delete_files

Function

Deletes a specified document from a knowledge base, which can only be performed by the knowledge base administrator. If the document does not exist, it is skipped. If the document list is empty, an error is reported.

Prototype

from mx_rag.knowledge import delete_files
def delete_files(knowledge, doc_names)

Parameters

Example

from mx_rag.embedding.local import TextEmbedding
from mx_rag.knowledge import KnowledgeStore, KnowledgeDB, upload_files, delete_files, FilesLoadInfo
from mx_rag.document import LoaderMng
from mx_rag.storage.document_store import SQLiteDocstore
from mx_rag.storage.vectorstore import MindFAISS
from langchain.text_splitter import RecursiveCharacterTextSplitter
from mx_rag.knowledge import upload_dir
from mx_rag.document.loader import DocxLoader, PdfLoader, ExcelLoader

loader_mng = LoaderMng()
loader_mng.register_loader(DocxLoader, [".docx"])
loader_mng.register_loader(PdfLoader, [".pdf"])
loader_mng.register_loader(ExcelLoader, [".xlsx"])
# loader_mng.register_loader(ImageLoader, [".png"])
loader_mng.register_splitter(RecursiveCharacterTextSplitter,
                             [".docx", ".pdf", ".xlsx"])
# Set the NPU used for vector retrieval.
dev = 0
# Load the embedding model.
emb = TextEmbedding("/path/to/model", dev_id=dev)
# Initialize the vector database.
vector_store = MindFAISS(x_dim=1024, devs=[dev], 
                         load_local_index="/path/to/index", auto_save=True)
# Initialize the relational database for document chunks.
chunk_store = SQLiteDocstore(db_path="./sql.db")
# Initialize the relational database for knowledge management.
knowledge_store = KnowledgeStore(db_path="./sql.db")
# Add a knowledge base and its administrator.
knowledge_store.add_knowledge(knowledge_name="test", user_id='Default', role='admin')
# Initialize knowledge management.
knowledge_db = KnowledgeDB(knowledge_store=knowledge_store, chunk_store=chunk_store, vector_store=vector_store,
                           knowledge_name="test", user_id='Default', white_paths=["/home/"])
# Upload domain-specific knowledge documents.
# Call upload_files.
upload_files(knowledge=knowledge_db, files=["/path/data/test.docx"], loader_mng=loader_mng,
             embed_func=emb.embed_documents, force=True)
# Upload the directory of domain-specific documents.
# Call upload_dir.
params = FilesLoadInfo(knowledge=knowledge_db, dir_path="/path/data/files", loader_mng=loader_mng,
                       embed_func=emb.embed_documents, force=True, load_image=False)
upload_dir(params=params)
# Call delete_files.
delete_files(knowledge_db, ["test.docx"])