kdeps-tools-ocr_image
v1.2.0Extract text from an image via tesseract OCR. Runs entirely locally -- no API key required. Supports png, jpg/jpeg, tiff, bmp, gif. Requires: file (absolute path to the image). Optional: language (tesseract -l value, e.g. 'eng' or 'eng+fra'; default 'eng'), psm (page segmentation mode, default 3), oem (engine mode, default 3). Does not support PDF -- use load_document with type pdf for text-layer PDFs.
set tools / shelf tools
LLM context: ~220 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/ocr_image
- 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/ocr_image@<version>.
Contents
Extract text from an image via tesseract OCR. Runs entirely locally -- no API key required. Supports png, jpg/jpeg, tiff, bmp, gif. Requires: file (absolute path to the image). Optional: language (tesseract -l value, e.g. 'eng' or 'eng+fra'; default 'eng'), psm (page segmentation mode, default 3), oem (engine mode, default 3). Does not support PDF -- use load_document with type pdf for text-layer PDFs.
| Parameter | Type | Description |
|---|---|---|
| file * | string | Absolute path to the image to extract text from |
| language | string | tesseract -l value, e.g. 'eng' or 'eng+fra'. Default: engdefault: eng |
| psm | integer | tesseract --psm page segmentation mode (3 = fully automatic)default: 3 |
| oem | integer | tesseract --oem engine mode (3 = whatever is available)default: 3 |
Command (declared in YAML, no Go code)
tesseract
Arguments: {{.args.file}}stdout-l{{.args.language}}--psm{{.args.psm}}--oem{{.args.oem}}
Paths kept in the workspace: file
version: 1.2.0
description: 'Extract text from an image via tesseract OCR. Runs entirely locally -- no API key required. Supports png, jpg/jpeg, tiff, bmp, gif. Requires: file (absolute path to the image). Optional: language (tesseract -l value, e.g. ''eng'' or ''eng+fra''; default ''eng''), psm (page segmentation mode, default 3), oem (engine mode, default 3). Does not support PDF -- use load_document with type pdf for text-layer PDFs.'
parameters:
file:
type: string
description: Absolute path to the image to extract text from
required: true
language:
type: string
description: 'tesseract -l value, e.g. ''eng'' or ''eng+fra''. Default: eng'
default: eng
psm:
type: integer
description: 'tesseract --psm page segmentation mode (3 = fully automatic)'
default: 3
oem:
type: integer
description: 'tesseract --oem engine mode (3 = whatever is available)'
default: 3
exec:
command: tesseract
install: tesseract-ocr
paths: [file] # checked against the workspace boundary
args:
- "{{.args.file}}"
- stdout # tesseract writes the text to stdout
- "-l"
- "{{.args.language}}"
- "--psm"
- "{{.args.psm}}"
- "--oem"
- "{{.args.oem}}"
Versions
| Version | Published | Status |
|---|---|---|
| 1.2.0 | 10/21/2026 | active |
| 1.1.0 | 10/13/2026 | active |
| 1.0.0 | 10/11/2026 | active |
Details
- Author
- kdeps
- License
- Apache-2.0
- Latest Version
- 1.2.0
- Published
- 10/11/2026