Back to directory

RadCrew Unveiled

The source for the RadCrew.org website, a monorepo pairing a Vite React frontend with a FastAPI backend that answers visitor questions through a guardrailed, RAG-grounded chatbot.

RadCrew Unveiled

RadCrew Unveiled is the monorepo source for the RadCrew.org website, consisting of a Vite React frontend and a FastAPI-and-Uvicorn backend that together serve the site and its FAQ chatbot API. The browser sends a chat message to the backend and reads back a Server-Sent Events stream: a guardrails step screens the incoming message, a router then sends it either to feedback submission or the RAG path, which retrieves matching snippets from the site's own static copy and optional GitHub Markdown content.

The configured LLM provider then streams a grounded answer, using OpenRouter when an API key for it is set, or otherwise Hugging Face; if retrieval is weak and there is no prior conversation history, the system returns a safe fallback response with contact guidance rather than an unsupported answer. The project is a Yarn 1 monorepo, with separate frontend and backend test suites (Vitest and pytest) and its own lint and build commands.

More in RAG

See all 540
  • ai·rete·rag

    ai-rete-rag.com

    A platform that pairs a Rete rule engine with retrieval-augmented generation, so deterministic rules decide an outcome and grounded retrieval explains the decision in plain language.

  • Xtriever

    github.com

    A hybrid retrieval engine for retrieval-augmented generation, written in Rust to run on-device on a phone or a laptop, combining lexical BM25 search, dense embedding search, reciprocal-rank fusion and cross-encoder re-ranking with no server.

  • FileFlux

    github.com

    A .NET library that turns PDF, DOCX, HWP and other documents into optimized chunks for RAG systems, through a five-stage pipeline built on high-performance Rust FFI readers.