Name		Name	Last commit message	Last commit date
parent directory ..
imgs		imgs
src		src
Intelligent_Image_Gallery.ipynb		Intelligent_Image_Gallery.ipynb
README.md		README.md
app.py		app.py
requirements.txt		requirements.txt

README.md

Intelligent Image Gallery with Uploads, Deduplication, and Text-Based Search Using Vector DB Qdrant and Sentence Transformers.

Smart Image Gallery powered by AI. That can perform the following Tasks:

Search your images using just Text. (Ex: "Smiling group photos", "Surfing", "Exam Notes", etc.,.)
Image Deduplication

Dataset : Currently testing out with an open-source dataset called cats_vs_dogs from HuggingFace.
Dataset : cats_vs_dogs contains about 23,422 images of dogs and cats.
Qdrant : Qdrant is a lightweight vector database that recently started their managed cloud services, which let you use a free cluster for trial and the option to upgrade as you use more features. We will use it to store our dataset in the form of vectors.
CLIP : CLIP is a text and image encoder model that generates embeddings for both text and images! We need a vector representation of images to store them in the Qdrant collection. CLIP
Gradio : User interface built using the open-source demo platform Gradio.

Go to qdrant, Create a new account -> Create new cluster -> Create API key for usage.

Set up environment :

pip install qdrant-client datasets sentence-transformers gradio

Download datasets from HuggingFace :

dataset = load_dataset("cats_vs_dogs",verification_mode='no_checks').shuffle()