Langchain agents

Lightweight AI inference gateway - local model registry & parameter transformer (Python SDK) - with optional Envoy proxy processor and FastAPI registry server deployment options.

Chat based recommendation system to recommend homes

This is a YouTube Q&A Chatbot powered by a Large Language Model (LLM) and FastAPI. Users can enter a YouTube video URL and ask questions — the system generates accurate answers using the video transcript.

Siomi is a platform multi-agent AI to generate answers to our clients by messages, documents, graphics, report from big data and more

Cost-aware model routing for LangChain agents. Routes execution turns to a fast model, keeps the expensive model for planning and recovery.

A quick and lightweight library to chat with databases. It uses schema over bulky data embedding for efficient and speedy interaction, ensuring data security.

Nicolay is a digital history experiment that uses artificial intelligence to explore the speeches of Abraham Lincoln.

Preventive context management for LangChain agents. Collapses consecutive tool-call groups before they fill the context window.

YouTube - Too Long; Didn't Watch

RockTalk is a private, locally running chatbot using Streamlit for the frontend, LangChain for the logic, and Amazon Bedrock as the backend. The webapp provides a user-friendly interface for interacting with various Language Models (LLMs) with advanced features for customization and data input, while keeping your session data local and private.

Rizz glasses (CarletonU Hackathon)

The method of re-ranking involves a two-stage retrieval system, with re-rankers playing a crucial role in evaluating the relevance of each document to the query. RAG systems can be optimized to mitigate hallucinations and ensure dependable search outcomes by selecting the optimal reranking model.

Building a semantic search engine using LangChain and OpenAI

Intelligent PDF Summarizer and Inquiry Companion

A RAG assistant using Ollama (Mistral), Qdrant vector DB, and Streamlit UI. Upload documents, scrape web pages, and interact with your data using real-time, session-isolated chat.

This is a document question answering app made with LangChain and deployed on Streamlit where you can upload a .txt or .docx file, ask questions based on the file and an LLM like Falcon-7B or Dolly-V2-3B answers it. ChromaDB is used as the vector database.

GenAI demo with Amazon Kendra, 🦜️🔗 LangChain and Amazon SageMaker JumpStart

Notes about Artificial Intelligence

Ailixir is an application that utilises LLMs and custom user input to generate AI agent prototypes specialised in fields such as health, economics, physics etc. The prototypes enable the user, which is an entrepreneur-developer, to compare the results produced by different LLMs.

AIGC 整合文档 https://aigc.latentcat.com

LLM agent that provides tools for convenient work with personal documents using voice or text.

AI-powered book recommendations engine that fuses semantic understanding and emotion intelligence to deliver deeply relevant book suggestions. Powered by LangChain, OpenAI embeddings, and emotion-aware NLP across ~7,000 titles, with an interactive Gradio experience for intuitive exploration.

Interactive Book Recommendation System using RAG and RecSys

This repo mainly encapsulates an LLM model + front-end + back-end for generating stories for children. It was a personal project in April last year and is now open source.

Python-based system designed to transcribe audio files, split the transcripts into manageable chunks, create text embeddings using HuggingFace models, and employ advanced question-answering models for retrieval-based QA.

An AI Application that generate diagram from user system requirements, 2nd runner VP Bank Hackathon 2024

Give your AI agents a fetch() that pays. Multi-protocol, multi-chain, open source.

This project seeks to create a comprehensive system for summarising research papers by harnessing the latest advancements in AI and NLP. By merging abstractive text summarization with LLMs and the RAG methodology, we anticipate developing a unique and effective approach to extracting valuable insights from research papers

An ai-chat-app to virtually create/train your custom imaginary friend/character and have realtime converstaion.

A modern web application that integrates a conversational AI chatbot with real-time user interactions smooth animations. Built using React, Framer Motion, Lucide Icons, and ShadCN Components on frontend and fastapi on backend. [Below is website deployed Frontend]

A Langchain app that allows you to chat with multiple PDFs

🤖 Agentic, open-source resume tailor that auto-optimizes your CV for any job description using ai agents— for Hacktoberfest 2025! 🎃

Claude Code plugin for converting n8n workflows to LangGraph TypeScript applications

This project implements a RAG (Retrieval-Augmented Generation) application to answer questions about phenotypes using biological and genomic data. The pipeline integrates information retrieval with response generation via language models (LLM), facilitating accurate analysis of phenotypic data.

