mirror of
https://github.com/HKUDS/LightRAG.git
synced 2025-12-02 01:46:30 +00:00
9923821d75
This parameter is no longer used. Its removal simplifies the API and clarifies that token length management is handled by upstream text chunking logic rather than the embedding wrapper.
262 lines
8.6 KiB
Plaintext
262 lines
8.6 KiB
Plaintext
### This is sample file of .env
|
||
|
||
###########################
|
||
### Server Configuration
|
||
###########################
|
||
HOST=0.0.0.0
|
||
PORT=9621
|
||
WEBUI_TITLE='My Graph KB'
|
||
WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
|
||
# WORKERS=2
|
||
# CORS_ORIGINS=http://localhost:3000,http://localhost:8080
|
||
|
||
### Optional SSL Configuration
|
||
# SSL=true
|
||
# SSL_CERTFILE=/path/to/cert.pem
|
||
# SSL_KEYFILE=/path/to/key.pem
|
||
|
||
### Directory Configuration (defaults to current working directory)
|
||
### Default value is ./inputs and ./rag_storage
|
||
# INPUT_DIR=<absolute_path_for_doc_input_dir>
|
||
# WORKING_DIR=<absolute_path_for_working_dir>
|
||
|
||
### Ollama Emulating Model and Tag
|
||
# OLLAMA_EMULATING_MODEL_NAME=lightrag
|
||
OLLAMA_EMULATING_MODEL_TAG=latest
|
||
|
||
### Max nodes return from grap retrieval in webui
|
||
# MAX_GRAPH_NODES=1000
|
||
|
||
### Logging level
|
||
# LOG_LEVEL=INFO
|
||
# VERBOSE=False
|
||
# LOG_MAX_BYTES=10485760
|
||
# LOG_BACKUP_COUNT=5
|
||
### Logfile location (defaults to current working directory)
|
||
# LOG_DIR=/path/to/log/directory
|
||
|
||
#####################################
|
||
### Login and API-Key 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/*
|
||
|
||
########################
|
||
### Query Configuration
|
||
########################
|
||
# LLM responde cache for query (Not valid for streaming response)
|
||
ENABLE_LLM_CACHE=true
|
||
# HISTORY_TURNS=0
|
||
# COSINE_THRESHOLD=0.2
|
||
### 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=30000
|
||
### maximum number of related chunks per source entity or relation (higher values increase re-ranking time)
|
||
# RELATED_CHUNK_NUMBER=5
|
||
|
||
### Reranker configuration (Set ENABLE_RERANK to true in reranking model is configed)
|
||
# ENABLE_RERANK=True
|
||
### Minimum rerank score for document chunk exclusion (set to 0.0 to keep all chunks, 0.6 or above if LLM is not strong enought)
|
||
# MIN_RERANK_SCORE=0.0
|
||
### Rerank model configuration (required when ENABLE_RERANK=True)
|
||
# RERANK_MODEL=jina-reranker-v2-base-multilingual
|
||
# RERANK_BINDING_HOST=https://api.jina.ai/v1/rerank
|
||
# RERANK_BINDING_API_KEY=your_rerank_api_key_here
|
||
|
||
########################################
|
||
### Document processing configuration
|
||
########################################
|
||
### Language: English, Chinese, French, German ...
|
||
SUMMARY_LANGUAGE=English
|
||
ENABLE_LLM_CACHE_FOR_EXTRACT=true
|
||
### 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)， and max tokens send to LLM
|
||
# FORCE_LLM_SUMMARY_ON_MERGE=4
|
||
# MAX_TOKENS=10000
|
||
### Maximum number of entity extraction attempts for ambiguous content
|
||
# MAX_GLEANING=1
|
||
|
||
###############################
|
||
### 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/3 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
|
||
#######################
|
||
### 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
|
||
### 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 (Must be larger than MAX_TOTAL_TOKENS+2000)
|
||
### see also env.ollama-binding-options.example for fine tuning ollama
|
||
# OLLAMA_LLM_NUM_CTX=32768
|
||
|
||
### Optional for Azure
|
||
# AZURE_OPENAI_API_VERSION=2024-08-01-preview
|
||
# AZURE_OPENAI_DEPLOYMENT=gpt-4o
|
||
|
||
####################################################################################
|
||
### Embedding Configuration (Should not be changed after the first file processed)
|
||
####################################################################################
