version: '0.7'

components:    # define all the building-blocks for Pipeline
  - name: ElasticsearchDocumentStore
    type: ElasticsearchDocumentStore
    params:
      host: localhost
  - name: ESRetriever
    type: ElasticsearchRetriever
    params:
      document_store: ElasticsearchDocumentStore    # params can reference other components defined in the YAML
      top_k: 5
  - name: Reader       # custom-name for the component; helpful for visualization & debugging
    type: FARMReader    # Haystack Class name for the component
    params:
      model_name_or_path: deepset/roberta-base-squad2
  - name: TextFileConverter
    type: TextConverter
  - name: PDFFileConverter
    type: PDFToTextConverter
  - name: Preprocessor
    type: PreProcessor
    params:
      split_by: word
      split_length: 1000
  - name: FileTypeClassifier
    type: FileTypeClassifier

pipelines:
  - name: query    # a sample extractive-qa Pipeline
    type: Query
    nodes:
      - name: ESRetriever
        inputs: [Query]
      - name: Reader
        inputs: [ESRetriever]

  - name: indexing
    type: Indexing
    nodes:
      - name: FileTypeClassifier
        inputs: [File]
      - name: TextFileConverter
        inputs: [FileTypeClassifier.output_1]
      - name: PDFFileConverter
        inputs: [FileTypeClassifier.output_2]
      - name: Preprocessor
        inputs: [PDFFileConverter, TextFileConverter]
      - name: ElasticsearchDocumentStore
        inputs: [Preprocessor]