Reduce default max total tokens to 30k

This commit is contained in:
yangdx 2025-07-27 10:33:06 +08:00
parent a67f93acc9
commit 055629d30d
2 changed files with 3 additions and 3 deletions

View file

@ -61,7 +61,7 @@ ENABLE_LLM_CACHE=true
### control the actual relations send to LLM
# MAX_RELATION_TOKENS=10000
### control the maximum tokens send to LLM (include entities, raltions and chunks)
# MAX_TOTAL_TOKENS=32000
# MAX_TOTAL_TOKENS=30000
### maximum number of related chunks per source entity or relation (higher values increase re-ranking time)
# RELATED_CHUNK_NUMBER=5
@ -92,7 +92,7 @@ ENABLE_LLM_CACHE_FOR_EXTRACT=true
###############################
### Max concurrency requests of LLM (for both query and document processing)
MAX_ASYNC=4
### Number of parallel processing documents(between 2~10, MAX_ASYNC/4 is recommended)
### Number of parallel processing documents(between 2~10, MAX_ASYNC/3 is recommended)
MAX_PARALLEL_INSERT=2
### Max concurrency requests for Embedding
# EMBEDDING_FUNC_MAX_ASYNC=8

View file

@ -17,7 +17,7 @@ DEFAULT_TOP_K = 40
DEFAULT_CHUNK_TOP_K = 10
DEFAULT_MAX_ENTITY_TOKENS = 10000
DEFAULT_MAX_RELATION_TOKENS = 10000
DEFAULT_MAX_TOTAL_TOKENS = 32000
DEFAULT_MAX_TOTAL_TOKENS = 30000
DEFAULT_HISTORY_TURNS = 0
DEFAULT_ENABLE_RERANK = True
DEFAULT_COSINE_THRESHOLD = 0.2