Automation & Efficiency
RAG.md · 10 documents
Chunker Server
Provides an MCP server with five text chunking strategies and a text analysis tool for recommending the best strategy.
How-to: Customize Chunking Strategies
Shows how to choose and configure three chunking strategies for a RAG pipeline, with CLI and Python examples.
Installing dependencies
Explains RAG concepts and provides a complete Python script to build a FAISS vector index and answer questions using Google Gemini.
Contract RAG MVP — Plan
Defines a complete local-only contract analysis MVP with document upload, background processing, and RAG extraction via Ollama.
inst
Guides building a RAG chat interface that retrieves funny stories from PDFs and generates images using Pinecone and OpenAI.
Toasty — AI Triage & Responsible Disclosure Assistant (2026 — 350 hours)
Outlines a 16-week, 350-hour plan to build an AI assistant that triages issues, detects duplicates, extracts repro steps, and flags PII for OWASP BLT.
WeightedRAG Setup Guide
Walks through setting up the WeightedRAG pipeline: data prep, chunking, embedding, indexing, and retrieval evaluation.
Retrieval Augmented Generation
Implements a local Retrieval-Augmented Generation system using LangChain, Ollama, and Hugging Face models to augment LLM responses with context from a vector store.
WebRover
Presents an AI web agent with three specialized modes for task automation, research, and academic paper generation.
Plan
Outlines a phased implementation plan for a Swift CLI tool that generates commit messages using on-device FoundationModels.