Summarization Pipelines

version: '1.21.0'
name: 'summarization'

# This section defines nodes that you want to use in your pipelines. Each node must have a name and a type. You can also set the node's parameters here.
# The name is up to you, you can give your component a friendly name. You then use components' names when specifying their order in the pipeline.
# Type is the class name of the component. 
components:
  - name: DocumentStore
    type: DeepsetCloudDocumentStore
  - name: BM25Retriever # The keyword-based retriever
    type: BM25Retriever
    params:
      document_store: DocumentStore
      top_k: 10 # The number of results to return
  - name: EmbeddingRetriever # Selects the most relevant documents from the document store
    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 # Model optimized for semantic search. It has been trained on 215M (question, answer) pairs from diverse sources.
      model_format: sentence_transformers
      top_k: 10 # The number of results to return
  - name: JoinResults # Joins the results from both retrievers
    type: JoinDocuments
    params:
      join_mode: concatenate # Combines documents from multiple retrievers
  - name: Reranker # Uses a cross-encoder model to rerank the documents returned by the two retrievers
    type: SentenceTransformersRanker
    params:
      model_name_or_path: cross-encoder/ms-marco-MiniLM-L-6-v2 # Fast model optimized for reranking
      top_k: 1 # The number of results to return
      batch_size: 20  # Try to keep this number equal or larger to the sum of the top_k of the two retrievers so all docs are processed at once
  - name: PromptNode
    type: PromptNode
    params:
      default_prompt_template: deepset/summarization
      max_length: 400 # The maximum number of tokens the generated answer can have
      model_kwargs: # Specifies additional model settings
        temperature: 0 # Lower temperature works best for fact-based qa
      model_name_or_path: gpt-3.5-turbo
      top_k: 1
  - 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
      language: en
      split_respect_sentence_boundary: True # Retains complete sentences in split documents
# Here you define how the nodes are organized in the pipelines
# For each node, specify its input
pipelines:
  - name: query
    nodes:
      - name: BM25Retriever
        inputs: [Query]
      - name: EmbeddingRetriever
        inputs: [Query]
      - name: JoinResults
        inputs: [BM25Retriever, EmbeddingRetriever]
      - name: Reranker
        inputs: [JoinResults]
      - name: PromptNode
        inputs: [Reranker]
  - 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 that this converter receives txt files
      - name: PDFConverter
        inputs: [FileTypeClassifier.output_2] # Ensures that this converter receives PDFs
      - name: Preprocessor
        inputs: [TextConverter, PDFConverter]
      - name: EmbeddingRetriever
        inputs: [Preprocessor]
      - name: DocumentStore
        inputs: [EmbeddingRetriever]