# If you need help with the YAML format, have a look at https://docs.cloud.deepset.ai/docs/create-a-pipeline#create-a-pipeline-using-yaml.
# This is a friendly editor that helps you create your pipelines with autosuggestions. To use them, press Control + Space on your keyboard.
# Whenever you need to specify a model, this editor helps you out as well. Just type your Hugging Face organization and a forward slash (/) to see available models.

# This is baseline Question Answering pipeline for English. It has a good, vector-based Retriever and a small, fast Reader
version: '1.14.0'
name: "QA_en"

# This section defines the nodes 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 # The only supported document store in deepset Cloud
  - 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 # Model optimized for semantic search
      model_format: sentence_transformers
      pooling_strategy: cls_token # Specifies how the embeddings from the model should be combined
      top_k: 20 # The number of results to return
  - name: Reader # The component that actually fetches answers from among the 20 documents the Retriever returns
    type: FARMReader # Transformer-based Reader, specializes in extractive QA
    params:
      model_name_or_path: deepset/roberta-base-squad2 # An optimized variant of BERT, a strong all-round model
      context_window_size: 700 # The size of the window around the answer span
  - name: TextFileConverter # Converts files to documents
    type: TextConverter
  - name: Preprocessor # Splits documents into smaller ones, and cleans them up
    type: PreProcessor
    params:
      split_by: word # The unit by which you want to split your documents
      split_length: 250 # The maximum number of words in a document
      split_overlap: 30 # 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

pipelines: # Here you define the pipelines. For each component, specify its input.
  - name: query 
    nodes:
      - name: Retriever
        inputs: [Query]
      - name: Reader
        inputs: [Retriever]
  - name: indexing
    nodes:
      - name: TextFileConverter
        inputs: [File]
      - name: Preprocessor
        inputs: [TextFileConverter]
      - name: Retriever # We use the Retriever here to create embeddings
        inputs: [Preprocessor]
      - name: DocumentStore
        inputs: [Retriever]