> 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/summarize-documents.md).

# Summarize Documents

Create a summary of documents loaded earlier in the workflow. Specify what the reader needs so the result focuses on the right information.

## Use this tool

1. Load the documents in an earlier workflow step.
2. Describe the required summary in **Task**, including the topics or format to use.
3. Choose **Algorithm** and **Chunk Size**. Leave **Max Chunks** empty when all document sections must be considered.
4. Run the workflow and review **Summary** against the original documents.

## Behavior and limits

Sequential processing refines the result across sections; parallelized processing handles sections in parallel. Max Chunks samples a limited number of sections from large documents. This reduces processing but can omit material, so do not use it when complete coverage is required. No documents produces an error.

## Inputs

| Field      | Parameter    | Description                                                                                        |
| ---------- | ------------ | -------------------------------------------------------------------------------------------------- |
| Task       | `task`       | The task or question to process the documents with (e.g., 'Summarize', 'Extract key points', etc.) |
| Chunk Size | `chunk_size` | The size of text chunks to process at once (in characters) Default: `8000`.                        |

## Configuration

| Field                | Parameter    | Description                                                                                                                                                                      |
| -------------------- | ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Algorithm (required) | `algorithm`  | Processing algorithm: 'parallelized' for faster processing or 'sequential' for more coherent results                                                                             |
| Max Chunks           | `max_chunks` | Maximum number of document chunks to process. When set, large documents are sampled uniformly to this many chunks, reducing cost and latency. Leave empty to process all chunks. |

## Outputs

| Field   | Parameter | Description                             |
| ------- | --------- | --------------------------------------- |
| Summary | `summary` | The processed result from the documents |

## Related guides

* [Parsing, OCR, and Document Structure](https://docs.stackai.com/technical-reference/files-knowledge-and-retrieval/parsing-ocr-and-document-structure.md)


---

# 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/summarize-documents.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.
