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

doc: add information about log_dir parameter

Browse Source
This commit is contained in:
ultrageopro
2025-02-03 11:25:09 +03:00
parent 749003f380
commit 0284469fd4
2 changed files with 4 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
README.md
View File

@@ -799,6 +799,7 @@ if __name__ == "__main__":
| **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. | `./` |
### Error Handling ### Error Handling

6
lightrag/lightrag.py
View File

@@ -129,7 +129,7 @@ class LightRAG:
# logging # logging
current_log_level = logger.level current_log_level = logger.level
log_level: str = field(default=current_log_level) log_level: str = field(default=current_log_level)
logging_dir: str = field(default=os.getcwd()) log_dir: str = field(default=os.getcwd())
# text chunking # text chunking
chunk_token_size: int = 1200 chunk_token_size: int = 1200
@@ -184,8 +184,8 @@ class LightRAG:
chunking_func_kwargs: dict = field(default_factory=dict) chunking_func_kwargs: dict = field(default_factory=dict)
def __post_init__(self): def __post_init__(self):
os.makedirs(self.logging_dir, exist_ok=True) os.makedirs(self.log_dir, exist_ok=True)
log_file = os.path.join(self.logging_dir, "lightrag.log") log_file = os.path.join(self.log_dir, "lightrag.log")
set_logger(log_file) set_logger(log_file)
logger.setLevel(self.log_level) logger.setLevel(self.log_level)