khoj/config/khoj_docker.yml

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/org/*.org"]
    compressed-jsonl: "/data/embeddings/notes.jsonl.gz"
    embeddings-file: "/data/embeddings/note_embeddings.pt"
    index_heading_entries: false

  markdown:
    input-files: null
    input-filter: ["/data/markdown/*.md"]
    compressed-jsonl: "/data/embeddings/markdown.jsonl.gz"
    embeddings-file: "/data/embeddings/markdown_embeddings.pt"

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

  image:
    input-directories: ["/data/images/"]
    embeddings-file: "/data/embeddings/image_embeddings.pt"
    batch-size: 50
    use-xmp-metadata: false

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

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

  asymmetric:
    encoder: "sentence-transformers/multi-qa-MiniLM-L6-cos-v1"
    cross-encoder: "cross-encoder/ms-marco-MiniLM-L-6-v2"
    model_directory: "/data/models/asymmetric"

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

processor:
  #conversation:
  #  openai-api-key: null
  #  model: "text-davinci-003"
  #  conversation-logfile: "/data/embeddings/conversation_logs.json"