Popular GitHub Repositories for Vector Embeddings

local-first semantic code search engine

? SimilaritySearchKit is a Swift package providing on-device text embeddings and semantic search functionality for iOS and macOS applications.

Next-token prediction in JavaScript — build fast language and diffusion models.

YouTubeGPT • AI Chat with 100+ videos ft. YouTuber Marques Brownlee (@ MKBHD) ⚡️???

SmartScan is an innovative app powered by a CLIP model that automatically organizes your images by content similarity and enables text-based search.

AI chat over the US Constitution ? ? ??

Find Python Packages on PyPI with the help of vector embeddings

a vector embedding database with multiple storage engines and AI embedding integrations

YouTubeGPT ? AI Chat with 100+ videos ft. YouTuber Matt Wolfe (@mreflow) ????

Semantic QA with a markdown database: Query any markdown file using vector embedding, Pinecone vector database and GPT (langchain). A weaker version of privateGPT

UC Berkeley CS186 AI Chatbot ? ?? ?

AI Chat with The ₿itcoin Whitepaper

Python scripts that converts PDF files to text, splits them into chunks, and stores their vector representations using GPT4All embeddings in a Chroma DB. It also provides a script to query the Chroma DB for similarity search based on user input.

AI pipeline built with the honc and workers-ai. vector embeddings, web scraping and processing with Cloudflare Workflows (beta)

UC Berkeley EE16B AI Chatbot ? ?? ?

SoulCare is a mental health app using NLP to analyze social media sentiment, track symptoms, and offer AI-driven support with personalized reports, document uploads, and symptom-based prioritization.

Flask API for generating text embeddings using OpenAI or sentence_transformers

Semantic search with openai's embeddings stored to pineconedb (vector database)

Developed an AI-powered note-taking application using Next.js 14, ChatGPT API, vector embeddings, Pinecone, TailwindCSS, Shadcn UI, and TypeScript.

Text to Image & Reverse Image Search Engine built upon Vector Similarity Search utilizing CLIP VL-Transformer for Semantic Embeddings & Qdrant as the Vector-Store