config/models.yaml

llm:
  model_name: "openai/gpt-oss-20b"
  temperature: 0.7
  max_tokens: 1024
  streaming: true
  
embedding:
  model_name: "BAAI/bge-small-en-v1.5"
  max_length: 512
  
reranker:
  enabled: true
  model: "ms-marco-MiniLM-L-12-v2"
  top_n: 3