version: ignore

components:
  - name: DocumentStore
    type: ElasticsearchDocumentStore
    params:
      host: localhost
  - name: Retriever # Selects the most relevant documents from the document store and passes them on to the Reader
    type: EmbeddingRetriever # Uses a Transformer model to encode the document and the query
    params:
      document_store: DocumentStore
      embedding_model: sentence-transformers/multi-qa-mpnet-base-dot-v1 # multi-qa-MiniLM-L6-dot-v1
      embed_meta_fields:
        - filename
      top_k: 10 # The number of results to return
  - name: BM25
    type: BM25Retriever
    params:
      document_store: DocumentStore
      top_k: 10
      
  - name: Joiner
    type: JoinDocuments
    params:
      join_mode: reciprocal_rank_fusion
  - name: Reader # The component that actually fetches answers from among the 20 documents returned by retriever 
    type: FARMReader # Transformer-based reader, specializes in extractive QA
    params:
      model_name_or_path: dmis-lab/biobert-large-cased-v1.1-squad # dmis-lab/biobert-base-cased-v1.1-squad
      context_window_size: 700 # The size of the window around the answer span
  - name: FileTypeClassifier # Routes files based on their extension to appropriate converters, by default txt, pdf, md, docx, html
    type: FileTypeClassifier
  - name: TextConverter # Converts files into documents
    type: TextConverter
  - name: PDFConverter # Converts PDFs into documents
    type: PDFToTextConverter
  - name: Preprocessor # Splits documents into smaller ones and cleans them up
    type: PreProcessor
    params:
      # With a vector-based retriever, it's good to split your documents into smaller ones
      split_by: word # The unit by which you want to split the documents
      split_length: 250 # The max number of words in a document
      split_overlap: 20 # Enables the sliding window approach
      split_respect_sentence_boundary: True # Retains complete sentences in split documents
      language: en # Used by NLTK to best detect the sentence boundaries for that language


# Here you define how the nodes are organized in the pipelines
# For each node, specify its input
pipelines:
  - name: query
    nodes:
      - name: Retriever
        inputs: [Query]
      - name: BM25
        inputs: [Query]
      - name: Joiner
        inputs: [Retriever, BM25]
      - name: Reader
        inputs: [Joiner]
  - name: indexing
    nodes:
    # Depending on the file type, we use a Text or PDF converter
      - name: FileTypeClassifier
        inputs: [File]
      - name: TextConverter
        inputs: [FileTypeClassifier.output_1] # Ensures this converter receives TXT files
      - name: PDFConverter
        inputs: [FileTypeClassifier.output_2] # Ensures this converter receives PDFs
      - name: Preprocessor
        inputs: [TextConverter, PDFConverter]
      - name: Retriever
        inputs: [Preprocessor]
      - name: DocumentStore
        inputs: [Retriever]