1  ---
 2  title: "PPTXToDocument"
 3  id: pptxtodocument
 4  slug: "/pptxtodocument"
 5  description: "Convert PPTX files to documents."
 6  ---
 7  
 8  # PPTXToDocument
 9  
10  Convert PPTX files to documents.
11  
12  <div className="key-value-table">
13  
14  |  |  |
15  | --- | --- |
16  | **Most common position in a pipeline** | Before [PreProcessors](../preprocessors.mdx)  or right at the beginning of an indexing pipeline |
17  | **Mandatory run variables**            | `sources`: PPTX file paths or [`ByteStream`](../../concepts/data-classes.mdx#bytestream)  objects           |
18  | **Output variables**                   | `documents`: A list of documents                                                               |
19  | **API reference**                      | [Converters](/reference/converters-api)                                                               |
20  | **GitHub link**                        | https://github.com/deepset-ai/haystack/blob/main/haystack/components/converters/pptx.py      |
21  
22  </div>
23  
24  ## Overview
25  
26  The `PPTXToDocument` component converts PPTX files into documents. It takes a list of file paths or [`ByteStream`](../../concepts/data-classes.mdx#bytestream) objects as input and outputs the converted result as a list of documents. Optionally, you can attach metadata to the documents through the `meta` input parameter.
27  
28  ## Usage
29  
30  First, install the`python-pptx` package to start using this converter:
31  
32  ```shell
33  pip install python-pptx
34  ```
35  
36  ### On its own
37  
38  ```python
39  from haystack.components.converters import PPTXToDocument
40  
41  converter = PPTXToDocument()
42  results = converter.run(
43      sources=["sample.pptx"],
44      meta={"date_added": datetime.now().isoformat()},
45  )
46  documents = results["documents"]
47  
48  print(documents[0].content)
49  
50  ## 'This is the text from the PPTX file.'
51  ```
52  
53  ### In a pipeline
54  
55  ```python
56  from haystack import Pipeline
57  from haystack.document_stores.in_memory import InMemoryDocumentStore
58  from haystack.components.converters import PPTXToDocument
59  from haystack.components.preprocessors import DocumentCleaner
60  from haystack.components.preprocessors import DocumentSplitter
61  from haystack.components.writers import DocumentWriter
62  
63  document_store = InMemoryDocumentStore()
64  
65  pipeline = Pipeline()
66  pipeline.add_component("converter", PPTXToDocument())
67  pipeline.add_component("cleaner", DocumentCleaner())
68  pipeline.add_component(
69      "splitter",
70      DocumentSplitter(split_by="sentence", split_length=5),
71  )
72  pipeline.add_component("writer", DocumentWriter(document_store=document_store))
73  pipeline.connect("converter", "cleaner")
74  pipeline.connect("cleaner", "splitter")
75  pipeline.connect("splitter", "writer")
76  
77  pipeline.run({"converter": {"sources": file_names}})
78  ```