gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Limit history messages to latest 1000 entries with truncation indicator

Browse source 
• Limit history to 1000 latest messages
• Add truncation message when needed
• Show count of truncated messages
• Update API documentation
• Prevent memory issues with large logs
This commit is contained in:
yangdx 2025-09-05 12:31:36 +08:00
parent 0ccf2036c6
commit 17d665c9f3
1 changed files with 23 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
lightrag/api/routers/document_routes.py
View file

@ -1947,7 +1947,8 @@ def create_document_routes(
- cur_batch (int): Current processing batch
- request_pending (bool): Flag for pending request for processing
- latest_message (str): Latest message from pipeline processing
- history_messages (List[str], optional): List of history messages
- history_messages (List[str], optional): List of history messages (limited to latest 1000 entries,
with truncation message if more than 1000 messages exist)
Raises:
HTTPException: If an error occurs while retrieving pipeline status (500)
@ -1982,8 +1983,28 @@ def create_document_routes(
status_dict["update_status"] = processed_update_status
# Convert history_messages to a regular list if it's a Manager.list
# and limit to latest 1000 entries with truncation message if needed
if "history_messages" in status_dict:
status_dict["history_messages"] = list(status_dict["history_messages"])
history_list = list(status_dict["history_messages"])
total_count = len(history_list)
if total_count > 1000:
# Calculate truncated message count
truncated_count = total_count - 1000
# Take only the latest 1000 messages
latest_messages = history_list[-1000:]
# Add truncation message at the beginning
truncation_message = (
f"[Truncated history messages: {truncated_count}/{total_count}]"
)
status_dict["history_messages"] = [
truncation_message
] + latest_messages
else:
# No truncation needed, return all messages
status_dict["history_messages"] = history_list
# Ensure job_start is properly formatted as a string with timezone information
if "job_start" in status_dict and status_dict["job_start"]: