Skip to content
/ R2R Public
forked from SciPhi-AI/R2R

A framework for rapid development and deployment of production-ready RAG systems

License

Notifications You must be signed in to change notification settings

dosyago/R2R

 
 

Repository files navigation

R2R: Production-ready RAG systems.

Docs Discord Github Stars Commits-per-week License: MIT

A semi-opinionanted RAG framework.

Sciphi Framework

R2R was conceived to bridge the gap between experimental RAG models and robust, production-ready systems. Our semi-opinionated framework cuts through the complexity, offering a straightforward path to deploy, adapt, and maintain RAG pipelines in production. We prioritize simplicity and practicality, aiming to set a new industry benchmark for ease of use and effectiveness.

Quick Install:

Install R2R directly using pip:

# use the `'r2r[all]'` to download all required deps
pip install 'r2r[parsing]'

Links

Join the Discord server

Read our Docs

Basic Examples

The project includes several basic examples that demonstrate application deployment and interaction:

  1. app.py: This example runs the main application, which includes the ingestion, embedding, and RAG pipelines served via FastAPI.

    poetry run uvicorn examples.basic.app:app
  2. run_client.py: This example should be run after starting the main application. It demonstrates uploading text entries as well as a PDF to the local server with the python client. Further, it shows document and user-level vector management with built-in features.

    poetry run python -m examples.basic.run_client
  3. run_pdf_chat.py: An example demonstrating upload and chat with a more realistic pdf.

    # Ingest pdf
    poetry run python -m examples.pdf_chat.run_demo ingest
    
    # Ask a question
    poetry run python -m examples.pdf_chat.run_demo search "What are the key themes of Meditations?"
  4. web: A web application which is meant to accompany the framework to provide visual intelligence.

    cd web && pnpm install
    # Serve the web app
    pnpm dev

60s demo of the examples

slim_demo.mp4

Full Install:

Follow these steps to ensure a smooth setup:

  1. Install Poetry:

    • Before installing the project, make sure you have Poetry on your system. If not, visit the official Poetry website for installation instructions.
  2. Clone and Install Dependencies:

    • Clone the project repository and navigate to the project directory:
      git clone [email protected]:SciPhi-AI/r2r.git
      cd r2r
    • Install the project dependencies with Poetry:
      # See pyproject.toml for available extras
      # use "all" to include every optional dependency
      poetry install --extras "parsing"
  3. Configure Environment Variables:

    • You need to set up cloud provider secrets in your .env. At a minimum, you will need an OpenAI key.
    • The framework currently supports PostgreSQL (locally), pgvector and Qdrant with plans to extend coverage.
    • If starting from the example, copy .env.example to .env to apply your configurations:
      cp .env.example .env

Key Features

  • 🚀 Rapid Deployment: Facilitates a smooth setup and development of production-ready RAG systems.
  • ⚖️ Flexible Standarization: Ingestion, Embedding, and RAG with proper Observability.
  • 🧩 Easy to modify: Provides a structure that can be extended to deploy your own custom pipelines.
  • 📦 Versioning: Ensures your work remains reproducible and traceable through version control.
  • 🔌 Extensibility: Enables a quick and robust integration with various VectorDBs, LLMs and Embeddings Models.
  • 🤖 OSS Driven: Built for and by the OSS community, to help startups and enterprises to quickly build with RAG.
  • 📝 Deployment Support: Available to help you build and deploy your RAG systems end-to-end.

Core Abstractions

The framework primarily revolves around three core abstractions:

  • The Ingestion Pipeline: Facilitates the preparation of embeddable 'Documents' from various data formats (json, txt, pdf, html, etc.). The abstraction can be found in ingestion.py.

  • The Embedding Pipeline: Manages the transformation of text into stored vector embeddings, interacting with embedding and vector database providers through a series of steps (e.g., extract_text, transform_text, chunk_text, embed_chunks, etc.). The abstraction can be found in embedding.py.

  • The RAG Pipeline: Works similarly to the embedding pipeline but incorporates an LLM provider to produce text completions. The abstraction can be found in rag.py.

Each pipeline incorporates a logging database for operation tracking and observability.

About

A framework for rapid development and deployment of production-ready RAG systems

Resources

License

Stars

Watchers

Forks

Packages

No packages published

Languages

  • Python 63.7%
  • TypeScript 24.6%
  • SCSS 6.2%
  • Shell 3.7%
  • Other 1.8%