yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-11-21 12:33:46 +00:00
Code Issues Packages Projects Releases Wiki Activity
LightRAG/lightrag/constants.py

57 lines
1.8 KiB
Python
Raw Normal View History

feat: Centralize configuration and update defaults This commit introduces `lightrag/constants.py` to centralize default values for various configurations across the API and core components. Key changes: - Added `constants.py` to centralize default values - Improved the `get_env_value` function in `api/config.py` to correctly handle string "None" as a None value and to catch `TypeError` during value conversion. - Updated the default `SUMMARY_LANGUAGE` to "English" - Set default `WORKERS` to 2
2025-05-06 22:00:43 +08:00
"""
Centralized configuration constants for LightRAG.
This module defines default values for configuration constants used across
different parts of the LightRAG system. Centralizing these values ensures
consistency and makes maintenance easier.
"""
feat: add environment variables to /health endpoint and centralize defaults - Add 9 environment variables to /health endpoint configuration section - Centralize default constants in lightrag/constants.py for consistency - Update config.py to use centralized defaults for better maintainability
2025-07-28 00:30:56 +08:00
# Default values for server settings
feat: Centralize configuration and update defaults This commit introduces `lightrag/constants.py` to centralize default values for various configurations across the API and core components. Key changes: - Added `constants.py` to centralize default values - Improved the `get_env_value` function in `api/config.py` to correctly handle string "None" as a None value and to catch `TypeError` during value conversion. - Updated the default `SUMMARY_LANGUAGE` to "English" - Set default `WORKERS` to 2
2025-05-06 22:00:43 +08:00
DEFAULT_WOKERS = 2
DEFAULT_TIMEOUT = 150
feat: add environment variables to /health endpoint and centralize defaults - Add 9 environment variables to /health endpoint configuration section - Centralize default constants in lightrag/constants.py for consistency - Update config.py to use centralized defaults for better maintainability
2025-07-28 00:30:56 +08:00
# Default values for extraction settings
DEFAULT_SUMMARY_LANGUAGE = "English" # Default language for summaries
DEFAULT_FORCE_LLM_SUMMARY_ON_MERGE = 4
DEFAULT_MAX_GLEANING = 1
Refactor: Rename llm_model_max_token_size to summary_max_tokens This commit renames the parameter 'llm_model_max_token_size' to 'summary_max_tokens' for better clarity, as it specifically controls the token limit for entity relation summaries.
2025-07-28 00:49:08 +08:00
DEFAULT_SUMMARY_MAX_TOKENS = 10000 # Default maximum token size
feat: add environment variables to /health endpoint and centralize defaults - Add 9 environment variables to /health endpoint configuration section - Centralize default constants in lightrag/constants.py for consistency - Update config.py to use centralized defaults for better maintainability
2025-07-28 00:30:56 +08:00
# Separator for graph fields
GRAPH_FIELD_SEP = "<SEP>"
feat: centralize environment variable defaults in constants.py
2025-07-15 16:11:50 +08:00
# Query and retrieval configuration defaults
DEFAULT_TOP_K = 40
DEFAULT_CHUNK_TOP_K = 10
DEFAULT_MAX_ENTITY_TOKENS = 10000
DEFAULT_MAX_RELATION_TOKENS = 10000
Reduce default max total tokens to 30k
2025-07-27 10:33:06 +08:00
DEFAULT_MAX_TOTAL_TOKENS = 30000
Set DEFAULT_HISTORY_TURNS to 0
2025-07-16 02:20:27 +08:00
DEFAULT_HISTORY_TURNS = 0
Centralize query parameters into LightRAG class This commit refactors query parameter management by consolidating settings like `top_k`, token limits, and thresholds into the `LightRAG` class, and consistently sourcing parameters from a single location.
