> For the complete documentation index, see [llms.txt](https://docs.stackai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.stackai.com/stackai-tools/document-processing.md).

# Document Processing

Extract text, answer questions, or prepare document files for later workflow steps. Choose carefully between tools that accept file URLs and tools that process documents loaded earlier in the workflow.

## Choose a tool

| Tool                                                                               | Use it to                                                                               |
| ---------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------- |
| [Parse Files](/stackai-tools/document-processing/parse-files.md)                   | Extract text from file URLs and divide it into smaller sections for later processing.   |
| [Document Q\&A](/stackai-tools/document-processing/document-q-and-a.md)            | Answer a question using documents loaded earlier in the workflow.                       |
| [Summarize Documents](/stackai-tools/document-processing/summarize-documents.md)   | Create a summary of documents loaded earlier in the workflow.                           |
| [Transcribe Documents](/stackai-tools/document-processing/transcribe-documents.md) | Produce a text transcription of documents already loaded in the workflow.               |
| [Translate Documents](/stackai-tools/document-processing/translate-documents.md)   | Translate the text of documents loaded earlier in the workflow.                         |
| [Split Files](/stackai-tools/document-processing/split-files.md)                   | Divide parsed file content into smaller text groups.                                    |
| [Page Split](/stackai-tools/document-processing/page-split.md)                     | Create separate file parts from selected page ranges.                                   |
| [Split Sheets](/stackai-tools/document-processing/split-sheets.md)                 | Divide CSV or Excel data into smaller groups of rows.                                   |
| [Unzip File](/stackai-tools/document-processing/unzip-file.md)                     | Extract files from a ZIP archive so later workflow steps can process them individually. |
| [Fill Form (PDF/DOCX)](/stackai-tools/document-processing/fill-form-pdf-docx.md)   | Fill a PDF or DOCX form and return a downloadable completed file.                       |

**Document inputs:** Document Q\&A, Summarize Documents, Transcribe Documents, and Translate Documents use documents loaded by an earlier workflow step. Parse Files, Page Split, Split Sheets, Unzip File, and Fill Form accept file URLs. Split Files divides parsed content.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.stackai.com/stackai-tools/document-processing.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.