from dataclasses import dataclass
from enum import Enum

@dataclass
class Task:
    benchmark: str
    metric: str
    col_name: str


# Select your tasks here
# ---------------------------------------------------
class Tasks(Enum):
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard 
    task0 = Task("anli_r1", "acc", "ANLI")
    task1 = Task("logiqa", "acc_norm", "LogiQA")

NUM_FEWSHOT = 0 # Change with your few shot
# ---------------------------------------------------



# Your leaderboard name
TITLE = """<h1 align="center" id="space-title">TAG leaderboard</h1>"""

# What does your leaderboard evaluate?
INTRODUCTION_TEXT = """
Intro text
"""

# Which evaluations are you running? how can people reproduce what you have?
LLM_BENCHMARKS_TEXT = f"""
## What does the TAG leaderboard evaluate?
In this leaderboard, you'll find execution accuracy comparisons of table question answering approaches on [TAG-Bench](https://github.com/TAG-Research/TAG-Bench/tree/main). TAG-Bench contains complex queries requiring world knowledge or semantic reasoning that goes beyond the information explicitly available in the database.

## How is accuracy measured?
Execution accuracy is measured as the number of exact matches to our annotated ground truth answers which are hand-labeled by experts.

## Citation
```
@misc{{biswal2024text2sqlenoughunifyingai,
      title={{Text2SQL is Not Enough: Unifying AI and Databases with TAG}}, 
      author={{Asim Biswal and Liana Patel and Siddarth Jha and Amog Kamsetty and Shu Liu and Joseph E. Gonzalez and Carlos Guestrin and Matei Zaharia}},
      year={2024},
      eprint={2408.14717},
      archivePrefix={{arXiv}},
      primaryClass={{cs.DB}},
      url={{https://arxiv.org/abs/2408.14717}}, 
    }}
```
"""

EVALUATION_QUEUE_TEXT = """
## Steps before submission

### 1) 
"""

CITATION_BUTTON_LABEL = "Copy the following snippet to cite these results"
CITATION_BUTTON_TEXT = r"""
"""