Giter VIP home page Giter VIP logo

r2r-rag-prebuilt's Introduction

README

This directory contains the necessary files to deploy a basic RAG pipeline using the R2R framework with the SciPhi cloud platform.

To test this application locally, run the following

# Install
pip install -r requirements.txt

# Launch
uvicorn src.app:app

Visit here for more information on how to customize your application.

File Structure

The main files in this directory are:

  • src/app.py: The main entry point for the application.
  • config.json: The configuration file used to control the deployment settings.
  • requirements.txt: The file specifying the Python dependencies required by the application.

Application Overview

The application is built using the r2r library and follows a pipeline-based architecture. The main entry point is in the src/app.py file, which creates a pipeline using the E2EPipelineFactory.create_pipeline() method. This method reads the configuration settings from the config.json file to set up the various components of the pipeline.

The config.json file contains the following configuration options:

  • database: Specifies the vector database provider. In this case, the default is set to "sciphi". This results in a SciPhi managed Lantern database. Selecting an alternative provider like qdrant allows the developer to connect with their remote cloud offering.
  • evals: Specifies the evaluation provider (set to "deepeval") and the pipeline evaluation frequency.
  • embedding: Specifies the embedding provider (set to "openai"), the embedding model, dimension, and batch size.
  • text_splitter: Specifies the text splitting settings, including the chunk size and chunk overlap.
  • language_model: Specifies the language model provider. In this case, it is set to "litellm".

Configuration

The config.json file is used to control the deployment settings of the application. You can modify the configuration options in this file to customize the behavior of the pipeline components, such as the database provider, continuous evaluation settings, embedding settings, text splitter settings, and language model provider.

r2r-rag-prebuilt's People

Contributors

emrgnt-cmplxty avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.