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

Deprecate log_level and log_file_path in LightRAG.

Browse Source 
- Remove log_level from API initialization
- Add warnings for deprecated logging params
This commit is contained in:
yangdx
2025-03-04 01:07:34 +08:00
parent 63cb057d41
commit b26a574f40
3 changed files with 35 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
README.md
View File

@@ -106,6 +106,9 @@ import asyncio
from lightrag import LightRAG, QueryParam from lightrag import LightRAG, QueryParam
from lightrag.llm.openai import gpt_4o_mini_complete, gpt_4o_complete, openai_embed from lightrag.llm.openai import gpt_4o_mini_complete, gpt_4o_complete, openai_embed
from lightrag.kg.shared_storage import initialize_pipeline_status from lightrag.kg.shared_storage import initialize_pipeline_status
from lightrag.utils import setup_logger
setup_logger("lightrag", level="INFO")
async def initialize_rag(): async def initialize_rag():
rag = LightRAG( rag = LightRAG(
@@ -344,6 +347,10 @@ from lightrag.llm.llama_index_impl import llama_index_complete_if_cache, llama_i
from llama_index.embeddings.openai import OpenAIEmbedding from llama_index.embeddings.openai import OpenAIEmbedding
from llama_index.llms.openai import OpenAI from llama_index.llms.openai import OpenAI
from lightrag.kg.shared_storage import initialize_pipeline_status from lightrag.kg.shared_storage import initialize_pipeline_status
from lightrag.utils import setup_logger
# Setup log handler for LightRAG
setup_logger("lightrag", level="INFO")
async def initialize_rag(): async def initialize_rag():
rag = LightRAG( rag = LightRAG(
@@ -640,6 +647,9 @@ export NEO4J_URI="neo4j://localhost:7687"
export NEO4J_USERNAME="neo4j" export NEO4J_USERNAME="neo4j"
export NEO4J_PASSWORD="password" export NEO4J_PASSWORD="password"
# Setup logger for LightRAG
setup_logger("lightrag", level="INFO")
# When you launch the project be sure to override the default KG: NetworkX # When you launch the project be sure to override the default KG: NetworkX
# by specifying kg="Neo4JStorage". # by specifying kg="Neo4JStorage".
@@ -649,8 +659,12 @@ rag = LightRAG(
working_dir=WORKING_DIR, working_dir=WORKING_DIR,
llm_model_func=gpt_4o_mini_complete, # Use gpt_4o_mini_complete LLM model llm_model_func=gpt_4o_mini_complete, # Use gpt_4o_mini_complete LLM model
graph_storage="Neo4JStorage", #<-----------override KG default graph_storage="Neo4JStorage", #<-----------override KG default
log_level="DEBUG" #<-----------override log_level default
) )
# Initialize database connections
await rag.initialize_storages()
# Initialize pipeline status for document processing
await initialize_pipeline_status()
``` ```
see test_neo4j.py for a working example. see test_neo4j.py for a working example.
@@ -859,7 +873,6 @@ Valid modes are:
| **kv\_storage** | `str` | Storage type for documents and text chunks. Supported types: `JsonKVStorage`, `OracleKVStorage` | `JsonKVStorage` | | **kv\_storage** | `str` | Storage type for documents and text chunks. Supported types: `JsonKVStorage`, `OracleKVStorage` | `JsonKVStorage` |
| **vector\_storage** | `str` | Storage type for embedding vectors. Supported types: `NanoVectorDBStorage`, `OracleVectorDBStorage` | `NanoVectorDBStorage` | | **vector\_storage** | `str` | Storage type for embedding vectors. Supported types: `NanoVectorDBStorage`, `OracleVectorDBStorage` | `NanoVectorDBStorage` |
| **graph\_storage** | `str` | Storage type for graph edges and nodes. Supported types: `NetworkXStorage`, `Neo4JStorage`, `OracleGraphStorage` | `NetworkXStorage` | | **graph\_storage** | `str` | Storage type for graph edges and nodes. Supported types: `NetworkXStorage`, `Neo4JStorage`, `OracleGraphStorage` | `NetworkXStorage` |
| **log\_level** | | Log level for application runtime | `logging.DEBUG` |
| **chunk\_token\_size** | `int` | Maximum token size per chunk when splitting documents | `1200` | | **chunk\_token\_size** | `int` | Maximum token size per chunk when splitting documents | `1200` |
| **chunk\_overlap\_token\_size** | `int` | Overlap token size between two chunks when splitting documents | `100` | | **chunk\_overlap\_token\_size** | `int` | Overlap token size between two chunks when splitting documents | `100` |
| **tiktoken\_model\_name** | `str` | Model name for the Tiktoken encoder used to calculate token numbers | `gpt-4o-mini` | | **tiktoken\_model\_name** | `str` | Model name for the Tiktoken encoder used to calculate token numbers | `gpt-4o-mini` |
@@ -881,7 +894,6 @@ Valid modes are:
