2255b91210
Introduces the LightRAG Retrieval-Augmented Generation framework as an Apolo app, including input/output schemas, types, and processors. Adds Helm chart value processing, environment and persistence configurations, and output service discovery for deployment. Includes scripts for generating type schemas and testing support, along with CI and linting setup tailored for the new app. Provides a documentation loader script to ingest markdown files into LightRAG with flexible referencing modes. Relates to MLO-469
216 lines
6.4 KiB
Text
216 lines
6.4 KiB
Text
# ==============================================
|
|
# LIGHTRAG CONFIGURATION
|
|
# ==============================================
|
|
OPENAI_API_KEY=sk-your-openai-api-key-here
|
|
|
|
# Server Configuration
|
|
HOST=0.0.0.0
|
|
PORT=9621
|
|
WEBUI_TITLE=LightRAG - Graph KB
|
|
WEBUI_DESCRIPTION=Graph-based RAG with PostgreSQL and pgvector
|
|
|
|
# LLM Configuration for LightRAG (OpenRouter)
|
|
LLM_BINDING=openai
|
|
LLM_MODEL=openai/o3-mini
|
|
LLM_BINDING_HOST=https://openrouter.ai/api/v1
|
|
LLM_BINDING_API_KEY=sk-your-openai-api-key-here
|
|
|
|
|
|
# Embedding Configuration for LightRAG (OpenAI direct)
|
|
# EMBEDDING_BINDING=openai
|
|
# EMBEDDING_MODEL=text-embedding-ada-002
|
|
# EMBEDDING_DIM=1536
|
|
# EMBEDDING_BINDING_HOST=https://api.openai.com/v1
|
|
# EMBEDDING_BINDING_API_KEY=sk-your-openai-api-key-here
|
|
EMBEDDING_BINDING=openai
|
|
EMBEDDING_MODEL=gemini-embedding-001
|
|
EMBEDDING_DIM=3072
|
|
EMBEDDING_BINDING_HOST=https://generativelanguage.googleapis.com/v1beta/openai/
|
|
EMBEDDING_BINDING_API_KEY=AI-your-gemini-api-key-here
|
|
|
|
# Storage Backend Configuration
|
|
LIGHTRAG_KV_STORAGE=PGKVStorage
|
|
LIGHTRAG_VECTOR_STORAGE=PGVectorStorage
|
|
LIGHTRAG_DOC_STATUS_STORAGE=PGDocStatusStorage
|
|
LIGHTRAG_GRAPH_STORAGE=NetworkXStorage
|
|
|
|
# PostgreSQL Configuration
|
|
POSTGRES_HOST=postgres
|
|
POSTGRES_PORT=5432
|
|
POSTGRES_USER=lightrag_user
|
|
POSTGRES_PASSWORD=lightrag_pass
|
|
POSTGRES_DATABASE=lightrag
|
|
POSTGRES_MAX_CONNECTIONS=12
|
|
|
|
# LightRAG Processing Configuration
|
|
ENABLE_LLM_CACHE=true
|
|
ENABLE_LLM_CACHE_FOR_EXTRACT=true
|
|
TIMEOUT=240
|
|
TEMPERATURE=0
|
|
MAX_ASYNC=4
|
|
MAX_TOKENS=32768
|
|
CHUNK_SIZE=1200
|
|
CHUNK_OVERLAP_SIZE=100
|
|
TOP_K=60
|
|
|
|
### ====================================================================================
|
|
|
|
|
|
# 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_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
|
|
|
|
### Settings for RAG query
|
|
# HISTORY_TURNS=3
|
|
# COSINE_THRESHOLD=0.2
|
|
# TOP_K=60
|
|
# MAX_TOKEN_TEXT_CHUNK=4000
|
|
# MAX_TOKEN_RELATION_DESC=4000
|
|
# MAX_TOKEN_ENTITY_DESC=4000
|
|
|
|
### Entity and ralation summarization configuration
|
|
### Language: English, Chinese, French, German ...
|
|
# SUMMARY_LANGUAGE=English
|
|
### 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 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=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: set as num_ctx option for Ollama by API Server
|
|
# MAX_TOKENS=32768
|
|
### 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
|
|
### Optional for Azure
|
|
# AZURE_OPENAI_API_VERSION=2024-08-01-preview
|
|
# AZURE_OPENAI_DEPLOYMENT=gpt-4o
|
|
|
|
### Embedding Configuration
|
|
### Embedding Binding type: openai, ollama, lollms, azure_openai
|
|
# 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
|
|
### 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
|
|
### Optional for Azure
|
|
# AZURE_EMBEDDING_DEPLOYMENT=text-embedding-3-large
|
|
# AZURE_EMBEDDING_API_VERSION=2023-05-15
|
|
|
|
### Data storage selection
|
|
# LIGHTRAG_KV_STORAGE=PGKVStorage
|
|
# LIGHTRAG_VECTOR_STORAGE=PGVectorStorage
|
|
# LIGHTRAG_DOC_STATUS_STORAGE=PGDocStatusStorage
|
|
# LIGHTRAG_GRAPH_STORAGE=Neo4JStorage
|
|
|
|
### TiDB Configuration (Deprecated)
|
|
# TIDB_HOST=localhost
|
|
# TIDB_PORT=4000
|
|
# TIDB_USER=your_username
|
|
# TIDB_PASSWORD='your_password'
|
|
# TIDB_DATABASE=your_database
|
|
### separating all data from difference Lightrag instances(deprecating)
|
|
# TIDB_WORKSPACE=default
|
|
|
|
### PostgreSQL Configuration
|
|
# POSTGRES_HOST=localhost
|
|
# POSTGRES_PORT=5432
|
|
# POSTGRES_USER=your_username
|
|
# POSTGRES_PASSWORD='your_password'
|
|
# POSTGRES_DATABASE=your_database
|
|
# 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_PORT=8529
|
|
|
|
# AGE Graph Name(apply to PostgreSQL and independent AGM)
|
|
### AGE_GRAPH_NAME is precated
|
|
# AGE_GRAPH_NAME=lightrag
|
|
|
|
### MongoDB Configuration
|
|
# MONGO_URI=mongodb://root:root@localhost:27017/
|
|
# MONGO_DATABASE=LightRAG
|
|
### separating all data from difference Lightrag instances(deprecating)
|
|
# MONGODB_GRAPH=false
|
|
|
|
### Milvus Configuration
|
|
# MILVUS_URI=http://localhost:19530
|
|
# MILVUS_DB_NAME=lightrag
|
|
# MILVUS_USER=root
|
|
# MILVUS_PASSWORD=your_password
|
|
# MILVUS_TOKEN=your_token
|
|
|
|
### Qdrant
|
|
# QDRANT_URL=http://localhost:16333
|
|
# QDRANT_API_KEY=your-api-key
|
|
|
|
### Redis
|
|
# REDIS_URI=redis://localhost:6379
|