A RAG (Retrieval-Augmented Generation) AI chatbot that allows users to upload multiple document types (PDF, DOCX, TXT, CSV) and ask questions about the content. Built using LangChain, Hugging Face embeddings, and Streamlit, it enables efficient document search and question answering using vector-based retrieval. 🚀

A hands-on RAG application that converts natural language questions into SQL queries for a real estate database. Built with LangChain, FastAPI, Streamlit, and OpenAI GPT-4o-mini. Perfect for learning Retrieval-Augmented Generation and LLM-powered database interactions.

Series of generative artificial intelligence (AI) for creating new content, including audio, code, images, text, simulations, and videos.

A fastapi wrapper of babca / python-gsmmodem for a waveshare sim7600x. Not an exact copy of the 'python-gsmmodem' so be sure to uninstall that lib or venv to run | Open-source Twilio with LLM batteries

A temporary/working memory system that assists REMO in handling LLM memories

GPT4 & LangChain & Chroma - Chatbot for large PDF docs

Driving Dynamic Multi-Participant Chat Interactions for AI and Human Discourse 🤖

A powerful web-based research assistant built with Node.js that leverages Ollama LLM to generate intelligent search queries and fetch comprehensive results from popular search APIs (Tavily, Perplexity, or DuckDuckGo). Based on Ollama Deep Researcher from Langchain.

Tool for executing C/C++ code snippets with Langchain Agents.

This is a toy Web application written in Flask, featuring a Medical Assistant Chatbot powered by Large Language Models (LLMs) and Retrieval Augmented Generation (RAG).

LLM-powered Quantitative research assistant which combines financial data, quantitative models, and natural laungage generation to produce insightful market research reports. AI/ML + FinTech Engineering

A personal learning space for LangChain, featuring code snippets, notes, and mini-projects to explore LLM integrations. Ideal for beginners aiming to learn quickly through structured examples.

A RAG pipeline that doesn't trust its own answers. 4 AI agents collaborate to route queries, retrieve docs, synthesize answers, and catch hallucinations automatically.

This is the research agent powered UP with most capable GPT-4o model to do the research using several tools like graph generating, web searching , web scraping and access research document databases.

This is a AI Agent developed during a college project for the Machine Learning class. It is trained using the PokeAPI with the PokeBase library from Python and RAG documentation provided by Bulbapedia.

LM Studio에서 실행하는 로컬서버의 LLM과 임베딩을 이용하여 RAG 웹 챗봇 만들기

SmartRAG is a terminal-based RAG system using LangGraph. It processes queries by retrieving relevant content from markdown or PDFs, then responds using OpenAI GPT. Supports webpage-to-PDF conversion, vector DB search, and modular flow control.

On-Premise AI Powered Research Assistant Right In Your Terminal

Domain-agnostic agent orchestration platform. Django + HTMX dashboard, containerized specialist agents, natural language scheduling, multi-provider LLM support.

In this repository, you'll find a collection of well-structured code examples, exercises, and explanations to help you effectively interact with OpenAI's GPT-3.5 model and Langchain using JavaScript.

This AI-powered app enables users to ask questions to their Notion database using natural language.

A german workshop where you learn how to build RAGs with Langchain

The AI agents include a researcher, a chief editor, and an HTML writer. The researcher will gather the latest news on a specific topic, the editor will select the best one, and the HTML writer will create an HTML template for the newsletter.

AI Data Science Tutor powered by Google Gemini 1.5 Pro Latest offers multi-chat support, persistent memory, voice-to-text input, and IP banning for security. Users can create, rename, and delete chats, ensuring a seamless, secure, and intelligent AI-powered Data Science learning experience. 🚀

NewsBot is an AI-powered Q&A tool that answers questions from uploaded PDFs or web article URLs using LangChain, OpenAI, and Streamlit.

Summary and knowledge destilation of prof. Jordan Peterson's YouTube lectures on Personality and Its Transformations using different methods of information retrieval.

Web application to help develop scraping techniques to create context in LLM prompts.

AI Generated text adventure RPG with fully configurable mechanics

Meet MySQL Assistant: Access database info seamlessly with natural language. No SQL expertise required. Simply ask questions, receive clear responses.

RAG (Retrieval-Augmented Generation) app integrated with a voice assistant and knowledge base management system.

Thalia🍃 currently not developing any more.

All CPU efficient GPU-less Financial Analysis RAG Model with Qdrant, Langchain and GPT4All x Mistral-7B, run RAG without any GPU support!

