Skip to main content

A tool for evaluating RAG pipelines

Project description

ragulate

A tool for evaluating RAG pipelines

Installation

pip install ragulate

Usage

usage: ragulate [-h] {download-llamadataset,ingest,query} ...

RAGu-late CLI tool.

options:
  -h, --help            show this help message and exit

commands:
  {download-llamadataset,ingest,query}
    download-llamadataset
                        Download a llama-dataset
    ingest              Run an ingest pipeline
    query               Run an query pipeline
    compare             Compare results from 2 (or more) recipes

Download Dataset Example

ragulate download-llamadataset BraintrustCodaHelpDesk

Ingest Example

These commands should work:

ragulate ingest -n chunk_size_500_k_2 -s experiment_chunk_size_and_k.py -m ingest \
--var-name chunk_size --var-value 500 --var-name k --var-value 2 --dataset BraintrustCodaHelpDesk

ragulate ingest -n chunk_size_1000_k_2 -s experiment_chunk_size_and_k.py -m ingest \
--var-name chunk_size --var-value 1000 --var-name k --var-value 2 --dataset BraintrustCodaHelpDesk

Query Exmaple

These commands should work:

ragulate query -n chunk_size_500_k_2 -s experiment_chunk_size_and_k.py -m query_pipeline \
--var-name chunk_size --var-value 500  --var-name k --var-value 2 --dataset BraintrustCodaHelpDesk

ragulate query -n chunk_size_1000_k_2 -s experiment_chunk_size_and_k.py -m query_pipeline \
--var-name chunk_size --var-value 1000  --var-name k --var-value 2 --dataset BraintrustCodaHelpDesk

ragulate query -n chunk_size_500_k_5 -s experiment_chunk_size_and_k.py -m query_pipeline \
--var-name chunk_size --var-value 500  --var-name k --var-value 5 --dataset BraintrustCodaHelpDesk

ragulate query -n chunk_size_1000_k_5 -s experiment_chunk_size_and_k.py -m query_pipeline \
--var-name chunk_size --var-value 1000 --var-name k --var-value 5 --dataset BraintrustCodaHelpDesk

Compare Recipes Example

This command should work:

ragulate compare -r chunk_size_500_k_2 -r chunk_size_1000_k_2 -r chunk_size_500_k_5 -r chunk_size_1000_k_5

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

ragulate-0.0.6.tar.gz (11.6 kB view details)

Uploaded Source

Built Distribution

ragulate-0.0.6-py3-none-any.whl (13.9 kB view details)

Uploaded Python 3

File details

Details for the file ragulate-0.0.6.tar.gz.

File metadata

  • Download URL: ragulate-0.0.6.tar.gz
  • Upload date:
  • Size: 11.6 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.14 Linux/6.5.0-1021-azure

File hashes

Hashes for ragulate-0.0.6.tar.gz
Algorithm Hash digest
SHA256 2941f9614eda065cfbeb0da26124c9b0bc7f8f55165eadb14baa7ea55ebc6565
MD5 dfb652b07466c596cf52d77ac51062ec
BLAKE2b-256 7558482f432548f7b33574cac2fb756bbc832b25aea251574afb802c0e696f66

See more details on using hashes here.

File details

Details for the file ragulate-0.0.6-py3-none-any.whl.

File metadata

  • Download URL: ragulate-0.0.6-py3-none-any.whl
  • Upload date:
  • Size: 13.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: poetry/1.8.3 CPython/3.10.14 Linux/6.5.0-1021-azure

File hashes

Hashes for ragulate-0.0.6-py3-none-any.whl
Algorithm Hash digest
SHA256 4f98f5fd994cdcb3e09590ea09c849efbe47f55de3bec0bcc83240ae66dfd306
MD5 699be90b408541360d770299050970af
BLAKE2b-256 17249572c51620eb423f0029bc306b3bf5f38bb7521786c976737036b73a20de

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