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

lightrag/api/config.py

@@ -20,6 +20,12 @@ from lightrag.constants import (
     DEFAULT_COSINE_THRESHOLD,
     DEFAULT_RELATED_CHUNK_NUMBER,
     DEFAULT_MIN_RERANK_SCORE,
+    DEFAULT_FORCE_LLM_SUMMARY_ON_MERGE,
+    DEFAULT_MAX_ASYNC,
+    DEFAULT_MAX_TOKENS,
+    DEFAULT_SUMMARY_LANGUAGE,
+    DEFAULT_EMBEDDING_FUNC_MAX_ASYNC,
+    DEFAULT_EMBEDDING_BATCH_NUM,
 )
 
 # use the .env that is inside the current folder
@@ -111,14 +117,14 @@ def parse_args() -> argparse.Namespace:
     parser.add_argument(
         "--max-async",
         type=int,
-        default=get_env_value("MAX_ASYNC", 4, int),
+        default=get_env_value("MAX_ASYNC", DEFAULT_MAX_ASYNC, int),
         help="Maximum async operations (default: from env or 4)",
     )
     parser.add_argument(
         "--max-tokens",
         type=int,
-        default=get_env_value("MAX_TOKENS", 32000, int),
-        help="Maximum token size (default: from env or 32768)",
+        default=get_env_value("MAX_TOKENS", DEFAULT_MAX_TOKENS, int),
+        help="Maximum token size (default: from env or 32000)",
     )
 
     # Logging configuration
@@ -276,7 +282,7 @@ def parse_args() -> argparse.Namespace:
 
     # Add environment variables that were previously read directly
     args.cors_origins = get_env_value("CORS_ORIGINS", "*")
-    args.summary_language = get_env_value("SUMMARY_LANGUAGE", "English")
+    args.summary_language = get_env_value("SUMMARY_LANGUAGE", DEFAULT_SUMMARY_LANGUAGE)
     args.whitelist_paths = get_env_value("WHITELIST_PATHS", "/health,/api/*")
 
     # For JWT Auth
@@ -316,6 +322,17 @@ def parse_args() -> argparse.Namespace:
         "RELATED_CHUNK_NUMBER", DEFAULT_RELATED_CHUNK_NUMBER, int
     )
 
+    # Add missing environment variables for health endpoint
+    args.force_llm_summary_on_merge = get_env_value(
+        "FORCE_LLM_SUMMARY_ON_MERGE", DEFAULT_FORCE_LLM_SUMMARY_ON_MERGE, int
+    )
+    args.embedding_func_max_async = get_env_value(
+        "EMBEDDING_FUNC_MAX_ASYNC", DEFAULT_EMBEDDING_FUNC_MAX_ASYNC, int
+    )
+    args.embedding_batch_num = get_env_value(
+        "EMBEDDING_BATCH_NUM", DEFAULT_EMBEDDING_BATCH_NUM, int
+    )
+
     ollama_server_infos.LIGHTRAG_MODEL = args.simulated_model_name
 
     return args

lightrag/api/lightrag_server.py

@@ -535,6 +535,16 @@ def create_app(args):
                     "rerank_binding_host": args.rerank_binding_host
                     if rerank_model_func is not None
                     else None,
+                    # Environment variable status (requested configuration)
+                    "summary_language": args.summary_language,
+                    "force_llm_summary_on_merge": args.force_llm_summary_on_merge,
+                    "max_parallel_insert": args.max_parallel_insert,
+                    "cosine_threshold": args.cosine_threshold,
+                    "min_rerank_score": args.min_rerank_score,
+                    "related_chunk_number": args.related_chunk_number,
+                    "max_async": args.max_async,
+                    "embedding_func_max_async": args.embedding_func_max_async,
+                    "embedding_batch_num": args.embedding_batch_num,
                 },
                 "auth_mode": auth_mode,
                 "pipeline_busy": pipeline_status.get("busy", False),

lightrag/constants.py

@@ -6,12 +6,19 @@ different parts of the LightRAG system. Centralizing these values ensures
 consistency and makes maintenance easier.
 """
 
-# Default values for environment variables
-DEFAULT_MAX_GLEANING = 1
-DEFAULT_FORCE_LLM_SUMMARY_ON_MERGE = 4
+# Default values for server settings
 DEFAULT_WOKERS = 2
 DEFAULT_TIMEOUT = 150
 
+# Default values for extraction settings
+DEFAULT_SUMMARY_LANGUAGE = "English"  # Default language for summaries
+DEFAULT_FORCE_LLM_SUMMARY_ON_MERGE = 4
+DEFAULT_MAX_GLEANING = 1
+DEFAULT_MAX_TOKENS = 10000  # Default maximum token size
+
+# Separator for graph fields
+GRAPH_FIELD_SEP = "<SEP>"
+
 # Query and retrieval configuration defaults
 DEFAULT_TOP_K = 40
 DEFAULT_CHUNK_TOP_K = 10
@@ -26,12 +33,16 @@ DEFAULT_RELATED_CHUNK_NUMBER = 5
 DEFAULT_ENABLE_RERANK = True
 DEFAULT_MIN_RERANK_SCORE = 0.0
 
-# Separator for graph fields
-GRAPH_FIELD_SEP = "<SEP>"
-
 # File path configuration for vector and graph database
 DEFAULT_MAX_FILE_PATH_LENGTH = 4090
 
+# 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
+
 # Logging configuration defaults
 DEFAULT_LOG_MAX_BYTES = 10485760  # Default 10MB
 DEFAULT_LOG_BACKUP_COUNT = 5  # Default 5 backups