gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

added max paralle insert

Browse Source
This commit is contained in:
Yannick Stephan
2025-02-20 12:57:25 +01:00
parent de56aeb7c5
commit bae21a6fad
1 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
lightrag/lightrag.py
View File

@@ -347,6 +347,9 @@ class LightRAG:
"""If True, enables caching for entity extraction steps to reduce LLM costs.""" """If True, enables caching for entity extraction steps to reduce LLM costs."""
# Extensions # Extensions
max_parallel_insert: int = field(default_factory=lambda: int(os.getenv("MAX_PARALLEL_INSERT", 20)))
"""Maximum number of parallel insert operations."""
addon_params: dict[str, Any] = field(default_factory=dict) addon_params: dict[str, Any] = field(default_factory=dict)
# Storages Management # Storages Management
@@ -786,10 +789,9 @@ class LightRAG:
return return
# 2. split docs into chunks, insert chunks, update doc status # 2. split docs into chunks, insert chunks, update doc status
batch_size = self.addon_params.get("insert_batch_size", 10)
docs_batches = [ docs_batches = [
list(to_process_docs.items())[i : i + batch_size] list(to_process_docs.items())[i : i + self.max_parallel_insert]
for i in range(0, len(to_process_docs), batch_size) for i in range(0, len(to_process_docs), self.max_parallel_insert)
] ]
logger.info(f"Number of batches to process: {len(docs_batches)}.") logger.info(f"Number of batches to process: {len(docs_batches)}.")