inputs:
  chat_history:
    type: list
    default:
    - inputs:
        question: what is BERT?
      outputs:
        answer: BERT (Bidirectional Encoder Representations from Transformers) is a
          language representation model that pre-trains deep bidirectional
          representations from unlabeled text by jointly conditioning on both
          left and right context in all layers. Unlike other language
          representation models, BERT can be fine-tuned with just one additional
          output layer to create state-of-the-art models for a wide range of
          tasks such as question answering and language inference, without
          substantial task-specific architecture modifications. BERT is
          effective for both fine-tuning and feature-based approaches. It
          obtains new state-of-the-art results on eleven natural language
          processing tasks, including pushing the GLUE score to 80.5% (7.7%
          point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute
          improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point
          absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point
          absolute improvement).
  pdf_url:
    type: string
    default: https://arxiv.org/pdf/1810.04805.pdf
  question:
    type: string
    is_chat_input: true
    default: what NLP tasks does it perform well?
outputs:
  answer:
    type: string
    is_chat_output: true
    reference: ${chat_with_pdf_tool.output.answer}
  context:
    type: string
    reference: ${chat_with_pdf_tool.output.context}
nodes:
- name: setup_env
  type: python
  source:
    type: code
    path: setup_env.py
  inputs:
    conn: my_custom_connection
- name: chat_with_pdf_tool
  type: python
  source:
    type: code
    path: chat_with_pdf_tool.py
  inputs:
    history: ${inputs.chat_history}
    pdf_url: ${inputs.pdf_url}
    question: ${inputs.question}
    ready: ${setup_env.output}