MarkdownReader
Defined in: packages/readers/src/markdown.ts:9
Extract text from markdown files. Returns dictionary with keys as headers and values as the text between headers.
Extends
FileReader<Document>
Constructors
Constructor
new MarkdownReader(
removeHyperlinks?,removeImages?):MarkdownReader
Defined in: packages/readers/src/markdown.ts:17
Parameters
removeHyperlinks?
boolean = true
Indicates whether hyperlinks should be removed.
removeImages?
boolean = true
Indicates whether images should be removed.
Returns
MarkdownReader
Overrides
FileReader<Document>.constructor
Methods
markdownToTups()
markdownToTups(
markdownText):MarkdownTuple[]
Defined in: packages/readers/src/markdown.ts:29
Convert a markdown file to a dictionary. The keys are the headers and the values are the text under each header.
Parameters
markdownText
string
The markdown text to convert.
Returns
MarkdownTuple[]
- An array of tuples, where each tuple contains a header (or null) and its corresponding text.
removeImages()
removeImages(
content):string
Defined in: packages/readers/src/markdown.ts:70
Parameters
content
string
Returns
string
removeHyperlinks()
removeHyperlinks(
content):string
Defined in: packages/readers/src/markdown.ts:75
Parameters
content
string
Returns
string
parseTups()
parseTups(
content):MarkdownTuple[]
Defined in: packages/readers/src/markdown.ts:80
Parameters
content
string
Returns
MarkdownTuple[]
loadDataAsContent()
loadDataAsContent(
fileContent):Promise<Document<Metadata>[]>
Defined in: packages/readers/src/markdown.ts:91
Parameters
fileContent
Uint8Array
Returns
Promise<Document<Metadata>[]>
Overrides
FileReader.loadDataAsContent