---
metadata:
  - name: generator
    content: Diplodoc Platform v5.52.0
alternate:
  - https://catboost.ai/docs/en/concepts/input-data_graph-description.md
  - href: en/concepts/input-data_graph-description.md
    type: text/markdown
    title: Markdown version
  - href: ../llms.txt
    type: text/markdown
    title: llms.txt
---
> **Documentation Index:** Fetch the complete configuration index at https://catboost.ai/docs/en/llms.txt

# Graph description

#### Contains
A description of graph structure in the edge list format.

Graph information is used to calculate the [graph aggregated features](https://catboost.ai/docs/en/features/graph-aggregated-features.md).

{% note info %}

Only one thing can be passed, either a graph or [pairs description](https://catboost.ai/docs/en/concepts/input-data_pairs-description.md).

Can be used only when [dataset](https://catboost.ai/docs/en/concepts/input-data_values-file.md) contains the GroupId column.

If graph was used for model training, graph information will be also required for all action on model with dataset (applying, fstr calculation and so on).

{% endnote %}

#### Specification

- List each edge description on a new line.
- Use a tab as the delimiter to separate the columns on a line.

#### Row format

```
<start_vertex index><\t><end_vertex index>
```

- `start_vertex index`is the zero-based index of the start_vertex object from the graph.
- `end_vertex index`is the zero-based index of the loser object from the graph.

#### Example

```
2<\t>1
2<\t>0
7<\t>6
```