|
|
|
|
|
|
|
|
ANSWER_GENERATION_PROMPT = """ |
|
|
Think step by step and solve the problem. |
|
|
1. In the "thought" field, explain your thinking process in detail. |
|
|
2. In the "answer" field, provide the final answer concisely and clearly. The answer should be a direct response to the question, without including explanations or reasoning. |
|
|
You should format your output in xml format. For example, ouptut the thoughts in <thought>xxx</thought> format. |
|
|
|
|
|
Your task: {input} |
|
|
""" |
|
|
|
|
|
QA_SC_ENSEMBLE_PROMPT = """ |
|
|
Several answers have been generated to a same question. They are as follows: |
|
|
{solutions} |
|
|
|
|
|
Identify the concise answer that appears most frequently across them. This consistency in answers is crucial for determining the most reliable solution. |
|
|
|
|
|
In the "thought" field, provide a detailed explanation of your thought process. In the "solution_letter" field, output only the single letter ID (A, B, C, etc.) corresponding to the most consistent solution. Do not include any additional text or explanation in the "solution_letter" field. |
|
|
|
|
|
You should format your output in xml format. For example, ouptut the thoughts in <thought>xxx</thought> format. |
|
|
""" |
|
|
|
|
|
REFLECTION_ON_PUBLIC_TEST_PROMPT = """ |
|
|
Given a code problem and a python code solution which failed to pass test or execute, you need to analyze the reason for the failure and propose a better code solution.: |
|
|
### problem |
|
|
{problem} |
|
|
|
|
|
### Code Solution |
|
|
{solution} |
|
|
|
|
|
### Execution Result |
|
|
{exec_pass} |
|
|
|
|
|
#### Failed Test Case |
|
|
{test_fail} |
|
|
|
|
|
Please provide a reflection on the failed test cases and code solution, followed by a better code solution without any additional text or test cases. |
|
|
|
|
|
Your response should be formatted as follows: |
|
|
```json |
|
|
{{ |
|
|
"reflection_and_solution": "Your improved code solution here" |
|
|
}} |
|
|
``` |
|
|
|
|
|
Only include the improved code in the reflection_and_solution field, without any additional explanations or comments outside the code. |
|
|
""" |
|
|
|
|
|
SC_ENSEMBLE_PROMPT = """ |
|
|
Given the question described as follows: {problem} |
|
|
Several solutions have been generated to address the given question. They are as follows: |
|
|
{solutions} |
|
|
|
|
|
Carefully evaluate these solutions and identify the answer that appears most frequently across them. This consistency in answers is crucial for determining the most reliable solution. |
|
|
|
|
|
In the "thought" field, provide a detailed explanation of your thought process. In the "solution_letter" field, output only the single letter ID (A, B, C, etc.) corresponding to the most consistent solution. Do not include any additional text or explanation in the "solution_letter" field. |
|
|
|
|
|
You should format your output in xml format. For example, ouptut the thoughts in <thought>xxx</thought> format. |
|
|
""" |
|
|
|
|
|
PYTHON_CODE_VERIFIER_PROMPT = """ |
|
|
You are a professional Python programmer. Your task is to write complete, self-contained code based on a given mathematical problem and output the answer. The code should include all necessary imports and dependencies, and be ready to run without additional setup or environment configuration. |
|
|
|
|
|
Problem description: {problem} |
|
|
Other analysis: {analysis} |
|
|
{feedback} |
|
|
|
|
|
Your code should: |
|
|
1. Implement the calculation steps described in the problem. |
|
|
2. Define a function named `solve` that performs the calculation and returns the result. The `solve` function should not require any input parameters; instead, it should obtain all necessary inputs from within the function or from globally defined variables. |
|
|
3. `solve` function return the final calculation result. |
|
|
|
|
|
Please ensure your code is efficient, well-commented, and follows Python best practices. The output should be limited to basic data types such as strings, integers, and floats. It is prohibited to transmit images or other file formats. The code output is intended for a text-based language model. |
|
|
""" |
