server:
  env_name: ${APP_ENV:tensorrt}

llm:
  mode: tensorrt
  max_new_tokens: 512
  context_window: 3900

tensorrt:
  model_path: models/tensorrt
  engine_name: llama_float16_tp1_rank0.engine
  prompt_style: "llama2"

embedding:
  mode: huggingface

huggingface:
  embedding_hf_model_name: BAAI/bge-small-en-v1.5

vectorstore:
  database: qdrant

qdrant:
  path: local_data/private_gpt/qdrant