CF_Plan.yaml

name: "Plan_Flow"
description: |2- 
  Given a problem description, generate a high-level solution strategy.

# ~~~ Input interface specification ~~~
input_interface_non_initialized:  # Applied when constructing the first user message.
  - "problem_description"
  - "input_description"
  - "output_description"
  - "io_examples_and_explanation"

input_interface_initialized:  # Applied when constructing all subsequent user messages.
  - "query"

# ~~~ Output interface specification ~~~
output_interface:
  - "api_output"

# ~~~ Flow specification ~~~
backend:
  model_name:
    openai: "gpt-4"
    azure: "azure/gpt-4"
  n: 1
  max_tokens: 3000
  temperature: 0.3

  top_p: 0.2
  frequency_penalty: 0
  presence_penalty: 0

system_message_prompt_template:
  _target_: aiflows.prompt_template.JinjaPrompt
  template: |2-
    Your goal is to provide a high-level conceptual solution that, if implemented, will solve a given competitive programming problem.

    The user will specify the problem by providing you with:
      - the problem statement
      - input description
      - output description
      - example test cases
      - (optional) explanation of the test cases

    The proposed algorithm should be computationally efficient, logically correct and handle all corner cases.

    The user will provide you with a task and an output format that you will strictly follow.
  input_variables: []
  

human_message_prompt_template:
  _target_: aiflows.prompt_template.JinjaPrompt
  template: "{{query}}"
  input_variables:
    - "query"
  

init_human_message_prompt_template:
  _target_: aiflows.prompt_template.JinjaPrompt
  template: |2-
    # Problem statement
    {{problem_description}}

    # Input description
    {{input_description}}

    # Output description
    {{output_description}}

    {{io_examples_and_explanation}}


    Return a high-level conceptual solution that would solve the problem. Be very concise, and do not provide code.
    Reply in the following format:
    # Conceptual solution
    {{plan_placeholder}}
  input_variables:
    - "problem_description"
    - "input_description"
    - "output_description"
    - "io_examples_and_explanation"
  partial_variables:
    plan_placeholder: "{{conceptual_solution}}"