Skip to main content

Rago is a lightweight framework for RAG

Project description

Rago

Rago is a lightweight framework for RAG.

Features

  • Support for Hugging Face
  • Support for llama

Installation

If you want to install it for cpu only, you can run:

$ pip install rago[cpu]

But, if you want to install it for gpu (cuda), you can run:

$ pip install rago[gpu]

Setup

Llama 3

In order to use a llama model, visit its page on huggingface and request your access in its form, for example: https://huggingface.co/meta-llama/Llama-3.2-1B.

After you are granted access to the desired model, you will be able to use it with Rago.

you will also need to provide a hugging face token in order to download the models locally, for example:

rag = Rago(
    retrieval=StringRet(animals_data),
    augmented=SentenceTransformerAug(top_k=3),
    generation=LlamaGen(apikey=HF_TOKEN),
)
rag.prompt('Is there any animals larger than a dinosaur?')

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

rago-0.6.0.tar.gz (9.4 kB view details)

Uploaded Source

Built Distribution

rago-0.6.0-py3-none-any.whl (15.1 kB view details)

Uploaded Python 3

File details

Details for the file rago-0.6.0.tar.gz.

File metadata

  • Download URL: rago-0.6.0.tar.gz
  • Upload date:
  • Size: 9.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.11.10 Linux/6.5.0-1025-azure

File hashes

Hashes for rago-0.6.0.tar.gz
Algorithm Hash digest
SHA256 3616884ac8a8500feef0ff2e344dd26067017f34be2a574632b9ec0924e47d6e
MD5 286b138f51dc0542d9978676f01bf748
BLAKE2b-256 fced88c310d362ad955959898e17afd7484271f4326a7946a8052b532eb0bc46

See more details on using hashes here.

File details

Details for the file rago-0.6.0-py3-none-any.whl.

File metadata

  • Download URL: rago-0.6.0-py3-none-any.whl
  • Upload date:
  • Size: 15.1 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.4 CPython/3.11.10 Linux/6.5.0-1025-azure

File hashes

Hashes for rago-0.6.0-py3-none-any.whl
Algorithm Hash digest
SHA256 f332036f38d4e0f984119cb21a208f8430caf0c02847f2b5e3922206d9b8f6ef
MD5 2c3fc83fe843636352e43afcbc183b01
BLAKE2b-256 df1e7322460cb41f1ff38137a182e4ed0ad96ab01fbb49df81e68889649a3684

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page