Self-hosted RAG engine for AI coding assistants. Ingests technical docs & code repositories locally with structure-aware chunking. Serves grounded context via MCP to prevent hallucinations in software development workflows.

RAG-Ingest: A tool for converting PDFs to markdown and indexing them for enhanced Retrieval Augmented Generation (RAG) capabilities.

Case study using dotfurther's Open Discover Platform with the RavenDB document store to rapidly create a full-text search/eDiscovery/information governance capable demonstration application.

Drop-in RAG and AI agent toolkit for Laravel — parse, chunk, embed, search, chat.

A simple RAG toolkit.

A modular, self-hosted RAG pipeline for building a private, searchable personal knowledge base from PDFs and structured documents.

Extension of the original MemPalace with document ingestion, image assets, MCP tooling, and folder watch.

Production-grade RAG backend for document ingestion and semantic retrieval using embeddings and Pinecone.

An AI Analytics Dashboard for research labs analytics, collaboration, and email workflow using React and FastAPI.

Production-grade RAG chatbot with a FastAPI + LangGraph backend (Pinecone vector search + Groq LLM + Tavily web fallback) and a Streamlit chat UI, secured via API key and observable in LangSmith.

Plantilla n8n para la ingesta automatizada de documentos en sistemas RAG. Extrae, fragmenta y vectoriza datos locales hacia Supabase pgvector.

Self-hosted RAG prototype to ingest PDFs/HTML and chat with them via a local UI

An implementation of the GraphRAG pipeline (based on the 2024 paper "From Local to Global" by Edge et al.) for query-focused summarization of large text corpora.

Store millions of text chunks inside ultra-compact MP4 files, index them with local embeddings, and retrieve answers instantly for fully offline RAG with any LLM.

AI-powered RAG assistant for parents to get instant, context-aware answers on Brainwonders’ career counseling programs, pricing, and services. Built with Streamlit, LangChain, ChromaDB, and Google Gemma LLM for fast, multi-document retrieval and conversational Q&A.

Enterprise Document Ingestion with AI Embeddings — Multi-source ingestion pipeline with pgvector, GDPR compliance, and MCP server

A local AI-powered chat assistant that queries a persistent knowledge wiki built from your documents. Ingests PDFs, URLs, and markdown via Docling, extracts entities/concepts with LLMs, indexes in Qdrant for semantic search, and serves a chat UI—all running offline with Ollama. Inspired by Karpathy's LLM Wiki pattern.

Privacy-first document ingestion for Paperless-ngx supercharged with local AI

Local-first LLM Wiki built with Ollama, FastAPI, and SQLite.

Procurement intelligence and spend operating system for ingesting messy records, normalizing catalogs, surfacing savings/leakage, and giving operators proof-backed workflows, compliance controls, offers, operations, and pilot dashboards.