From c8c59c38b0350922a51587d3afa7ae57fad3097e Mon Sep 17 00:00:00 2001
From: yangdx <gzdaniel@me.com>
Date: Mon, 1 Sep 2025 00:14:57 +0800
Subject: [PATCH] Fix entity types configuration to support JSON list parsing

- Add JSON parsing for list env vars
- Update entity types example format
- Add list type support to get_env_value
---
 env.example            |  2 +-
 lightrag/api/config.py |  2 +-
 lightrag/utils.py      | 21 +++++++++++++++++++++
 3 files changed, 23 insertions(+), 2 deletions(-)

diff --git a/env.example b/env.example
index 02b3ec00..4ab64aba 100644
--- a/env.example
+++ b/env.example
@@ -125,7 +125,7 @@ ENABLE_LLM_CACHE_FOR_EXTRACT=true
 SUMMARY_LANGUAGE=English
 
 ### Entity types that the LLM will attempt to recognize
-# ENTITY_TYPES=["organization", "person", "equiment", "product", "technology", "location", "event", "category"]
+# ENTITY_TYPES='["Organization", "Person", "Equiment", "Product", "Technology", "Location", "Event", "Category"]'
 
 ### Chunk size for document splitting, 500~1500 is recommended
 # CHUNK_SIZE=1200
diff --git a/lightrag/api/config.py b/lightrag/api/config.py
index eae2f45b..f17d50f0 100644
--- a/lightrag/api/config.py
+++ b/lightrag/api/config.py
@@ -352,7 +352,7 @@ 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", DEFAULT_SUMMARY_LANGUAGE)
-    args.entity_types = get_env_value("ENTITY_TYPES", DEFAULT_ENTITY_TYPES)
+    args.entity_types = get_env_value("ENTITY_TYPES", DEFAULT_ENTITY_TYPES, list)
     args.whitelist_paths = get_env_value("WHITELIST_PATHS", "/health,/api/*")
 
     # For JWT Auth
diff --git a/lightrag/utils.py b/lightrag/utils.py
index ab4787c4..7c92d99c 100644
--- a/lightrag/utils.py
+++ b/lightrag/utils.py
@@ -82,6 +82,27 @@ def get_env_value(
 
     if value_type is bool:
         return value.lower() in ("true", "1", "yes", "t", "on")
+
+    # Handle list type with JSON parsing
+    if value_type is list:
+        try:
+            import json
+
+            parsed_value = json.loads(value)
+            # Ensure the parsed value is actually a list
+            if isinstance(parsed_value, list):
+                return parsed_value
+            else:
+                logger.warning(
+                    f"Environment variable {env_key} is not a valid JSON list, using default"
+                )
+                return default
+        except (json.JSONDecodeError, ValueError) as e:
+            logger.warning(
+                f"Failed to parse {env_key} as JSON list: {e}, using default"
+            )
+            return default
+
     try:
         return value_type(value)
     except (ValueError, TypeError):