> For the complete documentation index, see [llms.txt](https://docs.raga.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.raga.ai/ragaai-catalyst/ragaai-metric-library/text-summarization/summary-coherence.md).

# Summary Coherence

Check if summaries are logically connected and structured. Spot gaps in flow and enhance overall quality.

**Objective:** 

Summary Coherence measures the logical flow and structural integrity of the summary. It examines whether ideas are presented in a logically connected manner, ensuring that the summary follows a clear progression of thoughts. This is especially important in multi-sentence summaries, where disjointed or fragmented ideas can disrupt understanding.

**Required Columns in Dataset:**

`LLM Summary`, `Prompt`

**Interpretation:**

* **High values**: Indicate that the summary presents information in a well-organized, logically connected sequence.
* **Low values**: Suggest that the summary is disorganized or has disconnected thoughts, making it harder to follow.

**Execution via UI:**

<figure><img src="https://1811327582-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FYbIiNdp1QbG4avl7VShw%2Fuploads%2FgQWxFXMWfumID6uAJXdB%2Fimage.png?alt=media&amp;token=30356739-d455-4039-b3bb-d5de0ee7993e" alt=""><figcaption></figcaption></figure>

**Execution via SDK:**

```python
metrics=[
    {"name": "Summary Coherence", "config": {"model": "gpt-4o-mini", "provider": "openai"}, "column_name": "your-text", "schema_mapping": schema_mapping}
]
```