kdeps-components-load_document
v1.2.0kdeps kdeps-component: load_document
set components / shelf workflow
PurposeLoad a document through the kdeps API
LLM context: ~233 tokens when loaded (prompt or tool definition)
Where it runs
Part of the components set, used in workflow and agent mode. Ready-made workflow steps (sql, browser, email, git, ocr...) a resource calls by name; in agent mode they are also tools.
- a resource names a component (or the model calls it as a tool)
- the component's own resources runcomponents/load_document
- its output goes back to the caller
Loaded by: kdeps (agent loop), /settings, kdeps validate, kdeps run, kdeps bundle package, kdeps env, kdeps export k8s, kdeps test
In the code: kdeps (agent loop)yaml.(*Parser).ParseWorkflowyaml.(*Parser).loadAssetComponents
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.
Also installs what it requires, when missing or older: schemas/v1, tools/load_document.
Pin a version with kdeps install components/load_document@<version>.
Contents
component.yaml
apiVersion: kdeps.io/v1
kind: Component
metadata:
name: load_document
description: Load a document through the kdeps API
version: "1.2.0"
interface:
inputs:
- name: source
type: string
required: true
description: Absolute path to the document
- name: type
type: string
description: Document type. Omitted types follow the file extension
- name: columns
type: array
description: CSV only - optional column filter. Empty loads all columns
- name: password
type: string
description: PDF only - decryption password for encrypted PDFs
- name: chunkSize
type: number
default: 0
description: Split into chunks of this many characters (for RAG). 0 = no splitting
- name: chunkOverlap
type: number
default: 0
description: Characters of overlap between consecutive chunks
- name: chunkSplitter
type: string
description: Splitting strategy when chunkSize is set - recursive (default), token, or markdown
# body is the handler text. The HTTP envelope stays inside the call.
output: "{{ output('call').body }}"
resources:
- actionId: call
name: Load a document
httpClient:
method: POST
# In-process host. The HTTP executor calls the handler without dialing.
url: http://kdeps.api/apis/tools.kdeps.io/v1/tools/load_document/call
headers:
Content-Type: application/json
failOnError: true
timeout: 30s
data:
source: "{{ get('load_document.source') }}"
type: "{{ get('load_document.type') }}"
columns: "{{ get('load_document.columns') }}"
password: "{{ get('load_document.password') }}"
chunkSize: "{{ get('load_document.chunkSize') }}"
chunkOverlap: "{{ get('load_document.chunkOverlap') }}"
chunkSplitter: "{{ get('load_document.chunkSplitter') }}"
requires:
schemas/v1: ""
tools/load_document: ""
version: 1.2.0
requires:
schemas/v1: ""
tools/load_document: ""
files:
component.yaml: |
apiVersion: kdeps.io/v1
kind: Component
metadata:
name: load_document
description: Load a document through the kdeps API
version: "1.2.0"
interface:
inputs:
- name: source
type: string
required: true
description: Absolute path to the document
- name: type
type: string
description: Document type. Omitted types follow the file extension
- name: columns
type: array
description: CSV only - optional column filter. Empty loads all columns
- name: password
type: string
description: PDF only - decryption password for encrypted PDFs
- name: chunkSize
type: number
default: 0
description: Split into chunks of this many characters (for RAG). 0 = no splitting
- name: chunkOverlap
type: number
default: 0
description: Characters of overlap between consecutive chunks
- name: chunkSplitter
type: string
description: Splitting strategy when chunkSize is set - recursive (default), token, or markdown
# body is the handler text. The HTTP envelope stays inside the call.
output: "{{ output('call').body }}"
resources:
- actionId: call
name: Load a document
httpClient:
method: POST
# In-process host. The HTTP executor calls the handler without dialing.
url: http://kdeps.api/apis/tools.kdeps.io/v1/tools/load_document/call
headers:
Content-Type: application/json
failOnError: true
timeout: 30s
data:
source: "{{ get('load_document.source') }}"
type: "{{ get('load_document.type') }}"
columns: "{{ get('load_document.columns') }}"
password: "{{ get('load_document.password') }}"
chunkSize: "{{ get('load_document.chunkSize') }}"
chunkOverlap: "{{ get('load_document.chunkOverlap') }}"
chunkSplitter: "{{ get('load_document.chunkSplitter') }}"
Versions
| Version | Published | Status |
|---|---|---|
| 1.2.0 | 10/21/2026 | active |
| 1.1.1 | 10/21/2026 | active |
| 1.1.0 | 10/21/2026 | active |
| 1.0.0 | 10/20/2026 | active |
Details
- Author
- kdeps
- License
- Apache-2.0
- Latest Version
- 1.2.0
- Published
- 10/20/2026