From b26a574f40253ce6a32380b0f29b6d42d75ab0d6 Mon Sep 17 00:00:00 2001 From: yangdx Date: Tue, 4 Mar 2025 01:07:34 +0800 Subject: [PATCH] Deprecate log_level and log_file_path in LightRAG. - Remove log_level from API initialization - Add warnings for deprecated logging params --- README.md | 18 +++++++++++++++--- lightrag/api/lightrag_server.py | 2 -- lightrag/lightrag.py | 25 ++++++++++++++++++++----- 3 files changed, 35 insertions(+), 10 deletions(-) diff --git a/README.md b/README.md index abc2f8b3..5e8c5a94 100644 --- a/README.md +++ b/README.md @@ -106,6 +106,9 @@ import asyncio from lightrag import LightRAG, QueryParam 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.utils import setup_logger + +setup_logger("lightrag", level="INFO") async def initialize_rag(): 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.llms.openai import OpenAI 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(): rag = LightRAG( @@ -640,6 +647,9 @@ export NEO4J_URI="neo4j://localhost:7687" export NEO4J_USERNAME="neo4j" 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 # by specifying kg="Neo4JStorage". @@ -649,8 +659,12 @@ rag = LightRAG( working_dir=WORKING_DIR, llm_model_func=gpt_4o_mini_complete, # Use gpt_4o_mini_complete LLM model 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. @@ -859,7 +873,6 @@ Valid modes are: | **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` | | **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\_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` | @@ -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` | | **convert\_response\_to\_json\_func** | `callable` | Not used | `convert_response_to_json` | | **embedding\_cache\_config** | `dict` | Configuration for question-answer caching. Contains three parameters:
- `enabled`: Boolean value to enable/disable cache lookup functionality. When enabled, the system will check cached responses before generating new answers.
- `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.
- `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. | `./` | diff --git a/lightrag/api/lightrag_server.py b/lightrag/api/lightrag_server.py index 693c6a9f..c91f693f 100644 --- a/lightrag/api/lightrag_server.py +++ b/lightrag/api/lightrag_server.py @@ -329,7 +329,6 @@ def create_app(args): "similarity_threshold": 0.95, "use_llm_check": False, }, - log_level=args.log_level, namespace_prefix=args.namespace_prefix, auto_manage_storages_states=False, ) @@ -359,7 +358,6 @@ def create_app(args): "similarity_threshold": 0.95, "use_llm_check": False, }, - log_level=args.log_level, namespace_prefix=args.namespace_prefix, auto_manage_storages_states=False, ) diff --git a/lightrag/lightrag.py b/lightrag/lightrag.py index 4dacac08..114b5735 100644 --- a/lightrag/lightrag.py +++ b/lightrag/lightrag.py @@ -3,6 +3,7 @@ from __future__ import annotations import asyncio import configparser import os +import warnings from dataclasses import asdict, dataclass, field from datetime import datetime from functools import partial @@ -85,14 +86,10 @@ class LightRAG: doc_status_storage: str = field(default="JsonDocStatusStorage") """Storage type for tracking document processing statuses.""" - # Logging + # Logging (Deprecated, use setup_logger in utils.py instead) # --- - 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.""" # Entity extraction # --- @@ -270,6 +267,24 @@ class LightRAG: 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() if not os.path.exists(self.working_dir):