Update env.example

env.example

@@ -1,6 +1,8 @@
 ### This is sample file of .env
 
+###########################
 ### Server Configuration
+###########################
 HOST=0.0.0.0
 PORT=9621
 WEBUI_TITLE='My Graph KB'
@@ -9,29 +11,17 @@ OLLAMA_EMULATING_MODEL_TAG=latest
 # WORKERS=2
 # CORS_ORIGINS=http://localhost:3000,http://localhost:8080
 
-### Login Configuration
-# AUTH_ACCOUNTS='admin:admin123,user1:pass456'
-# TOKEN_SECRET=Your-Key-For-LightRAG-API-Server
-# TOKEN_EXPIRE_HOURS=48
-# GUEST_TOKEN_EXPIRE_HOURS=24
-# JWT_ALGORITHM=HS256
-
-### API-Key to access LightRAG Server API
-# LIGHTRAG_API_KEY=your-secure-api-key-here
-# WHITELIST_PATHS=/health,/api/*
-
 ### Optional SSL Configuration
 # SSL=true
 # SSL_CERTFILE=/path/to/cert.pem
 # SSL_KEYFILE=/path/to/key.pem
 
 ### Directory Configuration (defaults to current working directory)
-### Should not be set if deploy by docker (Set by Dockerfile instead of .env)
 ### Default value is ./inputs and ./rag_storage
 # INPUT_DIR=<absolute_path_for_doc_input_dir>
 # WORKING_DIR=<absolute_path_for_working_dir>
 
-### Max nodes return from grap retrieval
+### Max nodes return from grap retrieval in webui
 # MAX_GRAPH_NODES=1000
 
 ### Logging level
@@ -42,68 +32,95 @@ OLLAMA_EMULATING_MODEL_TAG=latest
 ### Logfile location (defaults to current working directory)
 # LOG_DIR=/path/to/log/directory
 
-### RAG Configuration
+#####################################
-### Chunk size for document splitting, 500~1500 is recommended
+### Login and API-Key Configuration
-# CHUNK_SIZE=1200
+#####################################
-# CHUNK_OVERLAP_SIZE=100
+# AUTH_ACCOUNTS='admin:admin123,user1:pass456'
+# TOKEN_SECRET=Your-Key-For-LightRAG-API-Server
+# TOKEN_EXPIRE_HOURS=48
+# GUEST_TOKEN_EXPIRE_HOURS=24
+# JWT_ALGORITHM=HS256
 
-### RAG Query Configuration
+### API-Key to access LightRAG Server API
+# LIGHTRAG_API_KEY=your-secure-api-key-here
+# WHITELIST_PATHS=/health,/api/*
+
+########################
+### Query Configuration
+########################
+# LLM responde cache for query (Not valid for streaming response
+ENABLE_LLM_CACHE=true
 # HISTORY_TURNS=3
-
+# COSINE_THRESHOLD=0.2
-### These parameters provide more precise control over total token usage
+### Number of entities or relations retrieved from KG
+# TOP_K=40
+### Maxmium number or chunks plan to send to LLM
+# CHUNK_TOP_K=10
+### control the actual enties send to LLM
 # MAX_ENTITY_TOKENS=10000
+### control the actual relations send to LLM
 # MAX_RELATION_TOKENS=10000
+### control the maximum tokens send to LLM (include entities, raltions and chunks)
 # MAX_TOTAL_TOKENS=32000
 
-# COSINE_THRESHOLD=0.2
+### Reranker configuration (Set ENABLE_RERANK to true in reranking model is configed)
-### Number of entities or relations to retrieve from KG
+ENABLE_RERANK=False
-# TOP_K=40
-### Number of text chunks to retrieve initially from vector search and keep after reranking
-# CHUNK_TOP_K=10
-
-### Enable reranking for retrieved text chunks (default: true)
-# ENABLE_RERANK=true
-
-### Rerank Configuration
-### Rerank model configuration (required when enable_rerank=true in query parameters)
 # RERANK_MODEL=BAAI/bge-reranker-v2-m3
 # RERANK_BINDING_HOST=https://api.your-rerank-provider.com/v1/rerank
 # RERANK_BINDING_API_KEY=your_rerank_api_key_here
 
-### Entity and relation summarization configuration
+########################################
+### Document processing configuration
+########################################
 ### Language: English, Chinese, French, German ...
 SUMMARY_LANGUAGE=English
+ENABLE_LLM_CACHE_FOR_EXTRACT=true
+### MAX_TOKENS: max tokens send to LLM for entity relation summaries (less than context size of the model)
+MAX_TOKENS=32000
+### Chunk size for document splitting, 500~1500 is recommended
+# CHUNK_SIZE=1200
+# CHUNK_OVERLAP_SIZE=100
+### Entity and relation summarization configuration
 ### Number of duplicated entities/edges to trigger LLM re-summary on merge ( at least 3 is recommented)
-# FORCE_LLM_SUMMARY_ON_MERGE=6
+# FORCE_LLM_SUMMARY_ON_MERGE=4
 ### Maximum number of entity extraction attempts for ambiguous content
 # MAX_GLEANING=1
 
-### Number of parallel processing documents(Less than MAX_ASYNC/2 is recommended)
+###############################
-# MAX_PARALLEL_INSERT=2
+### Concurrency Configuration
+###############################
+### Max concurrency requests of LLM (for both query and document processing)
+MAX_ASYNC=4
+### Number of parallel processing documents(between 2~10, MAX_ASYNC/4 is recommended)
+MAX_PARALLEL_INSERT=2
+### Max concurrency requests for Embedding
+# EMBEDDING_FUNC_MAX_ASYNC=8
+### Num of chunks send to Embedding in single request
+# EMBEDDING_BATCH_NUM=10
 
