Skip to content

The agent engineering platform.

docs: adding context for Textract linearization-config param (#32064)

Ahmad Elmalah1892a67eef1b
diff --git a/docs/docs/integrations/document_loaders/amazon_textract.ipynb b/docs/docs/integrations/document_loaders/amazon_textract.ipynb
index 9eb475180b..318a22e29a 100644
--- a/docs/docs/integrations/document_loaders/amazon_textract.ipynb
+++ b/docs/docs/integrations/document_loaders/amazon_textract.ipynb
@@ -216,7 +216,13 @@
"source": [
"## Example 4: Customizing the output format\n",
"\n",
- "You have the option to pass an additional parameter called `linearization_config` to the AmazonTextractPDFLoader which will determine how the text output will be linearized by the parser after Textract runs."
+ "When Amazon Textract processes a PDF, it extracts all text, including elements like headers, footers, and page numbers. This extra information can be \"noisy\" and reduce the effectiveness of the output.\n",
+ "\n",
+ "The process of converting a document's 2D layout into a clean, one-dimensional string of text is called linearization.\n",
+ "\n",
+ "The AmazonTextractPDFLoader gives you precise control over this process with the `linearization_config` parameter. You can use it to specify which elements to exclude from the final output.\n",
+ "\n",
+ "The following example shows how to hide headers, footers, and figures, resulting in a much cleaner text block, for more advanced use cases see this [AWS blog post](https://aws.amazon.com/blogs/machine-learning/amazon-textracts-new-layout-feature-introduces-efficiencies-in-general-purpose-and-generative-ai-document-processing-tasks/)."
]
},
{