pincone

A comprehensive toolkit for building advanced, AI-driven conversational voice agents with a focus on Retrieval-Augmented Generation (RAG). This repository provides a flexible and powerful platform for creating intelligent voice assistants that can interact with users in real-time and provide context-aware responses based on a knowledge base of your

AI Hiring Tool using React, Flask, OpenAI, and Pinecone. Recruiters input a job description, and the app parses it, scores candidate resumes or LinkedIn profiles, and generates tailored interview questions—showcasing AI integration, product intuition, and modern recruiting automation.

A Chat with PDF! Here, you can upload a PDF and chat with it to retrieve any information you need. It uses LangChain and OpenAI embeddings for processing, with Pinecone for vector storage.

Production-ready RAG service (FastAPI + Bedrock + Pinecone). Secure, modular, cloud-deployable.

The Open-Source Enterprise Meeting Intelligence Platform. A self-hosted, privacy-first alternative to Fireflies.ai & Otter.ai. Features autonomous recording (Zoom/Teams/Meet), Global RAG for cross-meeting chat, speaker diarization, and seamless 2-way sync with Jira & Slack. Built with Next.js 15, AWS Lambda, and OpenAI.

Profeval, a cutting-edge AI chatbot designed to simplify your search for the perfect professor!

MedicAsk is a local RAG medical chatbot: Pinecone , LangChain, Ollama (Llama 3.2) with a custom Flask/JS UI, history-aware follow-ups, streaming answers, and persistent chat history built fully cost-free and privacy-preserving.

A Retrieval-Augmented Generation (RAG) medical chatbot that uses LangChain, Pinecone, and a local Llama LLM. The app provides context-aware answers from a custom PDF knowledge base via a simple web interface.

Pinecone Vector DB

This is self study about the Genai using langchain

A full-stack movie ticket booking system with FastAPI backend , Windows Forms frontend and Integrate embeddings, vectordb.

A production-ready Retrieval-Augmented Generation (RAG) system that intelligently adapts to multiple document domains while maintaining excellence in Insurance, Legal, HR, and Compliance as primary domains.

Web application that allows you to interact with biomedical knowledge graphs and query biomedical questions.

AI-powered bookmark manager. Save any YouTube, Instagram, Twitter, or web link and search your bookmarks using natural language. Built with Next.js 14, Prisma, Pinecone, and Gemini.

An AI-powered FastAPI service that downloads, transcribes, and embeds Bunny.net videos using AGNO, FFmpeg, OpenAI, and Pinecone.

Hands-on NLP & RAG engineering curriculum — 14 modules from document loaders to agentic LangGraph systems. Covers chunking, embeddings, vector DBs, hybrid search, RAGAS evaluation, and production FastAPI deployment.

AI-powered medical chatbot providing symptom analysis, health information & medical guidance using LangChain, OpenAI GPT, and Pinecone vector database. Production-ready with safety protocols & comprehensive documentation.

Production-grade Corrective RAG (CRAG) system built with LangGraph, FastAPI, Pinecone, and React, featuring retrieval grading, query rewriting, web fallback, short-term memory, and evaluation against naive RAG using RAGAS.

Chat with PDF is a TypeScript-based project that allows users to interact with PDF documents through a chat interface. This project leverages Node.js and various npm packages to provide a seamless experience for parsing and querying PDF content.