Show HN: R2R V2 – A open source RAG engine with prod features

• R2R

  5 1,460 9.8 Python

  R2R is an open source answer engine with a RESTful API. Powered by RAG, features include hybrid search, graph / multimodal RAG, and more.

  

  Hi HN!

  We're building R2R [https://github.com/SciPhi-AI/R2R], an opinionated open source RAG answer engine that is built on top of Postgres+Neo4j. The best way to get started is with the docs - https://r2r-docs.sciphi.ai/introduction.

  Our V2 represents a major update from our V1 which we have spent the last 3 months intensely building after getting a ton of great feedback from our first ShowHN. New features include multimodal data ingestion, hybrid search with reranking, advanced RAG techniques (e.g. HyDE), automatic knowledge graph construction alongside the original goal of an observable RAG system built on top of a RESTful API that we first shared.

  The problem: Developers struggle to build truthful, accurate RAG solutions. Popular tools like Langchain are complex and lack crucial production features such as user/document management, observability, and a REST API. We experienced these challenges firsthand while building a large-scale semantic search engine, having users report numerous hallucinations and inaccuracies. This highlighted that search+RAG is a difficult problem. We're convinced that these missing features, and more, are essential to effectively monitor and improve such systems over time.

  We decided to build R2R so you can quickly build an AI system for question answering that you can rely on to improve with use. We wanted to make it as simple as possible to build, monitor, and improve a state-of-the-art RAG engine using any source of data.

  Teams have been using R2R to develop custom AI agents with their own data, with applications ranging from B2B lead generation to research assistants. Best of all, the developer experience is much improved. For example, we have recently seen multiple teams use R2R to deploy a user-facing RAG engine for their application within a day. By day 2 some of these same teams were using their generated logs to tune the system with advanced features like hybrid search and HyDE.

  Here are a few examples of how R2R can outperform classic RAG with semantic search only:

  1. “What were the UK's top exports in 2023?". R2R with hybrid search can identify documents mentioning "UK exports" and "2023", whereas semantic search finds related concepts like trade balance and economic reports.

  2. "List all YC founders that worked at Google and now have an AI startup." Our knowledge graph feature allows R2R to understand relationships between employees and projects, answering a query that would be challenging for simple vector search.

  3. “Compare `The Great Gatsby` to `1984`. Advanced RAG techniques supported by R2R can use agentic behavior to answer separate queries like “key themes of The Great Gatsby” and “key themes of 1984” and then perform aggregation. This gives a better answer semantic semantic search results of the original query, which for the example shown above are likely to be quite poor.

  The built in observability and customizability of R2R helps you to tune and improve your system long after launching. Our plan is to keep the API ~fixed while we iterate on the internal system logic, making it easier for developers to trust R2R for production from day 1.

  Our roadmap is still tentative, but we are working on the following: (1) Improve semantic chunking through third party providers or our own custom LLMs; (2) Training a custom model for knowledge graph triples extraction that will allow KG construction to be 10x more efficient. (This is in private beta, please reach out if interested!); (3) Ability to handle permissions at a more granular level than just a single user; (4) LLM-powered online evaluation of system performance + enhanced analytics and metrics.

  Getting started is easy. R2R is a lightweight repository that you can install locally with `pip install r2r`, or run with Docker. Check out our quickstart guide: https://r2r-docs.sciphi.ai/quickstart. Lastly, if it interests you, we are also working on a cloud solution at https://sciphi.ai.

• Scout Monitoring

  www.scoutapm.com featured

  Free Django app performance insights with Scout Monitoring. Get Scout setup in minutes, and let us sweat the small stuff. A couple lines in settings.py is all you need to start monitoring your apps. Sign up for our free tier today.

  

• R2R-Dashboard

  1 11 7.9 TypeScript

  

  No not yet, I've had difficulty getting these different providers to work together on integrations. If you have any suggestions we are all ears.

  In the meantime we've built our own dashboard which shows ingested documents, and has a customizeable chat interface - https://github.com/SciPhi-AI/R2R-Dashboard.

  It's still a bit rough though.

Suggest a related project