feat: add processing mode support for document uploads and ETL pipeline, improded error handling ux
Some checks are pending
Build and Push Docker Images / tag_release (push) Waiting to run
Build and Push Docker Images / build (./surfsense_backend, ./surfsense_backend/Dockerfile, backend, surfsense-backend, ubuntu-24.04-arm, linux/arm64, arm64) (push) Blocked by required conditions
Build and Push Docker Images / build (./surfsense_backend, ./surfsense_backend/Dockerfile, backend, surfsense-backend, ubuntu-latest, linux/amd64, amd64) (push) Blocked by required conditions
Build and Push Docker Images / build (./surfsense_web, ./surfsense_web/Dockerfile, web, surfsense-web, ubuntu-24.04-arm, linux/arm64, arm64) (push) Blocked by required conditions
Build and Push Docker Images / build (./surfsense_web, ./surfsense_web/Dockerfile, web, surfsense-web, ubuntu-latest, linux/amd64, amd64) (push) Blocked by required conditions
Build and Push Docker Images / create_manifest (backend, surfsense-backend) (push) Blocked by required conditions
Build and Push Docker Images / create_manifest (web, surfsense-web) (push) Blocked by required conditions

- Introduced a `ProcessingMode` enum to differentiate between basic and premium processing modes.
- Updated `EtlRequest` to include a `processing_mode` field, defaulting to basic.
- Enhanced ETL pipeline services to utilize the selected processing mode for Azure Document Intelligence and LlamaCloud parsing.
- Modified various routes and services to handle processing mode, affecting document upload and indexing tasks.
- Improved error handling and logging to include processing mode details.
- Added tests to validate processing mode functionality and its impact on ETL operations.
This commit is contained in:
DESKTOP-RTLN3BA\$punk 2026-04-14 21:26:00 -07:00
parent b659f41bab
commit 656e061f84
104 changed files with 1900 additions and 909 deletions

View file

@ -127,7 +127,8 @@ class DocumentsApiService {
throw new ValidationError(`Invalid request: ${errorMessage}`);
}
const { files, search_space_id, should_summarize, use_vision_llm } = parsedRequest.data;
const { files, search_space_id, should_summarize, use_vision_llm, processing_mode } =
parsedRequest.data;
const UPLOAD_BATCH_SIZE = 5;
const batches: File[][] = [];
@ -147,6 +148,7 @@ class DocumentsApiService {
formData.append("search_space_id", String(search_space_id));
formData.append("should_summarize", String(should_summarize));
formData.append("use_vision_llm", String(use_vision_llm));
formData.append("processing_mode", processing_mode);
const controller = new AbortController();
const timeoutId = setTimeout(() => controller.abort(), 120_000);
@ -444,6 +446,7 @@ class DocumentsApiService {
root_folder_id?: number | null;
enable_summary?: boolean;
use_vision_llm?: boolean;
processing_mode?: "basic" | "premium";
},
signal?: AbortSignal
): Promise<{ message: string; status: string; root_folder_id: number; file_count: number }> => {
@ -459,6 +462,7 @@ class DocumentsApiService {
}
formData.append("enable_summary", String(metadata.enable_summary ?? false));
formData.append("use_vision_llm", String(metadata.use_vision_llm ?? false));
formData.append("processing_mode", metadata.processing_mode ?? "basic");
const totalSize = files.reduce((acc, f) => acc + f.size, 0);
const timeoutMs = Math.min(Math.max((totalSize / (1024 * 1024)) * 5000, 30_000), 600_000);