Conversational Product Recommendations for E-Commerce

The Agentic AI Workshop by ADP Brazil Labs.

Safe Agentic Browsing. Assess target URLs for potential threats and alignment with the agent's browsing intent before navigation.

Creating RAG from Scratch . Creating RAG using the langchain. Creating RAG using llama indexing and Qdrant db

OdiaLingua is an innovative AI-powered chatbot platform designed to preserve and promote the Odia language. It features natural conversations, real-time information, and authentic text-to-speech capabilities, making Odia language accessible through modern technology.

Financial Analysis Agent that can get accurate data for a selected company and perform fundamental and technical analysis

基于本地知识库的轻量化对话机器人

DocuMentor is a sophisticated chatbot application designed to assist users in extracting valuable information from uploaded PDF documents. Users can upload PDF files, chat with the AI chatbot to ask questions or seek information related to the document, and receive well-informed responses.

LLMOps API 是一个基于 Flask 的 API 服务，用于构建、管理和部署基于大语言模型的智能体应用。该项目集成了 LangGraph 和 LangChain，提供了一套完整的工具链，用于创建具有状态、多角色的智能体应用程序。

This project implements an Agentic RAG (Retrieval Augmented Generation) Chatbot, initially accessible via a web interface. The bot's primary role is to serve as a genuine and professional company assistant, capable of engaging with clients, understanding their needs, and effectively guiding them towards purchasing our services and products.

Interactive ChatGPT model for querying Google Drive content. Extract insights from your documents effortlessly.

Java implementation for LangChain

An Open source version of FileQueryBot. Unleash the power of conversational AI on any document. Upload or link files in any format - PDF, TXT, PPTX, DOCX, and more - and let FileQueryBot answer your questions with precision and ease.

Scientific Research Assistant built with LLMs, Retrieval Augmented Generation, and Semantic Search.

A Flask-based onboarding chatbot utilizing Retrieval-Augmented Generation (RAG) with Llama 3.1:8b, powered by LangChain. Designed to assist new employees with onboarding tasks through intelligent, context-aware responses.

AI chat/voice assistant designed to calculate medical scores

AI Engineering Bootcamp for Programmers - A 19-module, 18-week immersive study plan designed for programmers looking to master AI engineering through real-world projects, foundational theory, and practical tools.

This repository is a mental health chatbot implemented using LangChain

Emotional Chatbot AI Question & Answer Text-Generation Knowledge-based on Formula 1 sport.

无需编程，即可快速构建基于先进AI模型的各类智能应用——从简单的问答机器人到包含复杂逻辑的工作流。构建完成后，一键发布 至主流社交平台、Web网页，或通过开放API无缝集成到现有系统进行深度开发。

GraphRag based chatbot built using LangChain and Neo4j, designed for hospital systems. The chatbot retrieves structured and unstructured data about patients, visits, physicians, insurance payers, and hospital locations. This project also explores integrating graph databases and deploying the chatbot using FastAPI & Streamlit

Upload PDFs, ask questions, and get answers with source references using LangChain, Gradio, and local document storage. An open-source AI-powered Q&A tool with source transparency.

A Typeform-inspired Chat Feature with Chat Agents for Engaging Data Collection, Powered by AutoGen and Langchain. Includes REST API Integration for Messaging Systems.

RAG (Retrieval-augmented generation) app made with Flutter, Firebase, Gemini, LangChain and Pinecone.

Claude Code Agents offer specialized AI agents for code, localization, architecture, and automation. Build review and tailor agents for tasks with trust 🐙

Unlock the potential of AI-driven solutions and delve into the world of Large Language Models. Explore cutting-edge concepts, real-world applications, and best practices to build powerful systems with these state-of-the-art models.

This talk was about how to build intelligent chatbot using OpenAI, Langchain, and Firebase.

SQL Agent powered by LLMs

Cargo is an AI-powered advanced multimodal RAG chatbot designed to enable automotive companies to interact effectively with their extensive user manuals.

Rag Tools for Retrieval QA

TravelGenie is a full-stack AI-powered travel assistant that helps users effortlessly plan end-to-end trips through a conversational interface. Built with FastAPI (backend) and TypeScript + Tailwind (frontend), it uses multi-agent orchestration to deliver intelligent travel suggestions.

The News Summarization & Fake News Detection App is an AI-powered solution I developed to make information consumption smarter and more trustworthy. Built with FastAPI, LangChain, HuggingFace, and FAISS, this application retrieves the latest news articles based on any user query