feat: Multi-Modal Embeddings #341
Open
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
hieulaitrung
force-pushed
the
multi-modal-embeddings
branch
from
172b3ad to
373681c
Compare
hieulaitrung
force-pushed
the
multi-modal-embeddings
branch
from
373681c to
8432313
Compare
trevorspires
approved these changes
Feb 20, 2025
trevorspires
approved these changes
Feb 20, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Issue #, if available: #312 Multi-Modal Embeddings
Description of changes:
Adding new Python POC under folder
genai-quickstart-pocs-python/amazon-bedrock-multi-modal-embeddings-poc.This POC demonstrates the implementation of reverse image search using Amazon Bedrock Titan Multimodal Embeddings model and Anthropic Claude 3, with a Streamlit frontend interfacing with FAISS vector database and local file system as image store. Users can import images from Hugging Face datasets which are processed to generate vector embeddings for the database. The system enables reverse image search where users can make a query and/or upload a reference image to find similar ones, with the LLM model providing detailed analysis of the results.
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.