tomatocream
4495a3cc62
- Add AGENTS.md with repo guidelines - Add lightrag-mcp: FastMCP server exposing insert_documents() + query_documents() to LLM agents via stdio transport, talks to LightRAG REST API - Add scripts/patch-vllm-cpu.py for CPU inference patching - Add .env.vllm for vLLM configuration - Update flake.nix with expanded dev shell - Update .env.lightrag - Remove CLAUDE.md (replaced by AGENTS.md)
24 lines
519 B
Bash
24 lines
519 B
Bash
LLM_BINDING=openai
|
|
LLM_MODEL=minimax/minimax-m2.7
|
|
LLM_BINDING_HOST=https://openrouter.ai/api/v1
|
|
LLM_BINDING_API_KEY=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
|
|
|
|
# Embeddings via Ollama (port 11434)
|
|
EMBEDDING_BINDING=ollama
|
|
EMBEDDING_MODEL=qwen3-embedding:4b
|
|
EMBEDDING_BINDING_HOST=http://localhost:11434
|
|
EMBEDDING_API_KEY=
|
|
EMBEDDING_DIM=2560
|
|
|
|
# Storage (local files)
|
|
RAG_DIR=./rag_storage
|
|
|
|
# Timeouts (in seconds)
|
|
EMBEDDING_TIMEOUT=60
|
|
TIMEOUT=60
|
|
|
|
# Server
|
|
HOST=0.0.0.0
|
|
PORT=9621
|
|
WORKERS=1
|