khteh/rag-agent
Python LLM-RAG deep agent using LangChain, LangGraph and LangSmith built on Quart web microframework and served using Hypercorn ASGI and WSGI web server.
This project helps operations managers, healthcare administrators, or AI/ML researchers efficiently get answers from diverse data sources, including online blogs, structured databases like PostgreSQL and Neo4J, and even real-time API calls. It takes your complex questions, breaks them down, and provides precise answers, such as hospital wait times or explanations of AI concepts, by synthesizing information from various digital resources. The end-user is typically someone who needs to query and understand information stored across multiple, disparate systems without needing to interact with each system individually.
Use this if you need a smart assistant that can answer complex questions by combining insights from unstructured text, relational databases, graph databases, and live data from APIs.
Not ideal if your data is simple, static, and resides in a single, easily queryable source, as the setup complexity would outweigh the benefits.
Stars
7
Forks
2
Language
Python
License
—
Category
Last pushed
Feb 04, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/khteh/rag-agent"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
deepsense-ai/ragbits
Building blocks for rapid development of GenAI applications
infiniflow/ragflow
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses...
GiovanniPasq/agentic-rag-for-dummies
A modular Agentic RAG built with LangGraph — learn Retrieval-Augmented Generation Agents in minutes.
truefoundry/cognita
RAG (Retrieval Augmented Generation) Framework for building modular, open source applications...
vectara/py-vectara-agentic
A python library for creating AI assistants with Vectara, using Agentic RAG