Fix critical issues and improve best practices in .env.unraid.example

Critical fixes:
- Fix SUMMARY_LENGTH_RECOMMENDED_ typo (trailing underscore)
- Change LLM_MODEL from gpt-5-mini to gpt-4o-mini (GPT-5 doesn't exist)
- Update all GPT-5 references to GPT-4o in comments

Best practice improvements:
- Reduce NEO4J_MAX_CONNECTION_POOL_SIZE from 75 to 50 (better for 6-core system)
- Add logging rotation settings (LOG_MAX_BYTES, LOG_BACKUP_COUNT)
- Add Advanced Entity/Relation Management settings documentation

The Advanced Entity/Relation Management settings help users control metadata
storage for entities/relations in the knowledge graph, which is especially
useful when processing large books where entities appear in many chunks.

.env.unraid.example

@@ -2,7 +2,7 @@
 ### LightRAG Configuration - Optimized for Books, Articles, and Podcast Transcripts
 ###
 ### FILL IN THE FOLLOWING PLACEHOLDERS:
-### - YOUR_OPENAI_API_KEY_HERE (for GPT-5-mini)
+### - YOUR_OPENAI_API_KEY_HERE (for GPT-4o-mini)
 ### - YOUR_VOYAGE_API_KEY_HERE (for voyage-3-large embeddings)
 ### - YOUR_JINA_API_KEY_HERE (for Jina reranker)
 ### - Neo4j connection details (URI, username, password, database)
@@ -31,6 +31,10 @@ TIMEOUT=180
 LOG_LEVEL=INFO
 # LOG_DIR=/path/to/logs
 
+### Log rotation (optional but recommended for production)
+# LOG_MAX_BYTES=10485760      # 10MB per log file
+# LOG_BACKUP_COUNT=5           # Keep 5 backup files
+
 #####################################
 ### Authentication (Optional)
 #####################################
@@ -84,12 +88,19 @@ ENTITY_TYPES='["Person", "Organization", "Location", "Event", "Concept", "Method
 ### Summary configuration
 FORCE_LLM_SUMMARY_ON_MERGE=8
 SUMMARY_MAX_TOKENS=1500
-SUMMARY_LENGTH_RECOMMENDED_=800
+SUMMARY_LENGTH_RECOMMENDED=800
 SUMMARY_CONTEXT_SIZE=15000
 
 ### Related chunks per entity/relation
 RELATED_CHUNK_NUMBER=5
 
+### Advanced Entity/Relation Management (optional)
+### Controls metadata storage for entities and relations in the knowledge graph
+# MAX_SOURCE_IDS_PER_ENTITY=300    # Max chunk IDs stored per entity (default: 300)
+# MAX_SOURCE_IDS_PER_RELATION=300  # Max chunk IDs stored per relation (default: 300)
+# SOURCE_IDS_LIMIT_METHOD=FIFO     # FIFO (drop oldest) or KEEP (keep oldest, faster)
+# MAX_FILE_PATHS=100               # Max file paths shown in metadata (display only)
+
 ###############################
 ### Concurrency Configuration
 ### Optimized for Dell T140 (6-core Xeon E-2226G, 32GB RAM)
@@ -100,15 +111,15 @@ EMBEDDING_FUNC_MAX_ASYNC=12
 EMBEDDING_BATCH_NUM=10
 
 ###########################################################################
-### LLM Configuration - OpenAI GPT-5-mini
+### LLM Configuration - OpenAI GPT-4o-mini
 ###########################################################################
 LLM_BINDING=openai
-LLM_MODEL=gpt-5-mini
+LLM_MODEL=gpt-4o-mini
 LLM_BINDING_HOST=https://api.openai.com/v1
 LLM_BINDING_API_KEY=YOUR_OPENAI_API_KEY_HERE
 LLM_TIMEOUT=180
 
-### GPT-5 configuration
+### GPT-4o configuration
 OPENAI_LLM_MAX_COMPLETION_TOKENS=9000
 OPENAI_LLM_TEMPERATURE=0.7
 
@@ -189,7 +200,7 @@ NEO4J_PASSWORD='YOUR_NEO4J_PASSWORD_HERE'
 NEO4J_DATABASE=neo4j
 
 ### Neo4j connection pool settings (optimized for your Dell T140)
-NEO4J_MAX_CONNECTION_POOL_SIZE=75
+NEO4J_MAX_CONNECTION_POOL_SIZE=50
 NEO4J_CONNECTION_TIMEOUT=30
 NEO4J_CONNECTION_ACQUISITION_TIMEOUT=30
 NEO4J_MAX_TRANSACTION_RETRY_TIME=30
@@ -223,7 +234,7 @@ NEO4J_KEEP_ALIVE=true
 ### QUICK START CHECKLIST
 ###########################################################################################
 ### 1. Fill in API keys:
-###    - YOUR_OPENAI_API_KEY_HERE (for GPT-5-mini)
+###    - YOUR_OPENAI_API_KEY_HERE (for GPT-4o-mini)
 ###    - YOUR_VOYAGE_API_KEY_HERE (for voyage-3-large embeddings)
 ###    - YOUR_JINA_API_KEY_HERE (for reranking)
 ###