app.yaml

$sources:
  - !pw.io.fs.read
    path: files-for-indexing
    format: binary
    with_metadata: true

  # - !pw.xpacks.connectors.sharepoint.read 
  #   url: $SHAREPOINT_URL
  #   tenant: $SHAREPOINT_TENANT
  #   client_id: $SHAREPOINT_CLIENT_ID
  #   cert_path: sharepointcert.pem
  #   thumbprint: $SHAREPOINT_THUMBPRINT
  #   root_path: $SHAREPOINT_ROOT
  #   with_metadata: true
  #   refresh_interval: 30

  # - !pw.io.gdrive.read
  #   object_id: $DRIVE_ID
  #   service_user_credentials_file: gdrive_indexer.json
  #   file_name_pattern:
  #     - "*.pdf"
  #     - "*.pptx"
  #   object_size_limit: null
  #   with_metadata: true
  #   refresh_interval: 30

$embedding_model: "mixedbread-ai/mxbai-embed-large-v1"

$embedder: !pw.xpacks.llm.embedders.SentenceTransformerEmbedder
  model: $embedding_model
  call_kwargs: 
    show_progress_bar: False

$splitter: !pw.xpacks.llm.splitters.TokenCountSplitter
  max_tokens: 400

$parser: !pw.xpacks.llm.parsers.UnstructuredParser
  cache_strategy: !pw.udfs.DefaultCache

$retriever_factory: !pw.stdlib.indexing.BruteForceKnnFactory
  reserved_space: 1000
  embedder: $embedder
  metric: !pw.stdlib.indexing.BruteForceKnnMetricKind.COS
  dimensions: 1536

document_store: !pw.xpacks.llm.document_store.DocumentStore
  docs: $sources
  parser: $parser
  splitter: $splitter
  retriever_factory: $retriever_factory

# Change host and port by uncommenting these lines
# host: "0.0.0.0"
# port: 8000

# Cache configuration
# with_cache: true

# If `terminate_on_error` is true then the program will terminate whenever any error is encountered.
# Defaults to false, uncomment the following line if you want to set it to true
# terminate_on_error: true