1  ---
 2  title: "CSVToDocument"
 3  id: csvtodocument
 4  slug: "/csvtodocument"
 5  description: "Converts CSV files to documents."
 6  ---
 7  
 8  # CSVToDocument
 9  
10  Converts CSV 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`: A list of 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/csv.py        |
21  
22  </div>
23  
24  ## Overview
25  
26  `CSVToDocument` converts one or more CSV files into a text document.
27  
28  The component uses UTF-8 encoding by default, but you may specify a different encoding if needed during initialization.
29  You can optionally attach metadata to each document with a `meta` parameter when running the component.
30  
31  ## Usage
32  
33  ### On its own
34  
35  ```python
36  from haystack.components.converters.csv import CSVToDocument
37  
38  converter = CSVToDocument()
39  results = converter.run(
40      sources=["sample.csv"],
41      meta={"date_added": datetime.now().isoformat()},
42  )
43  documents = results["documents"]
44  
45  print(documents[0].content)
46  ## 'col1,col2\now1,row1\nrow2row2\n'
47  ```
48  
49  ### In a pipeline
50  
51  ```python
52  from haystack import Pipeline
53  from haystack.document_stores.in_memory import InMemoryDocumentStore
54  from haystack.components.converters import CSVToDocument
55  from haystack.components.preprocessors import DocumentCleaner
56  from haystack.components.preprocessors import DocumentSplitter
57  from haystack.components.writers import DocumentWriter
58  
59  document_store = InMemoryDocumentStore()
60  
61  pipeline = Pipeline()
62  pipeline.add_component("converter", CSVToDocument())
63  pipeline.add_component("cleaner", DocumentCleaner())
64  pipeline.add_component(
65      "splitter",
66      DocumentSplitter(split_by="sentence", split_length=5),
67  )
68  pipeline.add_component("writer", DocumentWriter(document_store=document_store))
69  pipeline.connect("converter", "cleaner")
70  pipeline.connect("cleaner", "splitter")
71  pipeline.connect("splitter", "writer")
72  
73  pipeline.run({"converter": {"sources": file_names}})
74  ```