docker-compose.yml

services:
  qdrant:
    image: qdrant/qdrant
    ports: 
      - 6333:6333
    volumes: 
      - ./qdrant_storage:/qdrant/storage:z
  
  # llamacpp:
  #   container_name: llama-cpp
  #   build:
  #     context: ./llama-cpp-python/docker/cuda_simple
  #     dockerfile: Dockerfile
  #   ports:
  #     - 8888:8000
  #   volumes:
  #     - ./models:/models
  #   environment:
  #     - MODEL=/models/pygmalion-2-7b.Q4_K_M.gguf
  #     - N_GPU_LAYERS=40
  #     - N_CTX=4096
  #     - TZ=Etc/UTC
  #     - LLAMA_CUBLAS=1
  #   restart: no
  #   command: python3 -m llama_cpp.server --last_n_tokens_size 1
  #   # depends_on:
  #   #   - test
  #   deploy:
  #     resources:
  #       reservations:
  #         devices:
  #           - driver: nvidia
  #             count: 1
  #             capabilities: [gpu]

  # ragbot:
  #   build:
  #     context: .
  #     dockerfile: Dockerfile
  #   ports:
  #     - 8000:8000
  #   volumes:
  #     # - ./model:/models
  #   environment:
  #     - MARKDOWN_PATH=/docs
  #     - MODEL_PATH=/models/tinyllama-1.1b-chat-v0.3.Q4_K_M.gguf
  #     - EMBED_MODEL_NAME=sentence-transformers/all-mpnet-base-v2
  #     - HOST=0.0.0.0
  #     - PORT=8000
  #   depends_on: 
  #     - qdrant
  #     - llamacpp