content-type:
  # The /data/folder/ prefix to the folders is here because this is 
  # the directory to which the local files are copied in the docker-compose.
  # If changing, the docker-compose volumes should also be changed to match.
  org:
    input-files: null
    input-filter: "/data/notes/*.org"
    compressed-jsonl: "/data/generated/.notes.json.gz"
    embeddings-file: "/data/generated/.note_embeddings.pt"

  ledger:
    input-files: null
    input-filter: /data/ledger/*.beancount
    compressed-jsonl: /data/generated/.transactions.jsonl.gz
    embeddings-file: /data/generated/.transaction_embeddings.pt

  image:
    input-directory: "/data/images/"
    embeddings-file: "/data/generated/.image_embeddings.pt"
    batch-size: 50
    use-xmp-metadata: true

  music:
    input-files: null
    input-filter: "/data/music/*.org"
    compressed-jsonl: "/data/generated/.songs.jsonl.gz"
    embeddings-file: "/data/generated/.song_embeddings.pt"

search-type:
  symmetric:
    encoder: "sentence-transformers/paraphrase-MiniLM-L6-v2"
    cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
    model_directory: "/data/models/.symmetric"

  asymmetric:
    encoder: "sentence-transformers/msmarco-MiniLM-L-6-v3"
    cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
    model_directory: "/data/models/.asymmetric"

  image:
    encoder: "clip-ViT-B-32"
    model_directory: "/data/models/.image_encoder"

processor:
  conversation:
    openai-api-key: null
    conversation-logfile: "/data/conversation/.conversation_logs.json"