Namespace LMKit.Agents.Tools.BuiltIn.Document
Classes
- DocumentAttachmentExtractTool
A built-in tool for extracting embedded attachments from documents.
Enables agents to list and save embedded files from PDF, EML, and MBOX documents.
- DocumentTextExtractTool
A built-in tool for extracting text content from documents.
Enables agents to extract text from PDF, DOCX, XLSX, PPTX, EML, MBOX, and HTML files with optional page range selection.
- DocumentTextInfoTool
A built-in tool for retrieving document text information.
Enables agents to inspect document metadata such as page count, MIME type, text availability, and file size without extracting the full content.
- DocxToMarkdownTool
Converts a DOCX file into Markdown text.
- EmlToMarkdownTool
Converts an EML (email) file into structured Markdown.
- EmlToPdfTool
Converts an EML (email) file into a PDF document with embedded attachments.
- HtmlToMarkdownTool
Converts HTML text to Markdown.
- ImageCropTool
A built-in tool for cropping images.
Enables agents to automatically detect and remove uniform borders from scanned documents and images using tolerance-based edge detection.
- ImageDeskewTool
Detect and correct skew (rotation) in scanned documents and images.
Straightens scanned documents and photos using Sobel edge detection and structure tensor analysis, then saves the corrected image.
- ImageInfoTool
Get image dimensions, pixel format, and file size.
- ImageMeasureSkewTool
Measure the skew angle of a scanned document or image without modifying it.
- ImageResizeBoxTool
Resize an image to fit within a bounding box while preserving aspect ratio, with padding.
- ImageResizeTool
Resize an image to exact dimensions with optional pixel format conversion.
- ImageToPdfTool
A built-in tool for converting image files into a single PDF document.
Enables agents to combine one or more images (JPEG, PNG, BMP) into a PDF, with each image on its own page sized to match the image dimensions.
- MarkdownToDocxTool
Converts Markdown text to a DOCX file.
- MarkdownToHtmlTool
Converts Markdown text to HTML.
- MarkdownToPdfTool
Converts Markdown content to a PDF file with full formatting support.
- MboxToMarkdownTool
Converts an MBOX (Unix mailbox) file into structured Markdown.
- OcrRecognizeTool
Extract text from images using OCR (Optical Character Recognition).
Supports 34 languages including English, French, German, Chinese, Japanese, Arabic, and more.
- PdfExtractTool
Extracts specific pages from a PDF and saves them as a single output file.
- PdfMergeTool
A built-in tool for merging multiple PDF files into one.
Enables agents to combine multiple PDF documents into a single output file, preserving all pages in the specified order.
- PdfMetadataTool
A built-in tool for retrieving PDF metadata and basic document information.
Enables agents to inspect PDF page count, file size, version, and metadata fields (title, author, subject, keywords, creation date).
- PdfPagesTool
A built-in tool for inspecting PDF page details and extracting page text.
Enables agents to retrieve page dimensions, text-only flags, and extract text content from specific pages of a PDF document.
- PdfSearchTool
A built-in tool for searching text inside PDF documents.
Enables agents to find query occurrences across all pages or a selected page range, returning page numbers and text snippets.
- PdfSplitTool
Splits a PDF into multiple output files by page ranges.
- PdfToImageTool
A built-in tool for rendering PDF pages as images.
Enables agents to convert PDF pages to JPEG, PNG, or BMP image files with configurable resolution, format, and quality options.
- PdfUnlockTool
A built-in tool for removing password protection from PDF documents.
Enables agents to unlock a password-protected PDF by providing the known password, producing an unprotected copy that can be freely opened.