Automation & Efficiency
RAG.md · 10 documents
Chunker Server
The Chunker MCP Server provides advanced text chunking capabilities with multiple strategies and configurable options. It supports recursive, semantic, sentence-based, fixed-size, and markdown-aware chunking methods to meet different text processing needs. The server is now available in both original MCP and FastMCP implementations, with FastMCP offering enhanced type safety and automatic validation.
How-to: Customize Chunking Strategies
This guide shows you how to choose and configure different chunking strategies for your RAG pipeline. You can read more about why chunking matters in [Explanation: Understanding Chunking Strategies](../explanations/understanding_chunking.md).
Installing dependencies
[RAG: Retrieval Augmented Generation]
Contract RAG MVP — Plan
A standalone MVP application where:
inst
You're embarking on an exciting RAG project for Es Magico AI Studio! Building a chat interface that pulls funny stories from PDFs and generates images is a fantastic challenge. Below is a structured breakdown of how to tackle this using Pinecone as your vector database and OpenAI for all your AI heavy lifting.
Toasty — AI Triage & Responsible Disclosure Assistant (2026 — 350 hours)
**Goal:** Stand up Toasty as a reliable service wired to BLT/GitHub events; deliver safe, useful summaries early.
WeightedRAG Setup Guide
This guide walks you through setting up the WeightedRAG pipeline from scratch, including data preparation, chunking, and evaluation.
WebRover
<img src="https://img.shields.io/badge/Python-3776AB?style=for-the-badge&logo=python&logoColor=white" />
Retrieval Augmented Generation
Our implementation of a RAG is inspired from [this Lang Chain](https://python.langchain.com/docs/tutorials/rag/) tutorial, but we ensured that everything is running locally using _ollama_ or _Hugging Face_-based LLMs.
Plan
scg Implementation Plan