LightRAG/lightrag
Jon cf2a024e37 feat: Add endpoint and UI to retry failed documents
Add a new `/documents/reprocess_failed` API endpoint and corresponding
UI button to retry processing of failed and pending documents. This
addresses a common recovery scenario when document processing fails due
to server crashes, network errors, or LLM service outages.

Backend changes:
- Add ReprocessResponse model with status, message, and track_id fields
- Add POST /documents/reprocess_failed endpoint that triggers background
  reprocessing of FAILED, PENDING, and interrupted PROCESSING documents
- Reuses existing apipeline_process_enqueue_documents for consistency
- Includes comprehensive docstring and logging for observability

Frontend changes:
- Add TypeScript types and API function for the new endpoint
- Add retry handler with intelligent polling (fast refresh → normal)
- Add "Retry Failed" button in Documents page toolbar
- Button disabled when pipeline is busy to prevent duplicate operations
- Complete i18n support (English and Chinese translations)

This feature provides a convenient way to recover from processing
failures without requiring a full filesystem rescan.
2025-10-04 16:46:29 -04:00
..
api feat: Add endpoint and UI to retry failed documents 2025-10-04 16:46:29 -04:00
kg Fix graph truncation logic for depth-limited traversals 2025-09-24 18:03:11 +08:00
llm Fix linting 2025-10-03 02:10:02 +08:00
tools Fix linting 2025-08-23 02:39:12 +08:00
__init__.py Bump core version to 1.4.9.1 2025-09-28 15:25:02 +08:00
base.py Fix documentation for user_prompt parameter in QueryParam 2025-09-27 23:41:17 +08:00
constants.py Remove deprecated history_turns and ids parameters from query API endpoint 2025-09-25 04:58:57 +08:00
exceptions.py Rename allow_create to first_initialization for clarity 2025-08-23 02:34:39 +08:00
lightrag.py Fix mode parameter serialization error in Ollama chat API 2025-09-27 15:11:51 +08:00
namespace.py Refac: Add workspace infomation to all logger output for all storage type 2025-08-12 01:19:09 +08:00
operate.py Simplify reference formatting in LLM context generation 2025-10-01 22:20:58 +08:00
prompt.py Remove bold formatting from instruction headers in prompts 2025-10-02 00:58:03 +08:00
rerank.py fix: Resolve default rerank config problem when env var missing 2025-08-23 01:07:59 +08:00
types.py Add is_truncated to graph query for NetworkX graph db 2025-04-02 22:12:20 +08:00
utils.py Fix logging filter logic 2025-09-26 19:42:33 +08:00
utils_graph.py Fix GRAPH_FIELD_SEP import typo 2025-06-29 01:28:39 +05:00