The LLM Health Assistant is an AI-driven health consultation platform using LLM and RAG for intelligent Q&A, supporting text/voice interaction, PubMed retrieval, and user data management.

Retrieval-Augmented Generation (RAG) chatbot across four domains: Law, Health, Finance, and Technology. Curated domain-specific datasets from data sources; stored PDFs and embeddings using MongoDB and FAISS. Built a scalable RAG pipeline enabling high-precision similarity search and dynamic query responses.

This Python application creates a simple document assistant using Streamlit, pinecone (vector store) and a language model (openai) for generating responses to user queries.

Find art with AI using Cloudflare's Vector Database Vectorize, LlaVA and LlaMA on Workers AI, and more!

Themis Database System - High-performance C++ hybrid-database (graph-vector-relational-file) with AQL support and MVCC

The goal is to evaluate CVs based on the O-1A visa qualification criteria

An application that looks at input text to search for similar passages within given sources

Anthropic's Contextual Retrieval implementation with visual chunk comparison. Preview context enrichment before/after embedding.

💬🤖 Build a better chatbot 🤖💬

🗃️✨ Mebox is an open-source alternative to OpenAI's file_search tool, designed to efficiently process, store, and retrieve file-based information using Supabase and open source embeddings.

RAG based conversational sales agent chatbot with Gradio frontend that can answer queries about BMW Mini cars and provide suitable recommendations based on personal info.

retrieval augmented generation app based on gradio with different levels of integration. Using simple vector store db and a graph data structure

AIMPACT 2.0 is an advanced movie recommendation system that leverages Python and HTML technologies to provide personalized movie suggestions. The system analyzes user preferences and movie data to generate tailored recommendations, enhancing the user's viewing experience through intelligent algorithms and a user-friendly web interface.

VectorSearch.Tech - Blog articles , tutorials, and guides on latest search technologies.

HACKTOBERFEST '23 Open Source Contribution to Weaviate: Implemented python version of Multi-Modal Search using Weaviate

find-my-movie is a FastAPI-powered Movie Recommendation API that finds movies based on natural language Query, it generates vector embeddings for movie descriptions, and stores them in pgvector for efficient querying.

example portfolio for chatbots made with streamlit, u need to use your OpenAI API key to start a chat

FastAPI-based RAG app: upload PDFs, store OpenAI embeddings in Weaviate, and query with semantic search. Includes a simple HTML UI, Dockerized Weaviate, and ready-to-run setup via requirements.txt.

This application aims to provide users with a convenient way to interact with Langchain documentation through a chat interface powered by advanced Generative AI technologies

Use LLMs to analyze wine reviews