OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
Image & Video AI

Embeddit

Embeddit is a Python and Flask application that indexes images from a user-selected local folder and provides text-query and image-to-image search through a web interface. It uses OpenAI CLIP to create image embeddings and LanceDB for vector similarity search.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Embeddit — OpenViST project profile in Image & Video AI.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Embeddit when your images are in a local folder and you want both text-based discovery and visual similarity search in a locally run web app.

Who it is for

  • People organizing personal image collections
  • Teams browsing shared visual assets
  • Users searching product photography stored in a configurable folder

Documented uses

  • Find images using a text description.
  • Find visually similar images by uploading an example.
  • Search a local image collection through a browser interface.
Before you choose

Requirements & limits

  • Requires Python 3.8 or higher and pip.
  • The documented setup uses a Python virtual environment and installs dependencies from requirements.txt.
  • The search collection is selected through an image folder, with images/ as the default.

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 and search a local image folder

Run Embeddit’s local web interface to search a chosen image collection by text or visual similarity.

Before you start

  • Python 3.8 or higher and pip
  • The Embeddit project folder and its requirements.txt file
  • A folder of images to index

Steps

  1. From the project folder, create a virtual environment with the command below.

    Documented command
    python3 -m venv embeddit_env

  2. Activate it using embeddit_env\Scripts\activate on Windows, or source embeddit_env/bin/activate on macOS or Linux.

  3. Install dependencies with the command below.

    Documented command
    pip install -r requirements.txt

  4. Place images in the default images/ folder or specify a folder when starting the command below.

    Documented command
    python app_image_search.py --image-folder path/to/your/image/folder

  5. Open http://localhost:5000 in a browser and search with a text query or upload an image.

Expected outcome

A local browser interface for text-based image search and image-to-image similarity search over the selected folder.

Guide limitations

  • The instructions describe a local interface at localhost:5000 and a user-selected image folder.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
sankalp1999/Embeddit · Official homepage title · retained in its source language
How we review sourcesSuggest a correction