Skip to main content

Inspect retrieval results

Project description

Gesserit

drawing

A tiny utility to inspect retrieval results.

Installation

Install gesserit from PyPI using your favorite package manager:

pip install gesserit
# or
uv add gesserit

Usage

Create a search function that returns a list of SearchItem objects, then launch the web UI. Any typed parameters in your search function will be displayed as inputs in the UI:

from gesserit import Gesserit, SearchItem

def search_function(param_1: str, param_2: int = 10, param_3: bool = False):
    # Your search implementation here
    return [
        SearchItem(text="chunk text 1", metadata={"id": "1"}), 
        SearchItem(text="chunk text 2", metadata={"id": "2"})
    ]

app = Gesserit(search_function=search_function)
app.run()  # Accepts any uvicorn parameters

BEIR example

Run uv run examples/beir_nfcorpus.py to see a simple example using gesserit to inspect retrieval results. This example demonstrates text search on the NFCorpus dataset using LanceDB full-text search.
UI looks like this:

BEIR example

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

gesserit-0.3.0.tar.gz (31.7 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

gesserit-0.3.0-py3-none-any.whl (31.9 kB view details)

Uploaded Python 3

File details

Details for the file gesserit-0.3.0.tar.gz.

File metadata

  • Download URL: gesserit-0.3.0.tar.gz
  • Upload date:
  • Size: 31.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.7.20

File hashes

Hashes for gesserit-0.3.0.tar.gz
Algorithm Hash digest
SHA256 99a1881104454b9487d9bef107f39bb8cc9b925ff95c38715070bc0b0a7d39fb
MD5 23e75b6a3336ba04f2a8fb4ee3562620
BLAKE2b-256 fa503d0c54405abebbc5b6ddad7f45daa2bac732f92c1d6ff06aee6b84739230

See more details on using hashes here.

File details

Details for the file gesserit-0.3.0-py3-none-any.whl.

File metadata

  • Download URL: gesserit-0.3.0-py3-none-any.whl
  • Upload date:
  • Size: 31.9 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: uv/0.7.20

File hashes

Hashes for gesserit-0.3.0-py3-none-any.whl
Algorithm Hash digest
SHA256 0c0e785e442b8a01de6904bf1d54cf7dd200f039bb421828b1354bd385ea9341
MD5 8a491aca2079c8d91a03af295d5e661e
BLAKE2b-256 d8f14b03990d05a3ce9ba6d389d543339af36ccbba04ad86c9822d213980df9a

See more details on using hashes here.

Supported by

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