[modify] rag file system

This commit is contained in:
Mark
2026-04-27 16:05:27 +08:00
parent 3b359df02f
commit 30cdf229de
8 changed files with 228 additions and 348 deletions

View File

@@ -305,38 +305,25 @@ async def parse_documents(
detail="The file does not exist or you do not have permission to access it"
)
# 3. Construct file path/files/{kb_id}/{parent_id}/{file.id}{file.file_ext}
file_path = os.path.join(
settings.FILE_PATH,
str(db_file.kb_id),
str(db_file.parent_id),
f"{db_file.id}{db_file.file_ext}"
)
# 4. Check if the file exists
api_logger.debug(f"Constructed file path: {file_path}")
api_logger.debug(f"File metadata - kb_id: {db_file.kb_id}, parent_id: {db_file.parent_id}, file_id: {db_file.id}, extension: {db_file.file_ext}")
if not os.path.exists(file_path):
api_logger.error(f"File not found (possibly deleted): file_path={file_path}, file_id={db_file.id}, document_id={document_id}")
# 3. Get file_key for storage backend
if not db_file.file_key:
api_logger.error(f"File has no storage key (legacy data not migrated): file_id={db_file.id}")
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="File not found (possibly deleted)"
detail="File has no storage key (legacy data not migrated)"
)
# 5. Obtain knowledge base information
api_logger.info( f"Obtain details of the knowledge base: knowledge_id={db_document.kb_id}")
# 4. Obtain knowledge base information
api_logger.info(f"Obtain details of the knowledge base: knowledge_id={db_document.kb_id}")
db_knowledge = knowledge_service.get_knowledge_by_id(db, knowledge_id=db_document.kb_id, current_user=current_user)
if not db_knowledge:
api_logger.warning(f"The knowledge base does not exist or access is denied: knowledge_id={db_document.kb_id}")
raise HTTPException(
status_code=status.HTTP_404_NOT_FOUND,
detail="The knowledge base does not exist or access is denied"
)
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Knowledge base not found")
# 6. Task: Document parsing, vectorization, and storage
# from app.tasks import parse_document
# parse_document(file_path, document_id)
task = celery_app.send_task("app.core.rag.tasks.parse_document", args=[file_path, document_id])
# 5. Dispatch parse task with file_key (not file_path)
task = celery_app.send_task(
"app.core.rag.tasks.parse_document",
args=[db_file.file_key, document_id, db_file.file_name]
)
result = {
"task_id": task.id
}