> ## Documentation Index
> Fetch the complete documentation index at: https://unstructured-53-docs-243-plugins.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Table descriptions

After partitioning and chunking, you can have Unstructured generate text-based summaries of detected tables.

This summarization is done by using models offered through these providers:

* [GPT-4o](https://openai.com/index/hello-gpt-4o/), provided through OpenAI.
* [Claude 3.5 Sonnet](https://www.anthropic.com/news/claude-3-5-sonnet), provided through Anthropic.
* [Claude 3.5 Sonnet](https://aws.amazon.com/bedrock/claude/), provided through Amazon Bedrock.
* [Gemini 2.0 Flash](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2), provided through Vertex AI.

Here is an example of the output of a detected table using GPT-4o. Note specifically the `text` field that is added.
Line breaks have been inserted here for readability. The output will not contain these line breaks.

```json theme={null}
{
    "type": "Table",
    "element_id": "5713c0e90194ac7f0f2c60dd614bd24d",
    "text": "The table consists of 6 rows and 7 columns. The columns represent 
        inhibitor concentration (g), bc (V/dec), ba (V/dec), Ecorr (V), icorr 
        (A/cm\u00b2), polarization resistance (\u03a9), and corrosion rate 
        (mm/year). As the inhibitor concentration increases, the corrosion 
        rate generally decreases, indicating the effectiveness of the 
        inhibitor. Notably, the polarization resistance increases with higher 
        inhibitor concentrations, peaking at 6 grams before slightly 
        decreasing. This suggests that the inhibitor is most effective at 
        6 grams, significantly reducing the corrosion rate and increasing 
        polarization resistance. The data provides valuable insights into the 
        optimal concentration of the inhibitor for corrosion prevention.",
    "metadata": {
        "text_as_html": "<table>...<full results omitted for brevity>...</table>",
        "filetype": "application/pdf",
        "languages": [
            "eng"
        ],
        "page_number": 1,
        "image_base64": "/9j...<full results omitted for brevity>...//Z",
        "image_mime_type": "image/jpeg",
        "filename": "7f239e1d4ef3556cc867a4bd321bbc41.pdf",
        "data_source": {}
    }
}
```

The generated table's summary will overwrite any previous contents in the `text` field. The table's original content is available
in the `image_base64` field.

Any embeddings that are produced after these summaries are generated will be based on the new `text` field's contents.

## Generate table descriptions

To generate table descriptions, in an **Enrichment** node in a workflow, specify the following:

<Note>
  You can change a workflow's table description settings only through [Custom](/ui/workflows#create-a-custom-workflow) workflow settings.

  Table summaries are generated only when the **Partitioner** node in a workflow is also set to use the **High Res** partitioning strategy. [Learn more](/ui/partitioning).
</Note>

Select **Table**, and then choose one of the following provider (and model) combinations to use:

* **OpenAI (GPT-4o)**. [Learn more](https://openai.com/index/hello-gpt-4o/).
* **Anthropic (Claude 3.5 Sonnet)**. [Learn more](https://www.anthropic.com/news/claude-3-5-sonnet).
* **Amazon Bedrock (Claude 3.5 Sonnet)**. [Learn more](https://aws.amazon.com/bedrock/claude/).
* **Vertex AI (Gemini 2.0 Flash)**. [Learn more](https://cloud.google.com/vertex-ai/generative-ai/docs/gemini-v2).

Make sure after you choose the provider and model, that **Table Description** is also displayed. If **Table Description** and **Table to HTML** are both
displayed, be sure to select **Table Description**.