Files
Auto-GPT/data/README.md
2023-06-19 12:39:34 +00:00

37 lines
1.1 KiB
Markdown

# Challenges Data Schema of Benchmark
## General challenges
Input:
- **category** (str): information-retrieval
- **difficulty_level**(str): the difficulty of this query. choices from ["easy", "medium", "hard"]
## Information-retrieval challenges
Input:
- **category** (str): information-retrieval
- **query** (str): the question need to be solve.
- **ground** (dict): The ground truth.
- **answer** (str): The raw text of ground truth answer
- **should_contain** (list): the exact strings that is required in the final answer
- **should_not_contain** (list): the exact strings that should not be in the final answer
- **difficulty_level**(str): the difficulty of this query. choices from ["easy", "medium", "hard"]
Example:
```python
{
"category": "information-retrieval",
"query": "what is the capital of America",
"ground": {
"answer": "Washington",
"should_contain": ["Washington"],
"should_not_contain": ["New York", "Los Angeles", "San Francisco"]
},
"difficulty_level": "easy"
}
```
Output:
- **score** (float): scores range from [0, 1]