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/**/*.markdown"]
    compressed-jsonl: "/data/embeddings/markdown.jsonl.gz"
    embeddings-file: "/data/embeddings/markdown_embeddings.pt"

  pdf:
    input-files: null
    input-filter: ["/data/pdf/**/*.pdf"]
    compressed-jsonl: "/data/embeddings/pdf.jsonl.gz"
    embeddings-file: "/data/embeddings/pdf_embeddings.pt"

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

  notion: null
  github: null
  plugins: null

search-type:
  symmetric: null
  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:
    conversation-logfile: "/data/embeddings/conversation_logs.json"
    enable-offline-chat: false
    openai:
      api-key: null
      chat-model: "chat-gpt-3.5"

app:
  should_log_telemetry: true