kdeps-components-embedding_vectorize
v1.1.1kdeps kdeps-component: embedding_vectorize
set components / shelf workflow
PurposeConvert text into embeddings through the kdeps API
LLM context: ~100 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/embedding_vectorize
- 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/embedding_vectorize.
Pin a version with kdeps install components/embedding_vectorize@<version>.
Contents
component.yaml
apiVersion: kdeps.io/v1
kind: Component
metadata:
name: embedding_vectorize
description: Convert text into embeddings through the kdeps API
version: "1.1.1"
interface:
inputs:
- name: texts
type: array
description: Strings to embed. An empty list is refused
- name: backend
type: string
description: 'Embedding backend: openai, ollama, google'
- name: model
type: string
description: 'Embedding model, for example text-embedding-3-small'
# body is the handler text. The HTTP envelope stays inside the call.
output: "{{ output('call').body }}"
resources:
- actionId: call
name: Vectorize text
httpClient:
method: POST
# In-process host. The HTTP executor calls the handler without dialing.
url: http://kdeps.api/apis/tools.kdeps.io/v1/tools/embedding_vectorize/call
headers:
Content-Type: application/json
failOnError: true
timeout: 30s
data:
texts: "{{ get('embedding_vectorize.texts') }}"
backend: "{{ get('embedding_vectorize.backend') }}"
model: "{{ get('embedding_vectorize.model') }}"
requires:
schemas/v1: ""
tools/embedding_vectorize: ""
version: 1.1.1
requires:
schemas/v1: ""
tools/embedding_vectorize: ""
files:
component.yaml: |
apiVersion: kdeps.io/v1
kind: Component
metadata:
name: embedding_vectorize
description: Convert text into embeddings through the kdeps API
version: "1.1.1"
interface:
inputs:
- name: texts
type: array
description: Strings to embed. An empty list is refused
- name: backend
type: string
description: 'Embedding backend: openai, ollama, google'
- name: model
type: string
description: 'Embedding model, for example text-embedding-3-small'
# body is the handler text. The HTTP envelope stays inside the call.
output: "{{ output('call').body }}"
resources:
- actionId: call
name: Vectorize text
httpClient:
method: POST
# In-process host. The HTTP executor calls the handler without dialing.
url: http://kdeps.api/apis/tools.kdeps.io/v1/tools/embedding_vectorize/call
headers:
Content-Type: application/json
failOnError: true
timeout: 30s
data:
texts: "{{ get('embedding_vectorize.texts') }}"
backend: "{{ get('embedding_vectorize.backend') }}"
model: "{{ get('embedding_vectorize.model') }}"
Versions
| Version | Published | Status |
|---|---|---|
| 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
- 1.1.1
- Published
- 10/20/2026