From 9030280a583fd6af820d192fc8103528c472c04e Mon Sep 17 00:00:00 2001 From: Claude Date: Sat, 15 Nov 2025 10:25:46 +0000 Subject: [PATCH] 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 | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/.env.unraid.example b/.env.unraid.example index f1aa492b..a082c325 100644 --- a/.env.unraid.example +++ b/.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) ###