# LLM via Ollama
LLM_BINDING=ollama
LLM_MODEL=qwen3:0.6b
LLM_BINDING_HOST=http://localhost:11434

# Embeddings via Ollama
EMBEDDING_BINDING=ollama
EMBEDDING_MODEL=qwen3-embedding:0.6b
EMBEDDING_BINDING_HOST=http://localhost:11434
EMBEDDING_DIM=1024

# Storage (local files)
RAG_DIR=./rag_storage

# Timeouts (in seconds) — increase for large local models
EMBEDDING_TIMEOUT=60
TIMEOUT=60

# Server
HOST=0.0.0.0
PORT=9621
WORKERS=1