gmakstutis/LightRAG
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update env.example

Browse source 
• Comment out Ollama config
• Set OpenAI as active default
• Add EMBEDDING_TOKEN_LIMIT option
• Add Gemini embedding configuration
This commit is contained in:
yangdx 2025-11-15 01:25:56 +08:00
parent ec05d89c2a
commit acae404f04
1 changed files with 25 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

38
env.example
View file

@ -255,21 +255,23 @@ OLLAMA_LLM_NUM_CTX=32768
### For OpenAI: Set to 'true' to enable dynamic dimension adjustment
### For OpenAI: Set to 'false' (default) to disable sending dimension parameter
### Note: Automatically ignored for backends that don't support dimension parameter (e.g., Ollama)
# EMBEDDING_SEND_DIM=false
EMBEDDING_BINDING=ollama
EMBEDDING_MODEL=bge-m3:latest
EMBEDDING_DIM=1024
EMBEDDING_BINDING_API_KEY=your_api_key
# If LightRAG deployed in Docker uses 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/v1
# Ollama embedding
# EMBEDDING_BINDING=ollama
# EMBEDDING_MODEL=bge-m3:latest
# EMBEDDING_DIM=1024
# EMBEDDING_BINDING_API_KEY=your_api_key
### If LightRAG deployed in Docker uses host.docker.internal instead of localhost
# EMBEDDING_BINDING_HOST=http://localhost:11434
### OpenAI compatible embedding
EMBEDDING_BINDING=openai
EMBEDDING_MODEL=text-embedding-3-large
EMBEDDING_DIM=3072
EMBEDDING_SEND_DIM=false
EMBEDDING_TOKEN_LIMIT=8192
EMBEDDING_BINDING_HOST=https://api.openai.com/v1
EMBEDDING_BINDING_API_KEY=your_api_key
### Optional for Azure
# AZURE_EMBEDDING_DEPLOYMENT=text-embedding-3-large
@ -277,6 +279,16 @@ EMBEDDING_BINDING_HOST=http://localhost:11434
# AZURE_EMBEDDING_ENDPOINT=your_endpoint
# AZURE_EMBEDDING_API_KEY=your_api_key
### Gemini embedding
# EMBEDDING_BINDING=gemini
# EMBEDDING_MODEL=gemini-embedding-001
# EMBEDDING_DIM=1536
# EMBEDDING_TOKEN_LIMIT=2048
# EMBEDDING_BINDING_HOST=https://generativelanguage.googleapis.com
# EMBEDDING_BINDING_API_KEY=your_api_key
### Gemini embedding requires sending dimension to server
# EMBEDDING_SEND_DIM=true
### Jina AI Embedding
# EMBEDDING_BINDING=jina
# EMBEDDING_BINDING_HOST=https://api.jina.ai/v1/embeddings