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

Reduce embedding concurrency limit from 16 to 8

Browse source
This commit is contained in:
yangdx 2025-07-13 03:13:52 +08:00
parent a2eeae9661
commit 03b40937f7
2 changed files with 2 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
env.example
View file

@ -113,7 +113,7 @@ EMBEDDING_BINDING_HOST=http://localhost:11434
### Num of chunks send to Embedding in single request ### Num of chunks send to Embedding in single request
# EMBEDDING_BATCH_NUM=10 # EMBEDDING_BATCH_NUM=10
### Max concurrency requests for Embedding ### Max concurrency requests for Embedding
# EMBEDDING_FUNC_MAX_ASYNC=16 # EMBEDDING_FUNC_MAX_ASYNC=8
### Maximum tokens sent to Embedding for each chunk (no longer in use?) ### Maximum tokens sent to Embedding for each chunk (no longer in use?)
# MAX_EMBED_TOKENS=8192 # MAX_EMBED_TOKENS=8192
### Optional for Azure ### Optional for Azure

2
lightrag/lightrag.py
View file

@ -205,7 +205,7 @@ class LightRAG:
"""Batch size for embedding computations.""" """Batch size for embedding computations."""
embedding_func_max_async: int = field( embedding_func_max_async: int = field(
default=int(os.getenv("EMBEDDING_FUNC_MAX_ASYNC", 16)) default=int(os.getenv("EMBEDDING_FUNC_MAX_ASYNC", 8))
) )
"""Maximum number of concurrent embedding function calls.""" """Maximum number of concurrent embedding function calls."""