env.example
Set these on your host before deploying. Each platform has an “Environment Variables” section in the deploy flow. (showing first 20, more exist in env.example)
HOST
Server Configuration
PORT
WEBUI_TITLE
WEBUI_DESCRIPTION
OLLAMA_EMULATING_MODEL_TAG
Ollama Emulating Model and Tag OLLAMA_EMULATING_MODEL_NAME=lightrag
ENABLE_LLM_CACHE
Query Configuration How to control the context length sent to LLM: MAX_ENTITY_TOKENS + MAX_RELATION_TOKENS < MAX_TOTAL_TOKENS Chunk_Tokens…
RERANK_BINDING
Reranking configuration RERANK_BINDING type: null, cohere, jina, aliyun For rerank model deployed by vLLM use cohere binding
ENABLE_LLM_CACHE_FOR_EXTRACT
Document processing configuration
SUMMARY_LANGUAGE
Document processing output language: English, Chinese, French, German ...
MAX_ASYNC
Concurrency Configuration Max concurrency requests of LLM (for both query and document processing)
MAX_PARALLEL_INSERT
Number of parallel processing documents(between 2~10, MAX_ASYNC/3 is recommended)
LLM_BINDING
LLM_MODEL
LLM_BINDING_HOST
LLM_BINDING_API_KEY
secret
OPENAI_LLM_MAX_COMPLETION_TOKENS
secret
OpenAI Compatible API Specific Parameters Increased temperature values may mitigate infinite inference loops in certain LLM, such as…
OLLAMA_LLM_NUM_CTX
use the following command to see all support options for Ollama LLM lightrag-server --llm-binding ollama --help Ollama Server Specific…
EMBEDDING_BINDING
Embedding Configuration (Should not be changed after the first file processed) EMBEDDING_BINDING: ollama, openai, azure_openai, jina,…
EMBEDDING_MODEL
EMBEDDING_DIM
brew install flyctl && fly launch --from https://github.com/anush008/lightragcurl -L https://fly.io/install.sh | sh && fly launch --from https://github.com/anush008/lightragiwr https://fly.io/install.ps1 -useb | iex; fly launch --from https://github.com/anush008/lightrag