Pinecone

ESG knowledge graph + RAG agent. Turn long-form sustainability disclosures into cited answers, extracted entities, and a reviewable graph of evidence.

Intelligent Restaurant Customer Support Chatbot powered by RAG, LangChain, Pinecone, Gemini and Flask.

Full-stack RAG chatbot — upload PDFs, ask questions in natural language. Built with FastAPI, React, LangChain LCEL, Groq (LLaMA 3), and Pinecone. Features conversational memory, source citations, and a modern dark UI.

End-to-end NLP pipeline for automated contract analysis and risk assessment using CUAD and fine-tuned RoBERTa-Legal. Integrates spaCy NER, rule-based heuristics, and Pinecone for semantic search, with REST API deployment, containerization, and full test coverage for legal/compliance research.

A reference n8n workflow that turns a folder of business documents into a chat agent that only answers from those documents. Retrieval-augmented, grounded, with refusal when the answer is not in the indexed sources.

Chatbot developed during Tata Steel Summer Internship, uses live IoT Telemetry data for various machines and allows users to query and fetch details for the same.

AI-powered math tutor for the Israeli Bagrut exam (3/4/5 units) - RAG with Claude API, Pinecone & KaTeX

RAG-based AI Voice Customer Support Agent powered by Google Gemini, ElevenLabs, n8n, and Pinecone for real-time knowledge base retrieval and natural voice interactions.

A RAG chatbot built with n8n — automatically syncs documents from Google Drive, embeds them with OpenAI, stores vectors in Pinecone, and answers questions via an AI Agent

A Retrieval-Augmented Generation (RAG) chatbot that processes PDF documents and answers user queries using context-aware responses powered by Google's Gemini LLM.

Autonomous artist research & signing recommendation system for independent digital music distribution

An intelligent medical chatbot that leverages Gamma LLMV2, BERT-based models, vector embeddings, Pinecone, and LangChain to provide accurate healthcare information through a user-friendly interface.

AI chatbot that answers questions from PDF/word documents — built with n8n, Pinecone, and OpenRouter

And end to end RAG-based medical application (medibot) - Groq LLM, Langchain & Pinecone Vector Database.

RAG multi-agente con validación QA anti-alucinaciones (OpenAI + Pinecone + LangChain). Modo offline reproducible.

Medical Retrieval-Augmented Generation chatbot using LangChain, Pinecone, and LLMs.

Slack-native internal knowledge chatbot with nightly-reindexed RAG (Pinecone) and source-cited answers. Reference build behind a 50% onboarding-time-reduction case study.

Production-ready RAG AI agents built with Groq, Supabase, and Pinecone, showcasing document ingestion, vector search, embeddings, and knowledge-grounded responses.

Production-ready document intelligence platform demonstrating end-to-end AI engineering — from vector embedding and semantic search to streaming LLM responses and real-time NLP analytics. Built on a modern stack: React + TypeScript frontend, Python FastAPI backend, OpenAI embeddings, and Pinecone serverless vector store.............................

An intelligent, context-aware university chat assistant featuring user-scoped JWT authentication, voice assistance (Speech-to-Text & Text-to-Speech), a dynamic vector knowledge base (Pinecone RAG), and a production-ready dashboard.

An AI-powered coffee shop ordering app featuring a multi-agent chatbot pipeline (Content Filter → Classifier → RAG Details / Apriori Recommendations / Order Taking) built with Gemini 2.0 Flash, Pinecone, and Vertex AI. Full-stack with FastAPI backend and Vue 3 frontend.

Telegram assistant with long-term semantic memory powered by Pinecone and OpenAI

Enterprise RAG AI Assistant using FastAPI, React, OpenAI, and Pinecone

AI-powered medical chatbot using Llama 2, LangChain, and Pinecone for intelligent medical query retrieval and response generation.

End-to-end RAG system using n8n, Pinecone vector search, and OpenAI — turns any document into a queryable chatbot.

Hands-On Practice with OpenAI, ChatGPT and LangChain. Use Pinecone and Huggingface and integrate AI into your Node app

AI-powered Multi-Agent Financial Research System using LangGraph, LangChain, Pinecone RAG, Groq LLM, Tavily Search, Yahoo Finance, and Streamlit.

RAG Chatbot using FastAPI, Gemini and Pinecone

Facebook Messenger customer-service chatbot for RC Toy Store, using FastAPI, LangChain, Gemini, Pinecone RAG, and Google Sheets.

Production-ready Bhagavad Gita RAG chatbot using FastAPI, Streamlit, Gemini, FAISS, Milvus, and Pinecone.