| **addon\_params** | `dict` | Additional parameters, e.g., `{"example_number": 1, "language": "Simplified Chinese", "entity_types": ["organization", "person", "geo", "event"], "insert_batch_size": 10}`: sets example limit, output language, and batch size for document processing | `example_number: all examples, language: English, insert_batch_size: 10` | | **addon\_params** | `dict` | Additional parameters, e.g., `{"example_number": 1, "language": "Simplified Chinese", "entity_types": ["organization", "person", "geo", "event"], "insert_batch_size": 10}`: sets example limit, output language, and batch size for document processing | `example_number: all examples, language: English, insert_batch_size: 10` |
| **convert\_response\_to\_json\_func** | `callable` | Not used | `convert_response_to_json` | | **convert\_response\_to\_json\_func** | `callable` | Not used | `convert_response_to_json` |
| **embedding\_cache\_config** | `dict` | Configuration for question-answer caching. Contains three parameters:<br>- `enabled`: Boolean value to enable/disable cache lookup functionality. When enabled, the system will check cached responses before generating new answers.<br>- `similarity_threshold`: Float value (0-1), similarity threshold. When a new question's similarity with a cached question exceeds this threshold, the cached answer will be returned directly without calling the LLM.<br>- `use_llm_check`: Boolean value to enable/disable LLM similarity verification. When enabled, LLM will be used as a secondary check to verify the similarity between questions before returning cached answers. | Default: `{"enabled": False, "similarity_threshold": 0.95, "use_llm_check": False}` | | **embedding\_cache\_config** | `dict` | Configuration for question-answer caching. Contains three parameters:<br>- `enabled`: Boolean value to enable/disable cache lookup functionality. When enabled, the system will check cached responses before generating new answers.<br>- `similarity_threshold`: Float value (0-1), similarity threshold. When a new question's similarity with a cached question exceeds this threshold, the cached answer will be returned directly without calling the LLM.<br>- `use_llm_check`: Boolean value to enable/disable LLM similarity verification. When enabled, LLM will be used as a secondary check to verify the similarity between questions before returning cached answers. | Default: `{"enabled": False, "similarity_threshold": 0.95, "use_llm_check": False}` |
|**log\_dir** | `str` | Directory to store logs. | `./` |
</details> </details>

2
lightrag/api/lightrag_server.py
View File

@@ -329,7 +329,6 @@ def create_app(args):
"similarity_threshold": 0.95, "similarity_threshold": 0.95,
"use_llm_check": False, "use_llm_check": False,
}, },
log_level=args.log_level,
namespace_prefix=args.namespace_prefix, namespace_prefix=args.namespace_prefix,
auto_manage_storages_states=False, auto_manage_storages_states=False,
) )
@@ -359,7 +358,6 @@ def create_app(args):
"similarity_threshold": 0.95, "similarity_threshold": 0.95,
"use_llm_check": False, "use_llm_check": False,
}, },
log_level=args.log_level,
namespace_prefix=args.namespace_prefix, namespace_prefix=args.namespace_prefix,
auto_manage_storages_states=False, auto_manage_storages_states=False,
) )

25
lightrag/lightrag.py
View File

@@ -3,6 +3,7 @@ from __future__ import annotations
import asyncio import asyncio
import configparser import configparser
import os import os
import warnings
from dataclasses import asdict, dataclass, field from dataclasses import asdict, dataclass, field
from datetime import datetime from datetime import datetime
from functools import partial from functools import partial
@@ -85,14 +86,10 @@ class LightRAG:
doc_status_storage: str = field(default="JsonDocStatusStorage") doc_status_storage: str = field(default="JsonDocStatusStorage")
"""Storage type for tracking document processing statuses.""" """Storage type for tracking document processing statuses."""
# Logging # Logging (Deprecated, use setup_logger in utils.py instead)
# --- # ---
log_level: int = field(default=logger.level) log_level: int = field(default=logger.level)
"""Logging level for the system (e.g., 'DEBUG', 'INFO', 'WARNING')."""
log_file_path: str = field(default=os.path.join(os.getcwd(), "lightrag.log")) log_file_path: str = field(default=os.path.join(os.getcwd(), "lightrag.log"))
"""Log file path."""
# Entity extraction # Entity extraction
# --- # ---
@@ -270,6 +267,24 @@ class LightRAG:
initialize_share_data, initialize_share_data,
) )
# Handle deprecated parameters
kwargs = self.__dict__
if "log_level" in kwargs:
warnings.warn(
"WARNING: log_level parameter is deprecated, use setup_logger in utils.py instead",
UserWarning,
stacklevel=2,
)
# Remove the attribute to prevent its use
delattr(self, "log_level")
if "log_file_path" in kwargs:
warnings.warn(
"WARNING: log_file_path parameter is deprecated, use setup_logger in utils.py instead",
UserWarning,
stacklevel=2,
)
delattr(self, "log_file_path")
initialize_share_data() initialize_share_data()
if not os.path.exists(self.working_dir): if not os.path.exists(self.working_dir):