Update env sample file

env.example

@@ -1,12 +1,25 @@
 ### This is sample file of .env
 
+
 ### Server Configuration
-# HOST=0.0.0.0
-# PORT=9621
+HOST=0.0.0.0
+PORT=9621
+WEBUI_TITLE='My Graph KB'
+WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
+OLLAMA_EMULATING_MODEL_TAG=latest
 # WORKERS=2
 # CORS_ORIGINS=http://localhost:3000,http://localhost:8080
-WEBUI_TITLE='Graph RAG Engine'
-WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
+
+### 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
@@ -14,11 +27,10 @@ WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
 # SSL_KEYFILE=/path/to/key.pem
 
 ### Directory Configuration (defaults to current working directory)
-# WORKING_DIR=<absolute_path_for_working_dir>
+### Should 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>
-
-### Ollama Emulating Model Tag
-# OLLAMA_EMULATING_MODEL_TAG=latest
+# WORKING_DIR=<absolute_path_for_working_dir>
 
 ### Max nodes return from grap retrieval
 # MAX_GRAPH_NODES=1000
@@ -39,82 +51,57 @@ WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
 # MAX_TOKEN_RELATION_DESC=4000
 # MAX_TOKEN_ENTITY_DESC=4000
 
-### Settings for document indexing
+### Entity and ralation summarization configuration
+### Language: English, Chinese, French, German ...
 SUMMARY_LANGUAGE=English
-# CHUNK_SIZE=1200
-# CHUNK_OVERLAP_SIZE=100
-
-### Number of parallel processing documents in one patch
-# MAX_PARALLEL_INSERT=2
-
+### Number of duplicated entities/edges to trigger LLM re-summary on merge ( at least 3 is recommented)
+# FORCE_LLM_SUMMARY_ON_MERGE=6
 ### Max tokens for entity/relations description after merge
 # MAX_TOKEN_SUMMARY=500
-### Number of entities/edges to trigger LLM re-summary on merge ( at least 3 is recommented)
-# FORCE_LLM_SUMMARY_ON_MERGE=6
 
-### Num of chunks send to Embedding in single request
-# EMBEDDING_BATCH_NUM=32
-### Max concurrency requests for Embedding
-# EMBEDDING_FUNC_MAX_ASYNC=16
-# MAX_EMBED_TOKENS=8192
+### Number of parallel processing documents(Less than MAX_ASYNC/2 is recommended)
+# MAX_PARALLEL_INSERT=2
+### Chunk size for document splitting, 500~1500 is recommended
+# CHUNK_SIZE=1200
+# CHUNK_OVERLAP_SIZE=100
 
