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

added field

Browse Source
This commit is contained in:
Yannick Stephan
2025-02-20 13:05:59 +01:00
parent 37addb7c01
commit 2370a4336b
1 changed files with 9 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

19
lightrag/lightrag.py
View File

@@ -231,12 +231,12 @@ class LightRAG:
"""LightRAG: Simple and Fast Retrieval-Augmented Generation.""" """LightRAG: Simple and Fast Retrieval-Augmented Generation."""
working_dir: str = field( working_dir: str = field(
default_factory=lambda: f"./lightrag_cache_{datetime.now().strftime('%Y-%m-%d-%H:%M:%S')}" default=f"./lightrag_cache_{datetime.now().strftime('%Y-%m-%d-%H:%M:%S')}"
) )
"""Directory where cache and temporary files are stored.""" """Directory where cache and temporary files are stored."""
embedding_cache_config: dict[str, Any] = field( embedding_cache_config: dict[str, Any] = field(
default_factory=lambda: { default={
"enabled": False, "enabled": False,
"similarity_threshold": 0.95, "similarity_threshold": 0.95,
"use_llm_check": False, "use_llm_check": False,
@@ -261,32 +261,31 @@ class LightRAG:
"""Storage type for tracking document processing statuses.""" """Storage type for tracking document processing statuses."""
# Logging # Logging
current_log_level = logger.level log_level: int = field(default=logger.level)
log_level: int = field(default=current_log_level)
"""Logging level for the system (e.g., 'DEBUG', 'INFO', 'WARNING').""" """Logging level for the system (e.g., 'DEBUG', 'INFO', 'WARNING')."""
log_dir: str = field(default=os.getcwd()) log_dir: str = field(default=os.getcwd())
"""Directory where logs are stored. Defaults to the current working directory.""" """Directory where logs are stored. Defaults to the current working directory."""
# Text chunking # Text chunking
chunk_token_size: int = int(os.getenv("CHUNK_SIZE", "1200")) chunk_token_size: int = field(default=int(os.getenv("CHUNK_SIZE", 1200)))
"""Maximum number of tokens per text chunk when splitting documents.""" """Maximum number of tokens per text chunk when splitting documents."""
chunk_overlap_token_size: int = int(os.getenv("CHUNK_OVERLAP_SIZE", "100")) chunk_overlap_token_size: int = field(default=int(os.getenv("CHUNK_OVERLAP_SIZE", 100)))
"""Number of overlapping tokens between consecutive text chunks to preserve context.""" """Number of overlapping tokens between consecutive text chunks to preserve context."""
tiktoken_model_name: str = "gpt-4o-mini" tiktoken_model_name: str = field(default="gpt-4o-mini")
"""Model name used for tokenization when chunking text.""" """Model name used for tokenization when chunking text."""
# Entity extraction # Entity extraction
entity_extract_max_gleaning: int = 1 entity_extract_max_gleaning: int = field(default=1)
"""Maximum number of entity extraction attempts for ambiguous content.""" """Maximum number of entity extraction attempts for ambiguous content."""
entity_summary_to_max_tokens: int = int(os.getenv("MAX_TOKEN_SUMMARY", "500")) entity_summary_to_max_tokens: int = field(default=int(os.getenv("MAX_TOKEN_SUMMARY", 500)))
"""Maximum number of tokens used for summarizing extracted entities.""" """Maximum number of tokens used for summarizing extracted entities."""
# Node embedding # Node embedding
node_embedding_algorithm: str = "node2vec" node_embedding_algorithm: str = field(default="node2vec")
"""Algorithm used for node embedding in knowledge graphs.""" """Algorithm used for node embedding in knowledge graphs."""
node2vec_params: dict[str, int] = field( node2vec_params: dict[str, int] = field(