Add Vector Database (VDB) Automator for Entity Reference Fields

Created on 22 November 2024, 3 months ago

Problem/Motivation

Currently, the AI Automators module lacks functionality to perform semantic searches using vector databases (VDBs) and populate entity reference fields based on the search results. This feature would enhance content relationships by leveraging AI-driven semantic search capabilities.

Proposed resolution

Develop a new Automator plugin that:

  1. Accepts input text from a specified field.
  2. Searches a configured VDB for semantically similar entities.
  3. Retrieves a user-defined number of matching entities.
  4. Populates the target entity reference field with these results.

Remaining tasks

  • Design the Automator plugin architecture.
  • Implement integration with supported VDBs via abstraction layer.
  • Develop configuration options for specifying input fields, VDB settings, and the number of entities to retrieve.
  • Update documentation to guide users on setup and usage.

User interface changes

Add configuration settings within the AI Automators interface to manage VDB connections and Automator behavior.

📌 Task
Status

Needs work

Version

1.0

Component

AI Automators

Created by

🇬🇧United Kingdom seogow

Live updates comments and jobs are added and updated live.
Sign in to follow issues

Merge Requests

Comments & Activities

Production build 0.71.5 2024