Simple way to create composable AI agents

Agents and RAG workflows with little to no code

A python library for creating AI assistants with Vectara, using Agentic RAG

A RAG system is just the beginning of harnessing the power of LLM. The next step is creating an intelligent Agent. In Agentic RAG the Agent makes use of available tools, strategies and LLM to generate response in a specialized way. Unlike a simple RAG, an Agent can dynamically choose between tools, routing strategy, etc.

This repository provides the building blocks for integrating LangChain, LangGraph, and the Tilores entity resolution system.

Agentic RAG using Crew AI

GlancyAI is an LLM (like ChatGPT) that you can talk with, and it recommends products and helps you make your educated guess to buy a product.

Simple agents are good for 1-to-1 retrieval system. For more complex task we need multi steps reasoning loop. In a reasoning loop the agent can break down a complex task into subtasks and solve them step by step while maintaining a conversational memory.

Docker implementation of Llama Index Agentic RAG. Developing a RAG system requires multiple component such as LLM, Vector-DB, UI, etc. In this work we perform containerization of entire system.

A tailored Chatbot to reduce hallucinations and improve factuality.

Automated resume generation based on job link using CrewAi

AI Rate My Professor is an AI-powered chatbot that utilizes Agentic RAG AI to help users find detailed information about professors by name or university.

Investigating the efficacy of Retrieval-Augmented Generation (RAG) and Corrective Retrieval-Augmented Generation (CRAG) in harnessing external knowledge to improve AI model performance and output quality.

Conducting literature surveys is time-consuming for researchers and students who must sift through numerous academic papers. This project develops an application that streamlines the process, allowing users to search arXiv for relevant papers by keywords, authors, or topics, receive concise summaries, and interact with the content through Q&A.

Multi document Agentic RAG implementation using OpenAI GPT3.5-Turbo