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

Import from env and use default if none and removed useless import

Browse source
This commit is contained in:
haseebuchiha 2025-10-14 16:14:03 +05:00 • committed by DivinesLight
parent 7871600d8a
commit 4e740af79b
3 changed files with 7 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
env.example
View file

@ -73,6 +73,8 @@ ENABLE_LLM_CACHE=true
# MAX_RELATION_TOKENS=8000 # MAX_RELATION_TOKENS=8000
### control the maximum tokens send to LLM (include entities, relations and chunks) ### control the maximum tokens send to LLM (include entities, relations and chunks)
# MAX_TOTAL_TOKENS=30000 # MAX_TOTAL_TOKENS=30000
### control the maximum chunk_ids stored in vector db
# MAX_CHUNK_IDS_PER_ENTITY=500
### maximum number of related chunks per source entity or relation ### maximum number of related chunks per source entity or relation
### The chunk picker uses this value to determine the total number of chunks selected from KG(knowledge graph) ### The chunk picker uses this value to determine the total number of chunks selected from KG(knowledge graph)

1
lightrag/operate.py
View file

@ -53,7 +53,6 @@ from .constants import (
DEFAULT_KG_CHUNK_PICK_METHOD, DEFAULT_KG_CHUNK_PICK_METHOD,
DEFAULT_ENTITY_TYPES, DEFAULT_ENTITY_TYPES,
DEFAULT_SUMMARY_LANGUAGE, DEFAULT_SUMMARY_LANGUAGE,
DEFAULT_MAX_CHUNK_IDS_PER_ENTITY,
) )
from .kg.shared_storage import get_storage_keyed_lock from .kg.shared_storage import get_storage_keyed_lock
import time import time

8
lightrag/utils.py
View file

@ -2469,13 +2469,15 @@ def truncate_entity_source_id(chunk_ids: set, entity_name: str) -> set:
"""Limit chunk_ids, for entities that appear a HUGE no of times (To not break VDB hard upper limits)""" """Limit chunk_ids, for entities that appear a HUGE no of times (To not break VDB hard upper limits)"""
already_len: int = len(chunk_ids) already_len: int = len(chunk_ids)
if already_len >= DEFAULT_MAX_CHUNK_IDS_PER_ENTITY: max_chunk_ids_per_entity = get_env_value("MAX_CHUNK_IDS_PER_ENTITY", DEFAULT_MAX_CHUNK_IDS_PER_ENTITY, int)
if already_len >= max_chunk_ids_per_entity:
logger.warning( logger.warning(
f"Chunk Ids already exceeds {DEFAULT_MAX_CHUNK_IDS_PER_ENTITY} for {entity_name}, " f"Chunk Ids already exceeds {max_chunk_ids_per_entity } for {entity_name}, "
f"current size: {already_len} entries." f"current size: {already_len} entries."
) )
truncated_chunk_ids = set(list(chunk_ids)[0:DEFAULT_MAX_CHUNK_IDS_PER_ENTITY]) truncated_chunk_ids = set(list(chunk_ids)[0:max_chunk_ids_per_entity ])
return truncated_chunk_ids return truncated_chunk_ids