Repositório criado para o Workshop de Agentes de IA

A template repository for multi-agents architecture using LangGraph tool from LangChain

⚠️ ARCHIVED — migrated to github.com/devsper-com (runtime, registry, platform)

Harness the Power of Intelligent Search to Uncover Relevant Information from your Documents Instantly using generative AI

Explore Genkit agents for YouTube video searches and content generation. Find workflows to streamline your video discovery and blogging process. 🚀📂

Django-based text utility service, offering multi-language translation, sentiment analysis, and text summarization, all seamlessly deployed on AWS Lambda with Docker for robust and scalable performance.

🛍️ Automate your sales process with an AI-driven multi-agent system that improves efficiency from product inquiries to payment links.

This project showcases how Retrieval-Augmented Generation (RAG) can be applied to create an efficient and user-friendly system for querying large text documents. With this approach, users can easily extract and interact with relevant information from PDFs in real time.

Users can upload documents and seamlessly ask questions about their content, leveraging Retrieval-Augmented Generation (RAG) for precise and context-aware answers.

Building ReAct AI agents with sandboxed Python code execution using AWS Bedrock and LangGraph

Authorization library for RAG (Retrieval-Augmented Generation) pipelines using SpiceDB. Designed for LangChain and LangGraph integrations with support for any vector store

Using LangGraph to create agents, Pytests for testing and deployment on Streamlit

매직아이(SIRDS) 이미지를 해석하는 AI 모델을 구축하고, 학습 데이터량에 따른 지능 지수를 단계별 난이도로 구성하여 인간과 대결하는 게이미피케이션 AI 서비스

LLM complaint insights: Structured summaries, risk tags, and entity extraction on CFPB consumer complaints — built with OpenAI + LangChain, MLflow, Streamlit.

Trackify offers helpful insights, including thorough descriptions of the CV's strengths, recommendations for improving skills, the discovery of missing keywords, and an overall percentage match, by examining the content of the job description and the resume.

This repository demonstrates how to use LangChain’s with_structured_output to generate consistent, machine-readable responses. It includes examples with TypedDict, Pydantic, and JSON Schema, and how they help enforce reliable data formats in LLM applications.

This project allows you to search for academic papers on arXiv, download and process them, and generate responses to specific questions using embeddings and language models. The application leverages several tools including Gradio for the interface, ChromaDB for embedding storage, and LangChain for text processing.

A summarisation assistant powered by voice + RAG + Gen AI