name: "Code_Flow" description: |2- Given a problem description, generate code directly. # ~~~ Input interface specification ~~~ input_interface_non_initialized: # Applied when constructing the first user message. - "problem_description" - "io_description" - "constraints" - "python_stub" input_interface_initialized: # Applied when constructing all subsequent user messages. - "query" # ~~~ Output interface specification ~~~ output_interface: - "api_output" # ~~~ Flow specification ~~~ backend: __target__: flows.backends.llm_lite.LiteLLMBackend api_infos: ${local.api_information} 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_: flows.prompt_template.JinjaPrompt template: |2- Your goal is to provide executable Python code that solves a coding interview problem. The code should correctly handle all corner cases in order to pass the hidden test cases, which are used to evaluate the correctness of the solution. The user will specify the problem by providing you with: - the problem statement - example test cases - the constraints of the problem The user will provide you with a task and an output format that you will strictly follow. input_variables: [] human_message_prompt_template: _target_: flows.prompt_template.JinjaPrompt template: "{{query}}" input_variables: - "query" init_human_message_prompt_template: _target_: flows.prompt_template.JinjaPrompt template: |2- # Problem statement {{problem_description}} {{io_description}} # Constraints {{constraints}} Return Python code that solves the problem. The code should extend the following stub: ```python {{python_stub}} ``` without changing the method signatures. Reply in the following format: ```python {{code_placeholder}} ``` input_variables: - "problem_description" - "io_description" - "constraints" - "python_stub" partial_variables: code_placeholder: "{{python_code}}"