+#######################
 ### LLM Configuration
-ENABLE_LLM_CACHE=true
+#######################
-ENABLE_LLM_CACHE_FOR_EXTRACT=true
 ### Time out in seconds for LLM, None for infinite timeout
 TIMEOUT=240
 ### Some models like o1-mini require temperature to be set to 1
 TEMPERATURE=0
-### Max concurrency requests of LLM
-MAX_ASYNC=4
-### MAX_TOKENS: max tokens send to LLM for entity relation summaries (less than context size of the model)
-MAX_TOKENS=32000
 ### LLM Binding type: openai, ollama, lollms, azure_openai
 LLM_BINDING=openai
 LLM_MODEL=gpt-4o
 LLM_BINDING_HOST=https://api.openai.com/v1
 LLM_BINDING_API_KEY=your_api_key
+
+### Set as num_ctx option for Ollama LLM
+# OLLAMA_NUM_CTX=32768
+
 ### Optional for Azure
 # AZURE_OPENAI_API_VERSION=2024-08-01-preview
 # AZURE_OPENAI_DEPLOYMENT=gpt-4o
-### set as num_ctx option for Ollama LLM
-# OLLAMA_NUM_CTX=32768
 
-### Embedding Configuration
+####################################################################################
+### Embedding Configuration (Should not be changed after the first file processed)
+####################################################################################
 ### Embedding Binding type: openai, ollama, lollms, azure_openai
 EMBEDDING_BINDING=ollama
 EMBEDDING_MODEL=bge-m3:latest
@@ -111,51 +128,53 @@ EMBEDDING_DIM=1024
 EMBEDDING_BINDING_API_KEY=your_api_key
 # If the embedding service is deployed within the same Docker stack, use host.docker.internal instead of localhost
 EMBEDDING_BINDING_HOST=http://localhost:11434
-### Num of chunks send to Embedding in single request
-# EMBEDDING_BATCH_NUM=10
-### Max concurrency requests for Embedding
-# EMBEDDING_FUNC_MAX_ASYNC=8
 ### Maximum tokens sent to Embedding for each chunk (no longer in use?)
 # MAX_EMBED_TOKENS=8192
+
 ### Optional for Azure
 # AZURE_EMBEDDING_DEPLOYMENT=text-embedding-3-large
 # AZURE_EMBEDDING_API_VERSION=2023-05-15
 # AZURE_EMBEDDING_ENDPOINT=your_endpoint
 # AZURE_EMBEDDING_API_KEY=your_api_key
 
-###########################
+############################
 ### Data storage selection
-###########################
+############################
-### In-memory database with local file persistence(Recommended for small scale deployment)
+### Default storage (Recommended for small scale deployment)
 # LIGHTRAG_KV_STORAGE=JsonKVStorage
 # LIGHTRAG_DOC_STATUS_STORAGE=JsonDocStatusStorage
 # LIGHTRAG_GRAPH_STORAGE=NetworkXStorage
 # LIGHTRAG_VECTOR_STORAGE=NanoVectorDBStorage
+
+### Redis Storage (Recommended for production deployment)
+# LIGHTRAG_KV_STORAGE=RedisKVStorage
+# LIGHTRAG_DOC_STATUS_STORAGE=RedisDocStatusStorage
+
+### Vector Storage (Recommended for production deployment)
+# LIGHTRAG_VECTOR_STORAGE=MilvusVectorDBStorage
+# LIGHTRAG_VECTOR_STORAGE=QdrantVectorDBStorage
 # LIGHTRAG_VECTOR_STORAGE=FaissVectorDBStorage
+
+### Graph Storage (Recommended for production deployment)
+# LIGHTRAG_GRAPH_STORAGE=Neo4JStorage
+# LIGHTRAG_GRAPH_STORAGE=MemgraphStorage
+
 ### PostgreSQL
 # LIGHTRAG_KV_STORAGE=PGKVStorage
 # LIGHTRAG_DOC_STATUS_STORAGE=PGDocStatusStorage
 # LIGHTRAG_GRAPH_STORAGE=PGGraphStorage
 # LIGHTRAG_VECTOR_STORAGE=PGVectorStorage
+
 ### MongoDB (Vector storage only available on Atlas Cloud)
 # LIGHTRAG_KV_STORAGE=MongoKVStorage
 # LIGHTRAG_DOC_STATUS_STORAGE=MongoDocStatusStorage
 # LIGHTRAG_GRAPH_STORAGE=MongoGraphStorage
 # LIGHTRAG_VECTOR_STORAGE=MongoVectorDBStorage
-### Redis Storage (Recommended for production deployment)
-# LIGHTRAG_KV_STORAGE=RedisKVStorage
-# LIGHTRAG_DOC_STATUS_STORAGE=RedisDocStatusStorage
-### Vector Storage (Recommended for production deployment)
-# LIGHTRAG_VECTOR_STORAGE=MilvusVectorDBStorage
-# LIGHTRAG_VECTOR_STORAGE=QdrantVectorDBStorage
-### Graph Storage (Recommended for production deployment)
-# LIGHTRAG_GRAPH_STORAGE=Neo4JStorage
-# LIGHTRAG_GRAPH_STORAGE=MemgraphStorage
 
 ####################################################################
-### Default workspace for all storage types
+### WORKSPACE setting workspace name for all storage types
-### For the purpose of isolation of data for each LightRAG instance
+### in the purpose of isolating data from LightRAG instances.
-### Valid characters: a-z, A-Z, 0-9, and _
+### Valid workspace name constraints: a-z, A-Z, 0-9, and _
 ####################################################################
 # WORKSPACE=space1