#pinecone

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

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.

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

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

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

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

AI-powered medical education system with LangGraph ReAct agent orchestrating 4 custom tools (hybrid RAG, PubMed API, medical calculator, web search). Features research mode for multi-source evidence synthesis. Built with LangChain, Pinecone, Google Gemini. 716 PubMed articles, 222 tests.

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

Multi-agent AI customer support system — Pinecone hybrid RAG, SLA-aware ticketing, and RAGAS evaluation on FastAPI + Streamlit

FinSight — Streamlit + FastAPI app for India-focused equity portfolios and an agentic LangGraph assistant (OpenAI tools, Neon Postgres, optional Redis & Pinecone). Deploy-ready with Render.

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

Telegram-бот LARGE с векторной памятью Pinecone: RAG по маркетинговым тезисам Котлера и диджитала. OpenAI embeddings, семантический поиск, aiogram.