Skip to main content

A benchmarking tool for langchain based LLM pipelines.

Project description

langbench

PyPI - Version Python PyPI - Downloads CI

langbench is an easy to use benchmarking library for langchain based LLM pipelines.

Installation

pip install langbench

Metrics

langbench provides the following metrics:

  • toxicity: Toxicity of the generated text.
  • bias: Bias of the generated text, including:
    • political
    • gender
    • racial
    • educational
    • nationality
    • religious
    • others
  • latency: Latency of the generated text.

Reports are generated in the form of an html file.

Documentation

The official documentation is available at langbench.

License

This project is licensed under the MIT License - see the LICENSE file for details.

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

langbench-0.0.2.tar.gz (4.9 kB view details)

Uploaded Source

Built Distribution

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

langbench-0.0.2-py3-none-any.whl (6.3 kB view details)

Uploaded Python 3

File details

Details for the file langbench-0.0.2.tar.gz.

File metadata

  • Download URL: langbench-0.0.2.tar.gz
  • Upload date:
  • Size: 4.9 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for langbench-0.0.2.tar.gz
Algorithm Hash digest
SHA256 e3320fd7e72edce9ec5b2f546c4710c98c1a4545be8c41a52b291ea9c9e0c038
MD5 8fe390db6d5fac1db42b55cde620cad0
BLAKE2b-256 84e532ee5ed3cdd1c12af5de8e29df00113a2cb0e722e49cfa125d510362a907

See more details on using hashes here.

Provenance

The following attestation bundles were made for langbench-0.0.2.tar.gz:

Publisher: release.yaml on micvitc/langbench

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file langbench-0.0.2-py3-none-any.whl.

File metadata

  • Download URL: langbench-0.0.2-py3-none-any.whl
  • Upload date:
  • Size: 6.3 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/6.1.0 CPython/3.12.9

File hashes

Hashes for langbench-0.0.2-py3-none-any.whl
Algorithm Hash digest
SHA256 793dab673516e973876ba88bfc1e1ba5c3996e7520d94cf34244948680696fe6
MD5 256ff5d0569c3f2bdeeb538855eb7597
BLAKE2b-256 04d23401c10087fb316e8b743151538448c875bd04d334fabdc60379504e4f8b

See more details on using hashes here.

Provenance

The following attestation bundles were made for langbench-0.0.2-py3-none-any.whl:

Publisher: release.yaml on micvitc/langbench

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

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