mupdf

type PDF struct {
	Opts      PDFOptions
	Document  *fitz.Document
	Converter *mdconv.Converter
	Lock      *sync.Mutex
	Tokenizer *tiktoken.Tiktoken
}

type PDFOptions struct {
	// Password for encrypted PDF files.
	Password string

	// Page number to start loading from (default is 1).
	StartPage uint

	// Number of goroutines to load pdf documents
	NumThread int

	// EnablePageMerge
	EnablePageMerge bool

	// ChunkSize - maximum number of tokens allowed in a single document
	ChunkSize int

	ChunkOverlap int

	// TokenEncoding - encoding for Tokenizer to use for page merging
	TokenEncoding string

	// Tokenizer - target model for Tokenizer to use for page merging
	TokenModel string
}