 ### LLM Configuration
+ENABLE_LLM_CACHE=true
+ENABLE_LLM_CACHE_FOR_EXTRACT=true
 ### Time out in seconds for LLM, None for infinite timeout
-TIMEOUT=150
+TIMEOUT=240
 ### Some models like o1-mini require temperature to be set to 1
-TEMPERATURE=0.5
+TEMPERATURE=0
 ### Max concurrency requests of LLM
 MAX_ASYNC=4
-### Max tokens send to LLM (less than context size of the model)
+### Max tokens send to LLM for entity relation summaries (less than context size of the model)
 MAX_TOKENS=32768
-ENABLE_LLM_CACHE=true
-ENABLE_LLM_CACHE_FOR_EXTRACT=true
-
-### Ollama example (For local services installed with docker, you can use host.docker.internal as host)
-LLM_BINDING=ollama
-LLM_MODEL=mistral-nemo:latest
+### LLM Binding type: openai, ollama, lollms
+LLM_BINDING=openai
+LLM_MODEL=gpt-4o
+LLM_BINDING_HOST=https://api.openai.com/v1
 LLM_BINDING_API_KEY=your_api_key
-LLM_BINDING_HOST=http://localhost:11434
-
-### OpenAI alike example
-# LLM_BINDING=openai
-# LLM_MODEL=gpt-4o
-# LLM_BINDING_HOST=https://api.openai.com/v1
-# LLM_BINDING_API_KEY=your_api_key
-### lollms example
-# LLM_BINDING=lollms
-# LLM_MODEL=mistral-nemo:latest
-# LLM_BINDING_HOST=http://localhost:9600
-# LLM_BINDING_API_KEY=your_api_key
-
-### Embedding Configuration (Use valid host. For local services installed with docker, you can use host.docker.internal)
+
+### Embedding Configuration
+### Embedding Binding type: openai, ollama, lollms
+EMBEDDING_BINDING=ollama
 EMBEDDING_MODEL=bge-m3:latest
 EMBEDDING_DIM=1024
-# EMBEDDING_BINDING_API_KEY=your_api_key
-### ollama example
-EMBEDDING_BINDING=ollama
+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
-### OpenAI alike example
-# EMBEDDING_BINDING=openai
-# EMBEDDING_BINDING_HOST=https://api.openai.com/v1
-### Lollms example
-# EMBEDDING_BINDING=lollms
-# EMBEDDING_BINDING_HOST=http://localhost:9600
-
-### Optional for Azure (LLM_BINDING_HOST, LLM_BINDING_API_KEY take priority)
-# AZURE_OPENAI_API_VERSION=2024-08-01-preview
-# AZURE_OPENAI_DEPLOYMENT=gpt-4o
-# AZURE_OPENAI_API_KEY=your_api_key
-# AZURE_OPENAI_ENDPOINT=https://myendpoint.openai.azure.com
-
-# AZURE_EMBEDDING_DEPLOYMENT=text-embedding-3-large
-# AZURE_EMBEDDING_API_VERSION=2023-05-15
+### Num of chunks send to Embedding in single request
+# EMBEDDING_BATCH_NUM=32
+### Max concurrency requests for Embedding
+# EMBEDDING_FUNC_MAX_ASYNC=16
+### Maximum tokens sent to Embedding for each chunk (no longer in use?)
+# MAX_EMBED_TOKENS=8192
 
 ### Data storage selection
-LIGHTRAG_KV_STORAGE=JsonKVStorage
-LIGHTRAG_VECTOR_STORAGE=NanoVectorDBStorage
-LIGHTRAG_GRAPH_STORAGE=NetworkXStorage
-LIGHTRAG_DOC_STATUS_STORAGE=JsonDocStatusStorage
+# LIGHTRAG_KV_STORAGE=PGKVStorage
+# LIGHTRAG_VECTOR_STORAGE=PGVectorStorage
+# LIGHTRAG_DOC_STATUS_STORAGE=PGDocStatusStorage
+# LIGHTRAG_GRAPH_STORAGE=Neo4JStorage
 
 ### TiDB Configuration (Deprecated)
 # TIDB_HOST=localhost
@@ -135,22 +122,22 @@ POSTGRES_MAX_CONNECTIONS=12
 ### separating all data from difference Lightrag instances(deprecating)
 # POSTGRES_WORKSPACE=default
 
+### Neo4j Configuration
+NEO4J_URI=neo4j+s://xxxxxxxx.databases.neo4j.io
+NEO4J_USERNAME=neo4j
+NEO4J_PASSWORD='your_password'
+
 ### Independent AGM Configuration(not for AMG embedded in PostreSQL)
-AGE_POSTGRES_DB=
-AGE_POSTGRES_USER=
-AGE_POSTGRES_PASSWORD=
-AGE_POSTGRES_HOST=
+# AGE_POSTGRES_DB=
+# AGE_POSTGRES_USER=
+# AGE_POSTGRES_PASSWORD=
+# AGE_POSTGRES_HOST=
 # AGE_POSTGRES_PORT=8529
 
 # AGE Graph Name(apply to PostgreSQL and independent AGM)
 ### AGE_GRAPH_NAME is precated
 # AGE_GRAPH_NAME=lightrag
 
-### Neo4j Configuration
-NEO4J_URI=neo4j+s://xxxxxxxx.databases.neo4j.io
-NEO4J_USERNAME=neo4j
-NEO4J_PASSWORD='your_password'
-
 ### MongoDB Configuration
 MONGO_URI=mongodb://root:root@localhost:27017/
 MONGO_DATABASE=LightRAG
@@ -170,14 +157,3 @@ QDRANT_URL=http://localhost:16333
 
 ### Redis
 REDIS_URI=redis://localhost:6379
-
-### For JWT Auth
-# 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/*