Rename MAX_TOKENS to SUMMARY_MAX_TOKENS for clarity

README-zh.md

@@ -265,7 +265,7 @@ if __name__ == "__main__":
 | **embedding_func_max_async** | `int` | 最大并发异步嵌入进程数 | `16` |
 | **llm_model_func** | `callable` | LLM生成的函数 | `gpt_4o_mini_complete` |
 | **llm_model_name** | `str` | 用于生成的LLM模型名称 | `meta-llama/Llama-3.2-1B-Instruct` |
-| **summary_max_tokens** | `int` | 生成实体关系摘要时送给LLM的最大令牌数 | `32000`（默认值由环境变量MAX_TOKENS更改） |
+| **summary_max_tokens** | `int` | 生成实体关系摘要时送给LLM的最大令牌数 | `32000`（由环境变量 SUMMARY_MAX_TOKENS 设置） |
 | **llm_model_max_async** | `int` | 最大并发异步LLM进程数 | `4`（默认值由环境变量MAX_ASYNC更改） |
 | **llm_model_kwargs** | `dict` | LLM生成的附加参数 | |
 | **vector_db_storage_cls_kwargs** | `dict` | 向量数据库的附加参数，如设置节点和关系检索的阈值 | cosine_better_than_threshold: 0.2（默认值由环境变量COSINE_THRESHOLD更改） |

README.md

@@ -272,7 +272,7 @@ A full list of LightRAG init parameters:
 | **embedding_func_max_async** | `int` | Maximum number of concurrent asynchronous embedding processes | `16` |
 | **llm_model_func** | `callable` | Function for LLM generation | `gpt_4o_mini_complete` |
 | **llm_model_name** | `str` | LLM model name for generation | `meta-llama/Llama-3.2-1B-Instruct` |
-| **summary_max_tokens** | `int` | Maximum tokens send to LLM to generate entity relation summaries | `32000`（default value changed by env var MAX_TOKENS) |
+| **summary_max_tokens** | `int` | Maximum tokens send to LLM to generate entity relation summaries | `32000`（configured by env var SUMMARY_MAX_TOKENS) |
 | **llm_model_max_async** | `int` | Maximum number of concurrent asynchronous LLM processes | `4`（default value changed by env var MAX_ASYNC) |
 | **llm_model_kwargs** | `dict` | Additional parameters for LLM generation | |
 | **vector_db_storage_cls_kwargs** | `dict` | Additional parameters for vector database, like setting the threshold for nodes and relations retrieval | cosine_better_than_threshold: 0.2（default value changed by env var COSINE_THRESHOLD) |

env.example

@@ -107,7 +107,7 @@ ENABLE_LLM_CACHE_FOR_EXTRACT=true
 ### Entity and relation summarization configuration
 ### Number of duplicated entities/edges to trigger LLM re-summary on merge (at least 3 is recommented)， and max tokens send to LLM
 # FORCE_LLM_SUMMARY_ON_MERGE=4
-# MAX_TOKENS=10000
+# SUMMARY_MAX_TOKENS=10000
 ### Maximum number of entity extraction attempts for ambiguous content
 # MAX_GLEANING=1
 
@@ -148,18 +148,16 @@ LLM_BINDING_API_KEY=your_api_key
 
 ### OpenAI Specific Parameters
 ### Apply frequency penalty to prevent the LLM from generating repetitive or looping outputs
-# OPENAI_LLM_FREQUENCY_PENALTY=1.1
 # OPENAI_LLM_TEMPERATURE=1.0
 ### use the following command to see all support options for openai and azure_openai
 ### lightrag-server --llm-binding openai --help
 
 ### Ollama Server Specific Parameters
-### OLLAMA_LLM_NUM_CTX must be larger than MAX_TOTAL_TOKENS + 2000
+### OLLAMA_LLM_NUM_CTX must be provided, and should at least larger than MAX_TOTAL_TOKENS + 2000
 OLLAMA_LLM_NUM_CTX=32768
+# OLLAMA_LLM_TEMPERATURE=1.0
 ### Stop sequences for Ollama LLM
 # OLLAMA_LLM_STOP='["</s>", "Assistant:", "\n\n"]'
-### If OLLAMA_LLM_TEMPERATURE is not specified, the system will default to the value defined by TEMPERATURE
-# OLLAMA_LLM_TEMPERATURE=0.85
 ### use the following command to see all support options for Ollama LLM
 ### lightrag-server --llm-binding ollama --help
 

lightrag/api/config.py

@@ -122,7 +122,7 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument(
         "--max-tokens",
         type=int,
-        default=get_env_value("MAX_TOKENS", DEFAULT_SUMMARY_MAX_TOKENS, int),
+        default=get_env_value("SUMMARY_MAX_TOKENS", DEFAULT_SUMMARY_MAX_TOKENS, int),
         help=f"Maximum token size (default: from env or {DEFAULT_SUMMARY_MAX_TOKENS})",
     )
 

lightrag/lightrag.py

@@ -283,7 +283,7 @@ class LightRAG:
     """Name of the LLM model used for generating responses."""
 
     summary_max_tokens: int = field(
-        default=int(os.getenv("MAX_TOKENS", DEFAULT_SUMMARY_MAX_TOKENS))
+        default=int(os.getenv("SUMMARY_MAX_TOKENS", DEFAULT_SUMMARY_MAX_TOKENS))
     )
     """Maximum number of tokens allowed per LLM response."""