yujunjun/LightRAG
1
0
Fork 0
mirror of https://github.com/HKUDS/LightRAG.git synced 2025-11-18 11:04:42 +00:00
Code Issues Packages Projects Releases Wiki Activity
LightRAG/env.example

346 lines
12 KiB
Plaintext
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

### 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
### gunicorn worker timeout(as default LLM request timeout if LLM_TIMEOUT is not set)
# TIMEOUT=150
# 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>
### Tiktoken cache directory (Store cached files in this folder for offline deployment)
# TIKTOKEN_CACHE_DIR=./temp/tiktoken
### 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
###
### How to control the context lenght sent to LLM:
### MAX_ENTITY_TOKENS + MAX_RELATION_TOKENS < MAX_TOTAL_TOKENS
### Chunk_Tokens = MAX_TOTAL_TOKENS - Actual_Entity_Tokens - Actual_Reation_Tokens
######################################################################################
# LLM responde cache for query (Not valid for streaming response)
ENABLE_LLM_CACHE=true
# COSINE_THRESHOLD=0.2
### Number of entities or relations retrieved from KG
# TOP_K=40
### Maxmium number or chunks for naive vactor search
# CHUNK_TOP_K=20
### control the actual enties send to LLM
# MAX_ENTITY_TOKENS=6000
### control the actual relations send to LLM
# MAX_RELATION_TOKENS=8000
### 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
### The chunk picker uses this value to determine the total number of chunks selected from KG(knowledge graph)
### Higher values increase re-ranking time
# RELATED_CHUNK_NUMBER=5
### chunk selection strategies
### VECTOR: Pick KG chunks by vector similarity, delivered chunks to the LLM aligning more closely with naive retrieval
### WEIGHT: Pick KG chunks by entity and chunk weight, delivered more solely KG related chunks to the LLM
### If reranking is enabled, the impact of chunk selection strategies will be diminished.
# KG_CHUNK_PICK_METHOD=VECTOR
#########################################################
### Reranking configuration
### RERANK_BINDING type: null, cohere, jina, aliyun
### For rerank model deployed by vLLM use cohere binding
#########################################################
RERANK_BINDING=null
### Enable rerank by default in query params when RERANK_BINDING is not null
# RERANK_BY_DEFAULT=True
### rerank score chunk filter(set to 0.0 to keep all chunks, 0.6 or above if LLM is not strong enought)
# MIN_RERANK_SCORE=0.0
### For local deployment with vLLM
# RERANK_MODEL=BAAI/bge-reranker-v2-m3
# RERANK_BINDING_HOST=http://localhost:8000/v1/rerank
# RERANK_BINDING_API_KEY=your_rerank_api_key_here
### Default value for Cohere AI
# RERANK_MODEL=rerank-v3.5
# RERANK_BINDING_HOST=https://api.cohere.com/v2/rerank
# RERANK_BINDING_API_KEY=your_rerank_api_key_here
### Default value for Jina AI
# RERANK_MODELjina-reranker-v2-base-multilingual
# RERANK_BINDING_HOST=https://api.jina.ai/v1/rerank
# RERANK_BINDING_API_KEY=your_rerank_api_key_here
### Default value for Aliyun
# RERANK_MODEL=gte-rerank-v2
# RERANK_BINDING_HOST=https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-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
# SUMMARY_MAX_TOKENS=30000
### 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
### LLM_BINDING type: openai, ollama, lollms, azure_openai, aws_bedrock
###########################################################
### LLM request timeout setting for all llm (set to TIMEOUT if not specified, 0 means no timeout for Ollma)
# LLM_TIMEOUT=150
### Some models like o1-mini require temperature to be set to 1, some LLM can fall into output loops with low temperature
LLM_BINDING=openai
LLM_MODEL=gpt-4o
LLM_BINDING_HOST=https://api.openai.com/v1
LLM_BINDING_API_KEY=your_api_key
### Optional for Azure
# AZURE_OPENAI_API_VERSION=2024-08-01-preview
# AZURE_OPENAI_DEPLOYMENT=gpt-4o
### Openrouter example
# LLM_MODEL=google/gemini-2.5-flash
# LLM_BINDING_HOST=https://openrouter.ai/api/v1
# LLM_BINDING_API_KEY=your_api_key
# LLM_BINDING=openai
### OpenAI Specific Parameters
# OPENAI_LLM_TEMPERATURE=1.0
# OPENAI_LLM_REASONING_EFFORT=low
### For models like Qwen3 with fewer than 32B param, it is recommended to set the presence penalty to 1.5
# OPENAI_LLM_PRESENCE_PENALTY=1.5
### If the presence penalty still can not stop the model from generates repetitive or unconstrained output
# OPENAI_LLM_MAX_COMPLETION_TOKENS=16384
### OpenRouter Specific Parameters
# OPENAI_LLM_EXTRA_BODY='{"reasoning": {"enabled": false}}'
### Qwen3 Specific Parameters depoly by vLLM
# OPENAI_LLM_EXTRA_BODY='{"chat_template_kwargs": {"enable_thinking": false}}'
### use the following command to see all support options for OpenAI, azure_openai or OpenRouter
### lightrag-server --llm-binding openai --help
### Ollama Server Specific Parameters
### OLLAMA_LLM_NUM_CTX must be provided, and should at least larger than MAX_TOTAL_TOKENS + 2000
OLLAMA_LLM_NUM_CTX=32768
# OLLAMA_LLM_TEMPERATURE=1.0
### Stop sequences for Ollama LLM
# OLLAMA_LLM_STOP='["</s>", "Assistant:", "\n\n"]'
### use the following command to see all support options for Ollama LLM
### lightrag-server --llm-binding ollama --help
### Bedrock Specific Parameters
# BEDROCK_LLM_TEMPERATURE=1.0
####################################################################################
### Embedding Configuration (Should not be changed after the first file processed)
### EMBEDDING_BINDING: ollama, openai, azure_openai, jina, lollms, aws_bedrock
####################################################################################
### 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 (VoyageAI embedding 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
### Optional for Ollama embedding
OLLAMA_EMBEDDING_NUM_CTX=8192
### use the following command to see all support options for Ollama embedding
### lightrag-server --embedding-binding ollama --help
####################################################################
### 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 Vector Storage Configuration
### Vector storage type: HNSW, IVFFlat
POSTGRES_VECTOR_INDEX_TYPE=HNSW
POSTGRES_HNSW_M=16
POSTGRES_HNSW_EF=200
POSTGRES_IVFFLAT_LISTS=100
### 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_DATABASE=chunk-entity-relation
NEO4J_MAX_CONNECTION_POOL_SIZE=100
NEO4J_CONNECTION_TIMEOUT=30
NEO4J_CONNECTION_ACQUISITION_TIMEOUT=30
NEO4J_MAX_TRANSACTION_RETRY_TIME=30
NEO4J_MAX_CONNECTION_LIFETIME=300
NEO4J_LIVENESS_CHECK_TIMEOUT=30
NEO4J_KEEP_ALIVE=true
# 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
Reference in New Issue View Git Blame Copy Permalink