OpenRAG is a comprehensive, single package Retrieval-Augmented Generation platform built on Langflow, Docling, and Opensearch.
Python
fix: Index creation on ingest/check duplicate if it doesn't exist (#978)
Mike Fortman3e5b77dc2e3b
diff --git a/src/api/connectors.py b/src/api/connectors.pyindex da76541d2..c5578a802 100644--- a/src/api/connectors.py+++ b/src/api/connectors.py@@ -178,6 +178,8 @@ async def connector_sync(request: Request, connector_service, session_manager):if selected_files:# Explicit files selected (e.g., from file picker) - sync those specific files+ from .documents import _ensure_index_exists+ await _ensure_index_exists()task_id = await connector_service.sync_specific_files(working_connection.connection_id,user.user_id,diff --git a/src/api/documents.py b/src/api/documents.pyindex 8d7d386ec..31f1b2981 100644--- a/src/api/documents.py+++ b/src/api/documents.py@@ -6,6 +6,12 @@ from config.settings import get_index_namelogger = get_logger(__name__)+async def _ensure_index_exists():+ """Create the OpenSearch index if it doesn't exist yet."""+ from main import init_index+ await init_index()++async def check_filename_exists(request: Request, document_service, session_manager):"""Check if a document with a specific filename already exists"""filename = request.query_params.get("filename")@@ -29,10 +35,21 @@ async def check_filename_exists(request: Request, document_service, session_manalogger.debug(f"Checking filename existence", filename=filename, index_name=get_index_name())- response = await opensearch_client.search(- index=get_index_name(),- body=search_body- )+ try:+ response = await opensearch_client.search(+ index=get_index_name(),+ body=search_body+ )+ except Exception as search_err:+ if "index_not_found_exception" in str(search_err):+ logger.info("Index does not exist, creating it now before upload")+ await _ensure_index_exists()+ # Index was just created so no duplicates can exist+ return JSONResponse({+ "exists": False,+ "filename": filename+ }, status_code=200)+ raise# Check if any hits were foundhits = response.get("hits", {}).get("hits", [])diff --git a/src/api/upload.py b/src/api/upload.pyindex 76a137fdc..3eab9b4c4 100644--- a/src/api/upload.py+++ b/src/api/upload.py@@ -74,6 +74,9 @@ async def upload_path(request: Request, task_service, session_manager):owner_name = user.nameowner_email = user.email+ from .documents import _ensure_index_exists+ await _ensure_index_exists()+task_id = await task_service.create_upload_task(owner_user_id,file_paths,@@ -185,6 +188,9 @@ async def upload_bucket(request: Request, task_service, session_manager):owner_email = user.emailtask_user_id = user.user_id+ from .documents import _ensure_index_exists+ await _ensure_index_exists()+processor = S3FileProcessor(task_service.document_service,bucket,