### 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= # 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 ### Reranker 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 # SUMMARY_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 ### 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='["", "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 type: ollama, openai, azure_openai, jina, lollms ### 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