OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
RAG & Knowledge Systems

Embedditor

Embedditor is an open-source visual editor for preparing text chunks and embedding inputs for vector search. It lets users restructure chunks, select or exclude text, edit metadata and tokens, apply text cleanup and export processed files for downstream use.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Embedditor — OpenViST project profile in RAG & Knowledge Systems.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Embedditor between document preparation and vectorization when you want visual control over chunk boundaries, embedding text or metadata before indexing.

Who it is for

  • Teams preparing documents for vector search or retrieval-augmented generation.
  • Developers who want to review and adjust chunks before passing them to an indexing workflow.

Documented uses

  • Join or split chunks before vectorization.
  • Choose which words, sentences or portions of a chunk become embedding inputs.
  • Edit metadata and tokens, remove text noise, and apply TF-IDF filtering or token normalization.
  • Export prepared content in .veml or JSON for use in a downstream workflow.
Before you choose

Requirements & limits

The repository identifies the project as open source under AGPL-3.0 and documents a self-hosted setup. Its README also links to a demo on IngestAI and says to sign up to try it.

  • The documented application stack is PHP 8.2 and Laravel 10.x.
  • The self-hosted setup instructions require an OpenAI API key.
  • Exports are described as .veml or JSON; the README explicitly mentions LangChain and vector databases as downstream uses.
  • The repository describes cost and retrieval improvements as benefits, not guaranteed results.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up the Laravel application

Prepare the documented local application setup through its database and storage initialization steps.

Before you start

  • PHP 8.2
  • Laravel 10.x
  • An OpenAI API key

Steps

  1. Copy .env.example to .env.

  2. Set OPENAI_API_KEY in .env.

  3. Run php artisan migrate.

  4. Run php artisan db:seed.

  5. Run php artisan storage:link.

Expected outcome

The documented configuration and Laravel initialization steps are complete; the README gives http://localhost:8080/ as the dashboard address.

Guide limitations

  • These are repository setup instructions, not a verified execution or compatibility test.
Documentation 1 ↗
COMPARE OPTIONS

Compare options for Vector search

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
EmbedditorJoin or split chunks before vectorization.Self-hosted, Server, WebThe repository identifies the project as open source under AGPL-3.0 and documents a self-hosted setup. Its README also links to a demo on IngestAI and says to sign up to try it.
Chatbot with PDF for Semantic SearchPrepare document content as embeddings and save it to a supported vector database.WebThe repository is identified as open source and publicly visible on GitHub.
AI LLM PlaygroundAsk questions about PDF documents through an assistant interface.Web
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
IngestAI/embedditor · Official homepage title · retained in its source language
How we review sourcesSuggest a correction