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

# Best practices for parsing

> How to choose parse configurations for clean, reliable outputs

Parse options affect accuracy, cost, and speed. The following scenarios highlight when to use specific configurations.

## Handling handwriting or small text

* Use **[Agentic OCR](https://docs.reducto.ai/api-reference/parse#body-options-ocr-mode)**.
* Best for: forms, signatures, handwritten notes.
* Tradeoff: slightly higher cost and latency in exchange for higher accuracy.

## Working with non-Germanic languages

* Use the **[Multilingual OCR system](https://docs.reducto.ai/api-reference/parse#body-advanced-options-ocr-system)**.
* Needed for: languages outside English, Spanish, Italian, Portuguese, French, or German.
* Also improves parsing of Unicode and special characters.

## Unexpected symbols in your output

* **Cause:** metadata embeddings in PDFs may contain corrupted or hidden text.
* **Fix:** switch to **[OCR extraction mode](https://docs.reducto.ai/api-reference/parse#body-options-extraction-mode)**.
* **Avoid:** Hybrid or Metadata extraction modes unless you are sure the metadata is reliable.

## Missing checkboxes or images

* Enable experimental options in [parse configs](https://docs.reducto.ai/api-reference/parse#body-experimental-options):
  * `enable_checkboxes`: Detects and returns checkboxes with True/False.
  * `return_figure_images`: Detects and returns figures in the document.
  * `return_table_images`: Detects and returns tables in the document.

<Warning>
  URLs from `return_figure_images` and `return_table_images` expire in \~24 hours.\
  Download immediately if you need permanent storage.
</Warning>

## Complex tables causing problems?

* **Option 1: Enrich with table mode**
  * Enable `enrich_mode` with `table`.
  * Add prompts to guide how rows and columns should align.

* **Option 2: AI JSON format**
  * Use [Table Output Format → ai\_json](https://docs.reducto.ai/api-reference/parse#body-advanced-options-table-output-format).
  * Passes the table image to a model for structural analysis.
  * Tradeoff: higher latency, sometimes higher accuracy.

## Spreadsheet related configurations

Only three configurations change outputs for spreadsheets:

* `include_color_information`: adds Excel cell color details with LaTeX to the parse output.
* `spreadsheet_table_clustering`: splits up individual tables inside of multi-table spreadsheets.
* `large_table_chunking`: splits very large tables into smaller, manageable chunks for downstream processing.