> For the complete documentation index, see [llms.txt](https://docs.flowiseai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.flowiseai.com/integrations/langchain/document-loaders/microsoft-powerpoint.md).
# Microsoft Powerpoint
Microsoft PowerPoint is a presentation program for creating and displaying slide shows. This module provides functionality to load and process PowerPoint files using officeparser.
This module provides a sophisticated PowerPoint document loader that can:
* Load PowerPoint presentations
* Extract text from slides
* Split content into individual slides
* Handle slide numbering
* Process metadata per slide
* Support multiple slide formats
* Handle various slide separators
## Inputs
### Required Parameters
* **PowerPoint File**: The PowerPoint file(s) to process (.ppt, .pptx)
### Optional Parameters
* **Text Splitter**: A text splitter to process the extracted content
* **Additional Metadata**: JSON object with additional metadata
* **Omit Metadata Keys**: Comma-separated list of metadata keys to omit
## Outputs
* **Document**: Array of document objects containing metadata and pageContent
* **Text**: Concatenated string from pageContent of documents
## Features
* Text extraction
* Slide separation
* Metadata handling
* Error handling
* Memory-efficient processing
* Heuristic slide detection
* Content filtering
## Slide Detection Methods
### Pattern Recognition
The loader attempts to identify slides using common patterns:
* "Slide X" markers
* "Page X" markers
* "X/Y" page numbers
* Underscore separators
* Dash separators
* Multiple newlines
### Fallback Mechanisms
If pattern recognition fails:
1. Split by double newlines
2. Treat content as single slide
## Document Structure
Each document contains:
* **pageContent**: Extracted text content from the slide
* **metadata**:
* slideNumber: Sequential slide number
* documentType: "powerpoint"
* Additional custom metadata
## Content Processing
* Empty slides are filtered out
* Leading/trailing whitespace removed
* Minimum content length validation
* Reasonable slide count validation
## Metadata Attributes
Default attributes include:
* slideNumber: Slide number (number)
* documentType: Type of document (string)
* Custom metadata from input
## Notes
* Uses officeparser for extraction
* Handles various slide formats
* Intelligent slide detection
* Content validation
* Memory-efficient processing
* Error handling for invalid files
* Flexible output formats
* Robust fallback mechanisms
---
# 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.flowiseai.com/integrations/langchain/document-loaders/microsoft-powerpoint.md?ask=&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.
