Usage

To initialize the Shaper, specify the function to use for modifying your variables. In this example, the node takes the value query, and creates a list that contains this value as many times as it takes to match the length of the documents list. This list is passed down the pipeline under the key questions.

from haystack.nodes import Shaper

mapper = Shaper(
  func="expand_value_to_list"
  value="query",
  target_list=[Documents],
  output=questions
)

components:
        - name: mapper
          type: Shaper
          params:
            func: expand_value_to_list
            inputs:
                value: query
                target_list: documents
            outputs: 
                - questions

Functions

When initializing Shaper, you specify the function you want it to invoke. The supported functions are:

• rename
  Renames values without changing them.
  Example:

  YAML

  - name: shaper
    type: Shaper
    params:
      func: rename
      inputs:
        value: query
      output: [question]
  

• current_datetime
  Outputs the current time and/or date.
  Example:

  YAML

    - name: shaper
      type: Shaper
      params:
        func: current_datetime
        params:
          format: "%H:%M:%S %d/%m/%y"
        outputs:
          - date_time
  

• value_to_list
  Changes a value into a list. The value is repeated in the list to match the length of the list. For example, if you set the list length to five, the value is repeated in this list five times.
  Example:

  YAML

  - name:QuestionsShaper 
      type: Shaper
      params:
        func: value_to_list 
        inputs:
          value: query
        outputs:
          - questions
        params:
          target_list: [5]
  

• join_lists
  Joins multiple lists into a single list.

• join_strings
  Takes a list of strings and changes it into a list that contains a single string. The new list contains all the original strings separated by the specified delimiter.

• join_documents
  Takes a list of documents and changes it into a list containing a single document. The new list contains all the original documents separated by the specified delimiter. You can use the pattern parameter to control how each document is represented.

• join_documents_and_scores
  Takes a list of documents containing scores in their metadata and changes them into a list containing a single document. The resulting document contains both the content of the original

• format_string
  Replaces values in a string.

• format_document
  Changes a document into a string. You can control how the document is represented using the pattern parameter.

• format_answer
  Changes an answer into a single string. You can control how the answer is represented using the pattern parameter.

• join_documents_to_string
  Takes a list of documents and changes them into a single string. The resulting string is the joined results of all original documents separated by the delimiter you specify. You can control how each document is represented using the pattern parameter.

• string_to_answer
  Transforms a string into an answer. You can populate the answer's document IDs by extracting document references from the string.

• parse_references
  Parses an answer string for document references and returns the document ids of the referenced documents.

• answers_to_strings
  Extracts the content field of Answers and returns a list of strings.

• strings_to_documents
  Changes a list of strings into a list of documents.

• documents_to_strings
  Extracts the content field of each document you pass to it and puts it in a list of strings. Each item in this list is the content of the content field of one document.

In a pipeline, after performing a function, Shaper passes the new or modified values further down the pipeline.