from langchain_community.document_loaders import TextLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_chroma import Chroma
import os
from langchain_community.embeddings import DashScopeEmbeddings

ENVIRONMENT = os.environ.get('ENVIRONMENT', 'development')
DIR_NAME = os.path.dirname(__file__)
path = os.path.join(DIR_NAME, '..','config',ENVIRONMENT,"rag.txt")
loader = TextLoader(file_path=path)

docs = loader.load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=300, chunk_overlap=100)
splits = text_splitter.split_documents(docs)
out_dir = os.path.join(DIR_NAME, '..', 'chroma_db')
vectorstore = Chroma.from_documents(documents=splits, embedding=DashScopeEmbeddings(), persist_directory=out_dir)
print("向量数据库更新完毕")