Optimize pipeline status message

lightrag/lightrag.py

@@ -902,6 +902,13 @@ class LightRAG:
                         # Get file path from status document
                         file_path = getattr(status_doc, "file_path", "unknown_source")
 
+                        async with pipeline_status_lock:
+                            log_message = f"Processing file: {file_path}"
+                            pipeline_status["history_messages"].append(log_message)
+                            log_message = f"Processing d-id: {doc_id}"
+                            pipeline_status["latest_message"] = log_message
+                            pipeline_status["history_messages"].append(log_message)
+
                         # Generate chunks from document
                         chunks: dict[str, Any] = {
                             compute_mdhash_id(dp["content"], prefix="chunk-"): {

lightrag/operate.py

@@ -642,7 +642,7 @@ async def extract_entities(
         processed_chunks += 1
         entities_count = len(maybe_nodes)
         relations_count = len(maybe_edges)
-        log_message = f"  Chk {processed_chunks}/{total_chunks}: extracted {entities_count} Ent + {relations_count} Rel (deduplicated)"
+        log_message = f"Chk {processed_chunks}/{total_chunks}: extracted {entities_count} Ent + {relations_count} Rel (deduplicated)"
         logger.info(log_message)
         if pipeline_status is not None:
             async with pipeline_status_lock: