VisRAG-Ret-Test-InfoVQA

## Dataset Description
This is a VQA dataset based on Infographics from InfoVQA dataset from [InfoVQA](https://www.docvqa.org/datasets/infographicvqa).

### Load the dataset
```python
from datasets import load_dataset
import csv

def load_beir_qrels(qrels_file):
qrels = {}
with open(qrels_file) as f:
tsvreader = csv.DictReader(f, delimiter="\t")
for row in tsvreader:
qid = row["query-id"]
pid = row["corpus-id"]
rel = int(row["score"])
if qid in qrels:
qrels[qid][pid] = rel
else:
qrels[qid] = {pid: rel}
return qrels

corpus_ds = load_dataset("openbmb/VisRAG-Ret-Test-InfoVQA", name="corpus", split="train")
queries_ds = load_dataset("openbmb/VisRAG-Ret-Test-InfoVQA", name="queries", split="train")

qrels_path = "xxxx" # path to qrels file which can be found under qrels folder in the repo.
qrels = load_beir_qrels(qrels_path)
```

## 数据集说明
本数据集为一款基于InfoVQA数据集中信息图表（Infographics）构建的视觉问答（Visual Question Answering, VQA）数据集，其数据源取自[InfoVQA](https://www.docvqa.org/datasets/infographicvqa)。

### 数据集加载方式
python
from datasets import load_dataset
import csv

def load_beir_qrels(qrels_file):
qrels = {}
with open(qrels_file) as f:
tsvreader = csv.DictReader(f, delimiter=" ")
for row in tsvreader:
qid = row["query-id"]
pid = row["corpus-id"]
rel = int(row["score"])
if qid in qrels:
qrels[qid][pid] = rel
else:
qrels[qid] = {pid: rel}
return qrels

corpus_ds = load_dataset("openbmb/VisRAG-Ret-Test-InfoVQA", name="corpus", split="train")
queries_ds = load_dataset("openbmb/VisRAG-Ret-Test-InfoVQA", name="queries", split="train")

qrels_path = "xxxx" # 指向qrels文件的路径，该文件可在本仓库的qrels文件夹中获取
qrels = load_beir_qrels(qrels_path)

搜集汇总

背景与挑战

背景概述

VisRAG-Ret-Test-InfoVQA是一个基于InfoVQA数据集中信息图表的视觉问答（VQA）数据集，主要用于检索测试。它包含语料库和查询两个部分，遵循Apache License 2.0开源协议。