kdeps-tools-load_document
v1.1.1Load a document file and return its content as text. Supports PDF (langchaingo pdf loader), DOCX/EPUB/RTF/ODT (pandoc), HTML (goquery, lynx), CSV, text, directory, notion, markdown (textutil). Use for reading documents into the conversation for analysis or RAG pipelines. Returns document content with optional splitting into chunks. Requires: source (absolute file path). Optional: type (pdf, csv, html, text - auto-detected from extension), columns (CSV column filter), password (encrypted PDF), chunkSize (split into chunks of N characters), chunkOverlap, chunkSplitter (recursive, token, markdown).
set tools / shelf rag
LLM context: ~395 tokens when loaded (prompt or tool definition)
Where it runs
Part of the tools set, used in workflow and agent mode. What the model is told about each built-in tool: its description, usage notes and parameters. kdeps runs the tool itself.
- the agent loop builds the request
- the tool definitions are sent to the modeltools/load_document
- the model calls a tool
- kdeps runs it
- the result goes back to the model
Loaded by: kdeps (agent loop), /update, /settings, kdeps run, kdeps install, kdeps list, kdeps uninstall, kdeps update
In the code: kdeps (agent loop)agent.RegisterBuiltinToolsagent.definedAs
Install
A kdeps asset: installed with the first-run profile that includes its set, or the first time a command needs it, and updated without a new release.
Pin a version with kdeps install tools/load_document@<version>.
Contents
Load a document file and return its content as text. Supports PDF (langchaingo pdf loader), DOCX/EPUB/RTF/ODT (pandoc), HTML (goquery, lynx), CSV, text, directory, notion, markdown (textutil). Use for reading documents into the conversation for analysis or RAG pipelines. Returns document content with optional splitting into chunks. Requires: source (absolute file path). Optional: type (pdf, csv, html, text - auto-detected from extension), columns (CSV column filter), password (encrypted PDF), chunkSize (split into chunks of N characters), chunkOverlap, chunkSplitter (recursive, token, markdown).
| Parameter | Type | Description |
|---|---|---|
| chunkOverlap | number | Characters of overlap between consecutive chunks. Only used with chunkSize. |
| chunkSize | number | Split into chunks of this many characters (for RAG). 0 = no splitting. |
| chunkSplitter | string | Splitting strategy when chunkSize is set: recursive (default), token, or markdown. |
| columns | array | CSV only - optional column filter. Empty loads all columns. |
| password | string | PDF only - decryption password for encrypted PDFs. |
| source * | string | Absolute path to the document file |
| type | string | Document type: pdf, pandoc, docx, epub, rtf, odt, html, html_lynx, csv, text, textutil, directory, notion. Auto-detected from the file extension if omitted. pdf=langchaingo, pandoc=universal, docx/epub/rtf/odt=pandoc, html_lynx=lynx, textutil=macOS. |
version: 1.1.1
description: 'Load a document file and return its content as text. Supports PDF (langchaingo pdf loader), DOCX/EPUB/RTF/ODT (pandoc), HTML (goquery, lynx), CSV, text, directory, notion, markdown (textutil). Use for reading documents into the conversation for analysis or RAG pipelines. Returns document content with optional splitting into chunks. Requires: source (absolute file path). Optional: type (pdf, csv, html, text - auto-detected from extension), columns (CSV column filter), password (encrypted PDF), chunkSize (split into chunks of N characters), chunkOverlap, chunkSplitter (recursive, token, markdown).'
parameters:
chunkOverlap:
type: number
description: Characters of overlap between consecutive chunks. Only used with chunkSize.
chunkSize:
type: number
description: Split into chunks of this many characters (for RAG). 0 = no splitting.
chunkSplitter:
type: string
description: 'Splitting strategy when chunkSize is set: recursive (default), token, or markdown.'
columns:
type: array
description: CSV only - optional column filter. Empty loads all columns.
password:
type: string
description: PDF only - decryption password for encrypted PDFs.
source:
type: string
description: Absolute path to the document file
required: true
type:
type: string
description: 'Document type: pdf, pandoc, docx, epub, rtf, odt, html, html_lynx, csv, text, textutil, directory, notion. Auto-detected from the file extension if omitted. pdf=langchaingo, pandoc=universal, docx/epub/rtf/odt=pandoc, html_lynx=lynx, textutil=macOS.'
Versions
| Version | Published | Status |
|---|---|---|
| 1.1.1 | 10/22/2026 | active |
| 1.1.0 | 10/21/2026 | active |
| 1.0.0 | 10/11/2026 | active |
Details
- Author
- kdeps
- License
- Apache-2.0
- Latest Version
- 1.1.1
- Published
- 10/11/2026