Extensions provide a powerful way to augment the capabilities of the system by exporting blocks to the block manager. These blocks are loaded on startup, enabling you to create custom components and patches. In this guide, we'll outline how to use extensions to create and export components.

Creating Components with the Composition API

Follow Creating Components with the Composition API , you can use the composition API from the mercs_rete library to create components. First, make sure to import the necessary modules:

import { OAIBaseComponent, WorkerContext, OmniComponentMacroTypes, Composer } from 'mercs_rete';

Then, you can create components and patches using methods provided by OAIBaseComponent.

Example:

let component = OAIBaseComponent
  .create(NS_ONMI, "redactPll")
  .fromScratch()
  .set('title', 'PII Redaction')
  .set('category', 'Compliance')
  .set('description', 'Redact Personal Information from text')
  .setMethod('X-CUSTOM')
  .setMeta({
    source: 'summary',
    summary: 'A PII redactor built using the solvvy/redact-pii library, implementing regex based PII reduction along with support for Google Cloud',
    links: {
      'What is PII?': 'https://www.cloudflare.com/learning/privacy/what-is-pii/',
      'redact-pii github': 'https://github.com/solvvy/redact-pii',
      'google cloud DLP': 'https://cloud.google.com/d1pr',
      'Solvy': 'https://www.solvvy.com/'
    }
  });

Adding Inputs/Outputs

Follow Creating Components with the Composition API , you can also define and add inputs/outpus to the component:

const inputs = [
  { name: 'text', type: 'string', description: 'A string', customSocket: 'text' },
  // More input definitions...
  { name: 'usSocialSecurityNumber', type: 'boolean', default: true }
];

inputs.forEach(({ name, type, customSocket, description, default: defaultValue }) => {
  component.addInput(
    component.createInput(name, type, customSocket)
      .set('description', description)
      .setDefault(defaultValue)
      .toOmniIO()
  );
});

Configuring ESBuild to Avoid Errors

To prevent any errors from being thrown and to avoid bundling mercs_shared, which the server already has, you'll need to externalize mercs_rete. You can do this by adding --external:mercs_rete to the ESBuild in your package.json. This step ensures a smooth building process (because it already is loaded in server memory, no need to bundle it).

Export Components and Patches

Add the supports: ["blocks:v2"] property to the extension.yaml to tell the server to try to load the blocks:

supports:
    - "blocks:v2"

An extension must export an object containing hooks and a createComponents() function. Once you have defined your components and patches, combine them into an array and return them within the createComponents() function as described. The system will automatically load these during startup, incorporating them into the available set of components.

export default {
  hooks: extensionHooks,
  createComponents: () => {
    blocks: [ /*array of OmniComponentFormat*/ ],
    patches: [ /*array of OmniComponentPatch*/ ]
  }
}

Building the Extension

After making all the necessary updates to your extension code, run the following command to build the extension:

yarn build

This command compiles your code and generates the extension.js file, which contains the entire extension ready for use. If you are using TypeScript for your extension development, make sure to update the tsconfig.json file with the appropriate configuration for your project.

By following these steps, you can create complex and customizable components and integrate them into the system via extensions. Make sure to follow the guidelines for each type of component or patch and consult the specific documentation related to each class or method for more details.

Step 1: Import Necessary Components

Import the necessary components

Step 2: Create a New Component Instance

Instantiate the ComponentComposer and initialize your component by defining its namespace and operationId using the .create(displayNamespace, displayOperationId) method.

Set the namespace to const NS_OMNI

Step 3: Define Component Characteristics

Further define the characteristics of your component using provided methods. You can set the title, description, method, and category.

Instead of using the fromScratch() method, you can also utilize the fromJSON() method with a valid Partial<OmniComponentFormat> JSON. This must include both the displayNamespace/operationID and apiNamespace/operationId.

Step 4: Create and Add Inputs and Outputs

For inputs and outputs, you'll first create an IOComposer using the .createInput(name, type, customSocket) or .createOutput(name, type, customSocket) methods. You can further define their properties, including setting up controls which can be automatically selected or overridden.

Inputs always have controls associated with them, and they can be defined directly within the input creation process. Here's an example of defining an input with a control:

Note:

When using .allowMultiple() in conjunction with { array: true }, the input array is flattened into a single array:

You can define which characters are used for joining (or separating on input) an array (default is \n) via a custom setting (specific to the Text Socket):

Alternatively, you can also define inputs and outputs in an array:

You also have the option to directly write the JSON if that's your preference.

Step 5: Create and Add Controls (Optional)

Controls are created using the ControlComposer and are added similarly to inputs/outputs.

Or

Step 6: Define Execution Macro

You can define the behavior of your component using a macro. In this case, the OmniComponentMacroTypes.EXEC macro type is used.

Step 8: Export the Component

Finally, convert the component to JSON and export it.

Step 9: Add the Component to App Blocks

Note: extensions don’t need to call addBlock. they just need to export the createComponent function.

Optional Settings:

Composing Patches

To compose a patch with a valid OmniComponentPatch, the same format applies:

Dependencies

Use .dependsOn(string[]) to specify dependencies, indicating if a block relies on other blocks (for instance, when using runblock internally). For example:

Importing an Existing OpenAPI Specification

1. Locate the API Specification: Determine if the API specification exists at a known URL. For example, OpenAI's specification can be found at https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml.

