CC_flows / LC_Code.yaml
yeeef's picture
propagate changes
dca49e6
raw
history blame
2.11 kB
name: "Code_Flow"
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 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: []
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}}
{{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}}"
template_format: jinja2
input_data_transformations: []
input_keys:
- "problem_description"
- "io_description"
- "constraints"
- "python_stub"
output_data_transformations:
- _target_: flows.data_transformations.RegexFirstOccurrenceExtractor
regex: '(?<=```python)([\s\S]*?)(?=```)'
regex_fallback: '(?<=```)([\s\S]*?)(?=```)'
input_key: "api_output"
output_key: "code"
strip: True
assert_unique: True
output_keys:
- "code"