2025-07-15 23:56:49 +08:00
DEFAULT_COSINE_THRESHOLD = 0.2
reduce RELATED_CHUNK_NUMBER from 10 to 5
2025-07-24 02:49:05 +08:00
DEFAULT_RELATED_CHUNK_NUMBER = 5
feat: centralize environment variable defaults in constants.py
2025-07-15 16:11:50 +08:00
feat: Add rerank score filtering with configurable threshold - Add DEFAULT_MIN_RERANK_SCORE constant (default: 0.0) - Add MIN_RERANK_SCORE environment variable support - Filter chunks with rerank scores below threshold in process_chunks_unified - Add info-level logging for filtering operations - Handle empty results gracefully after filtering - Maintain backward compatibility with non-reranked chunks
2025-07-27 16:37:44 +08:00
# Rerank configuration defaults
feat: Skip rerank filtering when `min_rerank_score` is 0.0
2025-07-27 16:50:12 +08:00
DEFAULT_ENABLE_RERANK = True
feat: Add rerank score filtering with configurable threshold - Add DEFAULT_MIN_RERANK_SCORE constant (default: 0.0) - Add MIN_RERANK_SCORE environment variable support - Filter chunks with rerank scores below threshold in process_chunks_unified - Add info-level logging for filtering operations - Handle empty results gracefully after filtering - Maintain backward compatibility with non-reranked chunks
2025-07-27 16:37:44 +08:00
DEFAULT_MIN_RERANK_SCORE = 0.0
refactor: extract file path length limit to shared constant • Add DEFAULT_MAX_FILE_PATH_LENGTH constant • Replace hardcoded 4090 in Milvus impl
2025-07-26 10:45:03 +08:00
# File path configuration for vector and graph database
DEFAULT_MAX_FILE_PATH_LENGTH = 4090
feat: add environment variables to /health endpoint and centralize defaults - Add 9 environment variables to /health endpoint configuration section - Centralize default constants in lightrag/constants.py for consistency - Update config.py to use centralized defaults for better maintainability
2025-07-28 00:30:56 +08:00
# Async configuration defaults
DEFAULT_MAX_ASYNC = 4 # Default maximum async operations
# Embedding configuration defaults
DEFAULT_EMBEDDING_FUNC_MAX_ASYNC = 8 # Default max async for embedding functions
DEFAULT_EMBEDDING_BATCH_NUM = 10 # Default batch size for embedding computations
feat: Centralize configuration and update defaults This commit introduces `lightrag/constants.py` to centralize default values for various configurations across the API and core components. Key changes: - Added `constants.py` to centralize default values - Improved the `get_env_value` function in `api/config.py` to correctly handle string "None" as a None value and to catch `TypeError` during value conversion. - Updated the default `SUMMARY_LANGUAGE` to "English" - Set default `WORKERS` to 2
2025-05-06 22:00:43 +08:00
# Logging configuration defaults
DEFAULT_LOG_MAX_BYTES = 10485760 # Default 10MB
DEFAULT_LOG_BACKUP_COUNT = 5 # Default 5 backups
DEFAULT_LOG_FILENAME = "lightrag.log" # Default log filename
feat: refactor ollama server configuration management - Add ollama_server_infos attribute to LightRAG class with default initialization - Move default values to constants.py for centralized configuration - Refactor OllamaServerInfos class with property accessors and CLI support - Update OllamaAPI to get configuration through rag object instead of direct import - Add command line arguments for simulated model name and tag - Fix type imports to avoid circular dependencies
2025-07-28 01:38:35 +08:00
# Ollama server configuration defaults
DEFAULT_OLLAMA_MODEL_NAME = "lightrag"
DEFAULT_OLLAMA_MODEL_TAG = "latest"
DEFAULT_OLLAMA_MODEL_SIZE = 7365960935
DEFAULT_OLLAMA_CREATED_AT = "2024-01-15T00:00:00Z"
DEFAULT_OLLAMA_DIGEST = "sha256:lightrag"
Reference in New Issue Copy Permalink