1  ---
 2  title: "PDFMinerToDocument"
 3  id: pdfminertodocument
 4  slug: "/pdfminertodocument"
 5  description: "A component that converts complex PDF files to documents using pdfminer arguments."
 6  ---
 7  
 8  # PDFMinerToDocument
 9  
10  A component that converts complex PDF files to documents using pdfminer arguments.
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`: PDF 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/pdfminer.py  |
21  
22  </div>
23  
24  ## Overview
25  
26  The `PDFMinerToDocument` component converts PDF files into documents using [PDFMiner](https://pdfminersix.readthedocs.io/en/latest/) extraction tool arguments.
27  
28  You can use it in an indexing pipeline to index the contents of a PDF file in a Document Store. 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.
29  
30  When initializing the component, you can adjust several parameters to fit your PDF. See the full parameter list and descriptions in our [API reference](/reference/converters-api#pdfminertodocument).
31  
32  ## Usage
33  
34  First, install `pdfminer` package to start using this converter:
35  
36  ```shell
37  pip install pdfminer.six
38  ```
39  
40  ### On its own
41  
42  ```python
43  from haystack.components.converters import PDFMinerToDocument
44  
45  converter = PDFMinerToDocument()
46  results = converter.run(
47      sources=["sample.pdf"],
48      meta={"date_added": datetime.now().isoformat()},
49  )
50  documents = results["documents"]
51  
52  print(documents[0].content)
53  
54  ## 'This is a text from the PDF file.'
55  ```
56  
57  ### In a pipeline
58  
59  ```python
60  from haystack import Pipeline
61  from haystack.document_stores.in_memory import InMemoryDocumentStore
62  from haystack.components.converters import PDFMinerToDocument
63  from haystack.components.preprocessors import DocumentCleaner
64  from haystack.components.preprocessors import DocumentSplitter
65  from haystack.components.writers import DocumentWriter
66  
67  document_store = InMemoryDocumentStore()
68  
69  pipeline = Pipeline()
70  pipeline.add_component("converter", PDFMinerToDocument())
71  pipeline.add_component("cleaner", DocumentCleaner())
72  pipeline.add_component(
73      "splitter",
74      DocumentSplitter(split_by="sentence", split_length=5),
75  )
76  pipeline.add_component("writer", DocumentWriter(document_store=document_store))
77  pipeline.connect("converter", "cleaner")
78  pipeline.connect("cleaner", "splitter")
79  pipeline.connect("splitter", "writer")
80  
81  pipeline.run({"converter": {"sources": file_names}})
82  ```