A Retrieval-Augmented Generation (RAG) chatbot for Rwanda Coding Academy built with LangChain.JS and Ollama, combining local LLM inference with intelligent document retrieval to deliver context-aware, accurate, and private conversational AI.
# RCA-chatbot
A Retrieval-Augmented Generation (RAG) chatbot for Rwanda Coding Academy built with LangChain.JS and Ollama, combining local LLM inference with intelligent document retrieval to deliver context-aware, accurate, and private conversational AI.
# RAG Chat App with LangChain.js + Ollama
A Retrieval-Augmented Generation (RAG) chat application built using **LangChain.js** and **Ollama**.
It lets you run an LLM locally, retrieve documents, and get accurate context-aware answers.
---
## Quick Start
### 1. Clone the Repository
git clone
github.com
cd rag-chat-app
2. Install Dependencies
bash
Copy code
npm install
4. Install Ollama
Download and install Ollama from
ollama.ai.
Verify it works:
ollama --version
4. Pull the Model
Pull a local LLM (example: llama3):
ollama pull llama3
6. Configure Environment
npm run dev