|
||
### Embedding Binding type: openai, ollama, lollms, azure_openai, jina
|
||
|
||
### see also env.ollama-binding-options.example for fine tuning ollama
|
||
EMBEDDING_BINDING=ollama
|
||
EMBEDDING_MODEL=bge-m3:latest
|
||
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
|
||
|
||
### OpenAI compatible
|
||
# EMBEDDING_BINDING=openai
|
||
# EMBEDDING_MODEL=text-embedding-3-large
|
||
# EMBEDDING_DIM=3072
|
||
# EMBEDDING_BINDING_HOST=https://api.openai.com
|
||
# EMBEDDING_BINDING_API_KEY=your_api_key
|
||
|
||
### 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
|
||
|
||
### Jina AI Embedding
|
||
EMBEDDING_BINDING=jina
|
||
EMBEDDING_BINDING_HOST=https://api.jina.ai/v1/embeddings
|
||
EMBEDDING_MODEL=jina-embeddings-v4
|
||
EMBEDDING_DIM=2048
|
||
EMBEDDING_BINDING_API_KEY=your_api_key
|
||
|
||
####################################################################
|
||
### WORKSPACE setting workspace name for all storage types
|
||
### in the purpose of isolating data from LightRAG instances.
|
||
### Valid workspace name constraints: a-z, A-Z, 0-9, and _
|
||
####################################################################
|
||
# WORKSPACE=space1
|
||
|
||
############################
|
||
### Data storage selection
|
||
############################
|
||
### 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
|
||
|
||
### PostgreSQL Configuration
|
||
POSTGRES_HOST=localhost
|
||
POSTGRES_PORT=5432
|
||
POSTGRES_USER=your_username
|
||
POSTGRES_PASSWORD='your_password'
|
||
POSTGRES_DATABASE=your_database
|
||
POSTGRES_MAX_CONNECTIONS=12
|
||
# POSTGRES_WORKSPACE=forced_workspace_name
|
||
|
||
### PostgreSQL SSL Configuration (Optional)
|
||
# POSTGRES_SSL_MODE=require
|
||
# POSTGRES_SSL_CERT=/path/to/client-cert.pem
|
||
# POSTGRES_SSL_KEY=/path/to/client-key.pem
|
||
# POSTGRES_SSL_ROOT_CERT=/path/to/ca-cert.pem
|
||
# POSTGRES_SSL_CRL=/path/to/crl.pem
|
||
|
||
### Neo4j Configuration
|
||
NEO4J_URI=neo4j+s://xxxxxxxx.databases.neo4j.io
|
||
NEO4J_USERNAME=neo4j
|
||
NEO4J_PASSWORD='your_password'
|
||
NEO4J_MAX_CONNECTION_POOL_SIZE=100
|
||
NEO4J_CONNECTION_TIMEOUT=30
|
||
NEO4J_CONNECTION_ACQUISITION_TIMEOUT=30
|
||
MAX_TRANSACTION_RETRY_TIME=30
|
||
# NEO4J_WORKSPACE=forced_workspace_name
|
||
|
||
### MongoDB Configuration
|
||
MONGO_URI=mongodb://root:root@localhost:27017/
|
||
#MONGO_URI=mongodb+srv://xxxx
|
||
MONGO_DATABASE=LightRAG
|
||
# MONGODB_WORKSPACE=forced_workspace_name
|
||
|
||
### Milvus Configuration
|
||
MILVUS_URI=http://localhost:19530
|
||
MILVUS_DB_NAME=lightrag
|
||
# MILVUS_USER=root
|
||
# MILVUS_PASSWORD=your_password
|
||
# MILVUS_TOKEN=your_token
|
||
# MILVUS_WORKSPACE=forced_workspace_name
|
||
|
||
### Qdrant
|
||
QDRANT_URL=http://localhost:6333
|
||
# QDRANT_API_KEY=your-api-key
|
||
# QDRANT_WORKSPACE=forced_workspace_name
|
||
|
||
### Redis
|
||
REDIS_URI=redis://localhost:6379
|
||
REDIS_SOCKET_TIMEOUT=30
|
||
REDIS_CONNECT_TIMEOUT=10
|
||
REDIS_MAX_CONNECTIONS=100
|
||
REDIS_RETRY_ATTEMPTS=3
|
||
# REDIS_WORKSPACE=forced_workspace_name
|
||
|
||
### Memgraph Configuration
|
||
MEMGRAPH_URI=bolt://localhost:7687
|
||
MEMGRAPH_USERNAME=
|
||
MEMGRAPH_PASSWORD=
|
||
MEMGRAPH_DATABASE=memgraph
|
||
# MEMGRAPH_WORKSPACE=forced_workspace_name
|