Rago is a lightweight framework for RAG
Project description
Rago
Rago is a lightweight framework for RAG.
- Software License: BSD 3 Clause
- Documentation: https://osl-incubator.github.io/rago
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?')
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
rago-0.7.1.tar.gz
(10.5 kB
view details)
Built Distribution
rago-0.7.1-py3-none-any.whl
(17.4 kB
view details)
File details
Details for the file rago-0.7.1.tar.gz.
File metadata
- Download URL: rago-0.7.1.tar.gz
- Upload date:
- Size: 10.5 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
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 94faa748da92d547a02b34f1c7386e3f1b7f4c9dbc262d2d3d65c3d8957edb3b |
|
| MD5 | e8a89a33aa7314886227f944eb6e4902 |
|
| BLAKE2b-256 | bf3f195e0bfe916c4dc338e4bec30d0a7aa1ba0fb00db337bf99ccb42e69fedb |
File details
Details for the file rago-0.7.1-py3-none-any.whl.
File metadata
- Download URL: rago-0.7.1-py3-none-any.whl
- Upload date:
- Size: 17.4 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
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 7c54bc1c101c927c2790f8fa8cd16637ac9bbf241127f53a2dd130de4b628a7c |
|
| MD5 | 78ff1b548cc6b7a1c01d2c4bfb4bd376 |
|
| BLAKE2b-256 | 5c483494cbbed4d2a873dd7ea9791ce9453aacbf4dede2ee430625e104f335ab |
