vespaai-playground/NyRAG

advanced, scalable, no-code RAG

What it solves

NyRAG simplifies the process of building Retrieval-Augmented Generation (RAG) applications. It removes the complexity of manually setting up data ingestion pipelines for websites and documents, deploying search infrastructure, and building a chat interface for interacting with that data.

How it works

NyRAG uses a multi-stage retrieval process to ensure comprehensive answers:

  1. Query Enhancement: An LLM generates multiple search queries from a user's question to improve coverage.
  2. Embedding Generation: These queries are converted into embeddings using a SentenceTransformer model.
  3. Vespa Search: The tool performs a nearest-neighbor search against a Vespa deployment to find the most relevant document chunks.
  4. Chunk Fusion: Results are aggregated, deduplicated, and ranked to select the top-k chunks.
  5. Answer Generation: An LLM generates a grounded answer based strictly on the retrieved context.

Who it’s for

Developers and users who want to quickly deploy a RAG system using their own documents or website content, supporting both local (via Docker) and cloud-based Vespa deployments.

Highlights

  • Integrated UI: A web-based interface for managing the entire lifecycle from data processing to chatting.
  • Flexible Data Ingestion: Built-in support for crawling websites or processing local document directories.
  • Broad LLM Compatibility: Works with any OpenAI-compatible API, including local providers like Ollama, LM Studio, and vLLM, or cloud services like OpenRouter and OpenAI.
  • Hybrid Search: Leverages Vespa for efficient, high-performance retrieval.

Related

  • Project
    vespa-engine/sample-apps

    A collection of reference applications and tutorials for Vespa, demonstrating how to implement hybrid search, RAG, and multimodal vector retrieval at scale.

  • Dispatch
    Building LLM-Powered Web Apps with Client-Side Technology

    Ollama explores the feasibility of building fully local Retrieval-Augmented Generation (RAG) web applications using a combination of browser-based tools and Ollama for local LLM execution.

  • Project
    HKUDS/LightRAG

    A lightweight, graph-based RAG framework that combines knowledge graphs and vector embeddings to provide deep contextual understanding and efficient incremental updates.

  • Project
    rag-web-ui/rag-web-ui

    An intelligent dialogue system that allows users to build custom Q&A services by combining their own document knowledge bases with LLMs using Retrieval-Augmented Generation.

  • Project
    langflow-ai/openrag

    An intelligent agent-powered document search platform that enables users to upload, process, and query documents through a chat interface using RAG.