constants.py

import os

# from dotenv import load_dotenv
from chromadb.config import Settings

# https://python.langchain.com/en/latest/modules/indexes/document_loaders/examples/excel.html?highlight=xlsx#microsoft-excel
from langchain.document_loaders import CSVLoader, PDFMinerLoader, TextLoader, UnstructuredExcelLoader, Docx2txtLoader

# load_dotenv()
ROOT_DIRECTORY = os.path.dirname(os.path.realpath(__file__))

# Define the folder for storing database
SOURCE_DIRECTORY = f"{ROOT_DIRECTORY}/SOURCE_DOCUMENTS"

PERSIST_DIRECTORY = f"{ROOT_DIRECTORY}/DB"

# Can be changed to a specific number
INGEST_THREADS = os.cpu_count() or 8

# Define the Chroma settings
CHROMA_SETTINGS = Settings(
    chroma_db_impl="duckdb+parquet", persist_directory=PERSIST_DIRECTORY, anonymized_telemetry=False
)

# https://python.langchain.com/en/latest/_modules/langchain/document_loaders/excel.html#UnstructuredExcelLoader
DOCUMENT_MAP = {
    ".txt": TextLoader,
    ".md": TextLoader,
    ".py": TextLoader,
    ".pdf": PDFMinerLoader,
    ".csv": CSVLoader,
    ".xls": UnstructuredExcelLoader,
    ".xlxs": UnstructuredExcelLoader,
    ".docx": Docx2txtLoader,
    ".doc": Docx2txtLoader,
}

# Default Instructor Model
EMBEDDING_MODEL_NAME = "hkunlp/instructor-large"
# You can also choose a smaller model, don't forget to change HuggingFaceInstructEmbeddings
# to HuggingFaceEmbeddings in both ingest.py and run_localGPT.py
# EMBEDDING_MODEL_NAME = "all-MiniLM-L6-v2"