Skip to main content

A package that can be used to create RAGs with a single line of code.

Project description

Ragasas (Retrieval Augmented Generation as Software as a Service)

Example Usage:

from ragasas import Ragasas

# Data prep
openai_api_key = "YOUR_OPENAI_API_KEY"
data = [
    "Ragasas streamlines the RAG (Retrieval Augmented Generation) development process.",
    "Ragasas is a Python package.",
    "Ragasas was created by Eric Gustin.",
]
retriever_message = "Searches and returns documents regarding Ragasas."
system_message = "You are a helpful chatbot who is tasked with answering questions about Ragasas. Assume all questions are about Ragasas."

# Use Ragasas
ragasas = Ragasas(
    openai_api_key,
    data,
    retriever_message,
    system_message,
    embedding_model="text-embedding-ada-002",
    llm_model="gpt-3.5-turbo",
)
response = ragasas.ask("What is Ragasas?")
print(response["output"])

# Response: Ragasas is a Python package created by Eric Gustin. It streamlines the RAG (Retrieval Augmented Generation) development process.

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

ragasas-1.1.5.tar.gz (9.7 kB view details)

Uploaded Source

Built Distribution

ragasas-1.1.5-py3-none-any.whl (8.9 kB view details)

Uploaded Python 3

File details

Details for the file ragasas-1.1.5.tar.gz.

File metadata

  • Download URL: ragasas-1.1.5.tar.gz
  • Upload date:
  • Size: 9.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.9.19

File hashes

Hashes for ragasas-1.1.5.tar.gz
Algorithm Hash digest
SHA256 c72d959e0eb33eeacebb76eea4c973a88e4689a142e15ee8e41f2780b018e2b1
MD5 e21880d5832a64884e0c3e8805a7686b
BLAKE2b-256 2f619b1e15861078e5ac468a16adbcf9d008a19319787f484e404e30a24677de

See more details on using hashes here.

File details

Details for the file ragasas-1.1.5-py3-none-any.whl.

File metadata

  • Download URL: ragasas-1.1.5-py3-none-any.whl
  • Upload date:
  • Size: 8.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.9.19

File hashes

Hashes for ragasas-1.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 434cba3e19792755808b11dbc2438c1acaee4d44ed13f7b063914703a845af8a
MD5 b3563f598b5f5a28f8e002360cd8c673
BLAKE2b-256 88ed21c2abdc7998338d1ad8b8bc0ce4e0a3fa828c9a5e5a41347cade2f77566

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