You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
🤖 An Intelligent Chatbot: Powered by the locally hosted Ollama 3.2 LLM 🧠 and ChromaDB 🗂️, this chatbot offers semantic search 🔍, session-aware responses 🗨️, and an interactive Streamlit interface 🎨 for seamless user interaction. 🚀
The AI-Based Pre-Screening Assistant Bot is an AI-powered technical interview assistant that evaluates candidates using adaptive questioning, real-time feedback, and automated report generation. Built with Streamlit and RAGPipeline, it dynamically adjusts question complexity, tracks candidate performance, and emails interview summaries
iKOMA – Autonomous local AI assistant with secure internet search, continuous plan-execute-reflect loops, real-time dashboards, and safety-first guardrails.
A production-ready AI agent pipeline using LangChain for LLM workflows, LangGraph for agent orchestration, and LangSmith for observability supporting document processing, weather queries, and general Q&A with built-in monitoring and debugging.
An AI-powered medical documentation system that generates comprehensive discharge summaries using Retrieval-Augmented Generation (RAG) architecture. This application leverages advanced language models, medical domain embeddings, and vector databases to assist healthcare professionals in creating accurate, structured clinical documentation.
KardiaFlow is an ultra-low-cost, specialized clinical RAG engine running on FastAPI and ChromaDB for <$0.0002 per query. Designed to fix the flaws of generic document AI—which often destroys lab tables and lacks reliable citations—it delivers a modern, full-stack medical intelligence workspace.
Document Q&A agent template with per-user JWT auth and a pluggable vector store — FAISS or ChromaDB, one env var to switch. SQLite-backed audit trail included. Intermediate tier of the Document Intel Agent Template family — for real users, not yet a full enterprise deployment.
A Legal Assistant Chatbot for lawyers in which lawyers upload their cases in pdf and chatbot reads the all of the necessary points in the pdf It helps them to solve their cases faster.
A zero-infra document Q&A agent template — ChromaDB + your choice of offline or hosted embeddings + OpenAI/Bedrock generation. Clone, pip install, and get a grounded RAG loop running in minutes. POC tier of the Document Intel Agent Template family.
RAG-PDF Assistant — A simple Retrieval-Augmented Generation (RAG) chatbot that answers questions using custom PDF documents. It uses HuggingFace embeddings for text representation, stores them in a Chroma vector database, and generates natural language answers with Google Gemini. In this example, the assistant is powered by a few school policy doc
This repository contains experiments and code for working with Retrieval-Augmented Generation (RAG), vector embeddings, and document ingestion/parsing using Python and popular libraries such as LangChain, HuggingFace, FAISS, and ChromaDB.
An AI-powered e-commerce chatbot that answers FAQs using RAG (ChromaDB + Groq) and handles product search via text-to-SQL, with a semantic router directing
"A Full-Stack Generative AI Chatbot using Retrieval-Augmented Generation (RAG). Built with Streamlit, LangChain, and ChromaDB for chatting with local PDF documents. Supports both OpenAI and Open-Source LLMs."
Intelligent enterprise knowledge platform that ingests Box content, transcribes audio/video with Whisper, indexes documents using ChromaDB and local embeddings, and answers questions with Amazon Bedrock Claude.