwen2-0_5b-instruct-q8_0.gguf":
        "Qwen/Qwen2-0.5B-Instruct-GGUF",
    "https://huggingface.co/MaziyarPanahi/Qwen2-1.5B-Instruct-GGUF/resolve/main/Qwen2-1.5B-Instruct.Q8_0.gguf":
        "MaziyarPanahi/Qwen2-1.5B-Instruct.Q8_0.gguf",
}

EMBEDDER_NAME: str = "sentence-transformers/paraphrase-multilingual-mpnet-base-v2"

MAX_NEW_TOKENS: int = 1500

ABS_PATH = os.path.dirname(os.path.abspath(__file__))
MODELS_DIR = os.path.join(ABS_PATH, "../models")
AUTH_FILE = os.path.join(ABS_PATH, "auth.csv")


BLOCK_CSS = """

#buttons button {
    min-width: min(120px,100%);
}

"""