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

Update Docker deployment comments for LLM and embedding hosts

Browse source
This commit is contained in:
yangdx 2025-10-23 13:53:26 +08:00
parent fdf0fe048b
commit 6a29b5daa0
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
env.example
View file

@ -208,6 +208,7 @@ OPENAI_LLM_MAX_COMPLETION_TOKENS=9000
# OPENAI_LLM_EXTRA_BODY='{"chat_template_kwargs": {"enable_thinking": false}}' # OPENAI_LLM_EXTRA_BODY='{"chat_template_kwargs": {"enable_thinking": false}}'
### use the following command to see all support options for Ollama LLM ### use the following command to see all support options for Ollama LLM
### If LightRAG deployed in Docker uses host.docker.internal instead of localhost in LLM_BINDING_HOST
### lightrag-server --llm-binding ollama --help ### lightrag-server --llm-binding ollama --help
### Ollama Server Specific Parameters ### 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 must be provided, and should at least larger than MAX_TOTAL_TOKENS + 2000
@ -229,7 +230,7 @@ EMBEDDING_BINDING=ollama
EMBEDDING_MODEL=bge-m3:latest EMBEDDING_MODEL=bge-m3:latest
EMBEDDING_DIM=1024 EMBEDDING_DIM=1024
EMBEDDING_BINDING_API_KEY=your_api_key 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 # If LightRAG deployed in Docker uses host.docker.internal instead of localhost
EMBEDDING_BINDING_HOST=http://localhost:11434 EMBEDDING_BINDING_HOST=http://localhost:11434
### OpenAI compatible (VoyageAI embedding openai compatible) ### OpenAI compatible (VoyageAI embedding openai compatible)