dora/node-hub/dora-llama-cpp-python/test.yml

nodes:
  - id: dora-microphone
    build: pip install -e ../../node-hub/dora-microphone
    path: dora-microphone
    inputs:
      tick: dora/timer/millis/2000
    outputs:
      - audio

  - id: dora-vad
    build: pip install -e ../../node-hub/dora-vad
    path: dora-vad
    inputs:
      audio: dora-microphone/audio
    outputs:
      - audio
      - timestamp_start

  - id: dora-distil-whisper
    build: pip install -e ../../node-hub/dora-distil-whisper
    path: dora-distil-whisper
    inputs:
      input: dora-vad/audio
    outputs:
      - text
    env:
      TARGET_LANGUAGE: english

  - id: dora-llama-cpp-python
    build: pip install -e ../../node-hub/dora-llama-cpp-python
    path: dora-llama-cpp-python
    inputs:
      text: dora-distil-whisper/text
    outputs:
      - text
    env:
      MODEL_NAME_OR_PATH: TheBloke/Llama-2-7B-Chat-GGUF   # Llama 2.7B model pull from Hugging Face
      MODEL_FILE_PATTERN: "*Q4_K_M.gguf"
      SYSTEM_PROMPT: "You're a very succinct AI assistant with short answers."
      ACTIVATION_WORDS: "what how who where you"
      MAX_TOKENS: "512"
      N_GPU_LAYERS: "35"     # Enable GPU acceleration
      N_THREADS: "4"         # CPU threads
      CONTEXT_SIZE: "4096"   # Maximum context window

  - id: plot
    build: pip install -e ../../node-hub/dora-rerun
    path: dora-rerun
    inputs:
      text_llama: dora-llama-cpp-python/text  
      text_whisper: dora-distil-whisper/text

  - id: dora-kokoro-tts
    build: pip install -e ../../node-hub/dora-kokoro-tts
    path: dora-kokoro-tts
    inputs:
      text: dora-llama-cpp-python/text  
    outputs:
      - audio
    env:
      ACTIVATION_WORDS: you

  - id: dora-pyaudio
    build: pip install -e ../../node-hub/dora-pyaudio
    path: dora-pyaudio
    inputs:
      audio: dora-kokoro-tts/audio
      timestamp_start: dora-vad/timestamp_start