CC_flows / CF_PlanCritic.yaml
martinjosifoski's picture
Add an abstract CodeTesting Flow and working CF_CodeTesting Flow.
6fffc74
raw
history blame
2.23 kB
name: "PlanCritic_Flow"
verbose: True
description: "ToDO: add description"
model_name: "gpt-4"
generation_parameters:
n: 1
max_tokens: 3000
temperature: 0.3
model_kwargs:
top_p: 0.2
frequency_penalty: 0
presence_penalty: 0
system_message_prompt_template:
_target_: langchain.PromptTemplate
template: |2-
Your goal is to identify potential issues with a conceptual solution to 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
- a conceptual solution attempt
Crucially, your goal is to consider all aspects of the problem and pinpoint potential issues with the conceptual solution attempt (if any), and not to provide the conceptual solution or the code implementation yourself.
Some aspects to consider: Are there any logical mistakes with the proposed algorithm? Are the corner cases correctly handled?
The user will provide you with a task and an output format that you will strictly follow.
input_variables: []
template_format: jinja2
human_message_prompt_template:
_target_: langchain.PromptTemplate
template: "{{query}}"
input_variables:
- "query"
template_format: jinja2
query_message_prompt_template:
_target_: langchain.PromptTemplate
template: |2-
# Problem statement
{{problem_description}}
# Input description
{{input_description}}
# Output description
{{output_description}}
{{io_examples_and_explanation}}
# Conceptual solution attempt
{{plan}}
Consider the problem statement and the solution attempt. Are there any issues with the proposed conceptual solution or it is correct? Explain your reasoning very concisely.
input_variables:
- "problem_description"
- "input_description"
- "output_description"
- "io_examples_and_explanation"
- "plan"
template_format: jinja2
input_keys:
- "problem_description"
- "input_description"
- "output_description"
- "io_examples_and_explanation"
- "plan"
output_keys:
- "plan_feedback"