> ## Documentation Index
> Fetch the complete documentation index at: https://docs.multivon.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Loading Datasets

> Load eval cases from JSONL and CSV files.

## JSONL

Each line is a JSON object representing one `EvalCase`.

```python theme={null}
from multivon_eval import load_jsonl

cases = load_jsonl("cases.jsonl")
```

**cases.jsonl**

```json theme={null}
{"input": "What is the capital of France?", "expected_output": "Paris", "tags": ["factual"]}
{"input": "Summarize this article.", "context": "The article discusses...", "tags": ["summarization"]}
{"input": "Is this review positive?", "expected_output": "yes", "metadata": {"source": "amazon"}}
```

Supported fields:

| Field             | Type          | Description                                    |
| ----------------- | ------------- | ---------------------------------------------- |
| `input`           | string        | Required. The prompt sent to the model         |
| `expected_output` | string        | For ExactMatch, Contains, BLEU, ROUGE          |
| `context`         | string        | For Faithfulness, Hallucination, Summarization |
| `tags`            | list\[string] | For filtering and grouping in reports          |
| `metadata`        | object        | Arbitrary key-value data attached to results   |

## CSV

```python theme={null}
from multivon_eval import load_csv

cases = load_csv("cases.csv")
```

**cases.csv**

```
input,expected_output,context,tags
What is 2+2?,4,,math
Summarize this.,,Long text here...,summarization
Is Paris in France?,yes,,factual geography
```

## Auto-detect format

```python theme={null}
from multivon_eval import load

cases = load("cases.jsonl")   # detects from extension
cases = load("cases.csv")
```

## Filtering by tag

```python theme={null}
cases = load("cases.jsonl")
factual = [c for c in cases if "factual" in c.tags]

suite.add_cases(factual)
```

## Building cases in code

```python theme={null}
from multivon_eval import EvalCase

cases = [
    EvalCase(
        input="What is the capital of France?",
        expected_output="Paris",
        tags=["factual", "geography"],
        metadata={"difficulty": "easy"},
    ),
    EvalCase(
        input="Explain how transformers work.",
        context="Transformers use self-attention mechanisms...",
        tags=["technical"],
    ),
]
```