2. Validate the Specification: Use https://editor.swagger.io/ to validate the OpenAPI spec.

3. Add to System:

   • Navigate to packages/omni-server/extensions/omni-core-blocks/server/apis/[NAMESPACE]/[NAMESPACE].yaml.

   • Replace [NAMESPACE] with your desired namespace (e.g., openai).

   • Update the api section as below.

Example Configuration for OpenAI

namespace: openai
api:
  url: https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml
  basePath: https://api.openai.com/v1
  componentType: OAIComponent31
...

Creating an OpenAPI Spec

1. Generate Draft Spec: If the specification doesn't exist, use tools like "OpenAPI Spec Generator" or request ChatGPT 4 to draft an initial spec.

2. Validate the Specification: Use https://editor.swagger.io/ to validate the OpenAPI spec.

3. Add to System:

   • Go to packages/omni-server/extensions/omni-core-blocks/server/apis/[NAMESPACE]/api/[NAMESPACE].yaml.

   • Replace [NAMESPACE] with your desired namespace (e.g., getimg).

   • Update the api section as below.

Example Configuration for GetImg

namespace: getimg
api:
  spec: ./api/getimg.yaml
  basePath: https://api.getimg.ai
title: getimg

Configure API in YAML

Patch Authentication

We support the following authentication type:

http_basic' | 'http_bearer' | 'apiKey' | 'oauth2

If auth is not defined globally in the original OpenAPI spec, you can patch it in the API yaml /omni-core-blocks/server/apis/[NAMESPACE].yaml

namespace: elevenlabs
api:
  url: https://api.elevenlabs.io/openapi.json
  basePath: https://api.elevenlabs.io
  auth:
    type: apiKey
    requireKeys:
      - id: xi-api-key
        displayName: xi-api-key
        type: string
        in: header
title: elevenlabs

Filter APIs

namespace: openai
api:
  url: https://raw.githubusercontent.com/openai/openai-openapi/master/openapi.yaml
  basePath: https://api.openai.com/v1
  componentType: OAIComponent31
  auth:
  
filter:
  operationIds:
    - createChatCompletion
    - createCompletion
    - createImage
    - createModeration
    - createTranscription
    - createTranslation
    - createImageVariation
    - createImageEdit
    - createEdit
    - listModels
    - createEmbedding
title: openai

Configure Blocks in YAML

Basic Metadata

category: Text-to-Speech
description: >-
  Text to Speech Synthesis using the ElevenLabs API, supporting a variety of
  monolingual (english) and multilingual voices.
meta:
  source:
    title: 'ElevenLabs: Text To Speech'
    links:
      Website: https://beta.elevenlabs.io/speech-synthesis
      Subscription: https://beta.elevenlabs.io/subscription
      API Reference: https://docs.elevenlabs.io/api-reference/quick-start/introduction
      Documentation: https://docs.elevenlabs.io/welcome/introduction
      Voice Lab: https://beta.elevenlabs.io/voice-lab
    summary: >-
      Text to Speech Synthesis using the ElevenLabs API, supporting a variety of
      monolingual (english) and multilingual voices.
title: Text To Speech
apiNamespace: elevenlabs
apiOperationId: Text_to_speech_v1_text_to_speech__voice_id__post
displayNamespace: elevenlabs
displayOperationId: simpletts

Filter Inputs/Outputs

scripts:
  hideExcept:inputs:
    - prompt
    - temperature
    - model
    - top_p
    - seed
    - max_tokens
    - instruction
    - images
  hideExcept:outputs:
    - text

Transform

scripts:
  transform:inputs:
  transform:outputs:

Hoist?

scripts:
    hoist:input

Control

controls:
  preview:
    type: AlpineImageGalleryComponent
    displays: output:image
    opts:
      readonly: true

placeholder?

Input

type:

customSocket:

image:
    customSocket: image

Socket Format Options

Base64 image socket option:

socketOpts:
      format: base64

socketOpts:
      format: base64_withHeader

Array:

socketOpts:
      array: true

Allow multiple connect

allowMultiple: true

Rename

inputs:
  'n':
    title: Number of Images

Run block to Generate Choices

  model:
    type: string
    customSocket: text
    choices:
      block: getimg.listModels
      cache: global
      args: 
        pipeline: face-fix
        family: enhancements
      map:
        title: name
        value: id

Use JSONATA to Manipulate the format

messages:
    scripts:
      jsonata: >-
        [{"role":"system", "content": $string(instruction) }, {"role":"user",
        "content": $string(prompt) }]
      delete:
        - prompt
        - instruction
    hidden: true

Patch Security Scheme

securitySchemes

Default Result

how to patch when response doesn't have property?

outputs:
  _omni_result:
    hidden: true

Special Cases

When properties have mutually exclusive or dependencies

image_strength:
    scripts:
      jsonata: >
        $exists(init_image_mode) and init_image_mode = "IMAGE_STRENGTH" ? image_strength : undefined
  step_schedule_end:
    scripts:
      jsonata: >
        $exists(init_image_mode) and init_image_mode = "STEP_SCHEDULE" ? step_schedule_end : undefined
  step_schedule_start:
    scripts:
      jsonata: >
        $exists(init_image_mode) and init_image_mode = "STEP_SCHEDULE" ? step_schedule_start : undefined

Property name is Case-sensitive

Accept:
    hidden: true
    default: application/json
  Organization:
    hidden: true

When request content type is multipart/form-data, need file type to carry mimetype

image:
    customSocket: file