ssgrummons/rag-with-milvus-langchain-streamlit
Template for Retreival-Augmented Generation (RAG) application using Milvus for vector storage, LangGraph for ReAct agentic workflows, and Streamlit for a front end. Runs locally on Ollama with a pipeline to ingest markdown documentation.
This project helps you build a custom AI chatbot that can answer questions based on your specific documentation. You provide your markdown documents, and the system processes them to create a searchable knowledge base. The end result is an interactive web-based chat application where users can ask questions and get intelligent, context-aware responses, making it perfect for customer support, internal knowledge bases, or educational platforms.
No commits in the last 6 months.
Use this if you need to create a question-answering system that uses your private documents and runs entirely on your local machine.
Not ideal if you're looking for a simple, off-the-shelf chatbot without custom knowledge or if you prefer cloud-based AI services.
Stars
10
Forks
1
Language
Python
License
MIT
Category
Last pushed
May 21, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/ssgrummons/rag-with-milvus-langchain-streamlit"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RapidAI/RapidRAG
QA based on local knowledge and LLM.
benitomartin/substack-newsletters-search-course
Production RAG System Course
liweiphys/layra
LAYRA—an enterprise-ready, out-of-the-box solution—unlocks next-generation intelligent systems...
LHRLAB/HyperGraphRAG
[NeurIPS 2025] Official resources of "HyperGraphRAG: Retrieval-Augmented Generation via...
limanmys/sef
On premise enterprise-grade RAG-powered agentic workflow chatbot platform with multi-provider support