Skip to main content

SDK for truthsystems.ai, a hallucination detection API

Project description

Truth Systems SDK

This is the Python SDK for the Truth Systems API. It allows you to easily interact with the API to judge the veracity of claims based on provided sources.

To use it, you must first have access to the Truth Systems API. See our website for more information.

Quickstart

from truthsys import Client, TextInfluence, TextSource  # or AsyncClient if you like


client = Client.from_url("YOUR_BASE_URL")
ruling = client.judge(
    claim="Sally is a pretty cat",
    sources=[
        TextSource.from_text("I have a cat"),
        TextSource.from_text("I only have one pet"),
        TextSource.from_text("My pet is called Sally"),
    ],
)
ruling.verdict  # whether the claim is supported by the sources - one of "SUPPORTED", "UNSUPPORTED", "CONTRADICTED"

for statement in ruling.statements:
    # in this case, there are two statements: "Sally is a cat" and "Sally is pretty"
    print(f'The statement "{statement.text}" has been judged as {statement.verdict}')

    for influence in statement.influences:
        # the reasons for the judgement are statements within sources
        print(
            f'The statement "{influence.text}" made in "{influence.source}" influenced this judgement'
        )

        if isinstance(influence, TextInfluence):
            # currently always the case, might change in future versions
            print(
                f"The influence spans characters {influence.span[0]} to {influence.span[1]}"
            )

Errors

All error types raised by the SDK are available to import from truthsys.errors. Please report unexpected errors.

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

truthsys-0.1.0.tar.gz (8.1 kB view details)

Uploaded Source

Built Distribution

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

truthsys-0.1.0-py3-none-any.whl (10.0 kB view details)

Uploaded Python 3

File details

Details for the file truthsys-0.1.0.tar.gz.

File metadata

  • Download URL: truthsys-0.1.0.tar.gz
  • Upload date:
  • Size: 8.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: pdm/2.22.2 CPython/3.13.0 Linux/6.12.4-1-MANJARO

File hashes

Hashes for truthsys-0.1.0.tar.gz
Algorithm Hash digest
SHA256 7a694f1ef1499abd68a37e6408e99132ea35e329504099fc7575decc21f51c45
MD5 1a11fecf70b11ed0d2c0fa5f0bf90ee1
BLAKE2b-256 124269cc7e99bf56e52753be3a6af412bf93a9ee384dd02441cfd30d6be6ea5d

See more details on using hashes here.

File details

Details for the file truthsys-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: truthsys-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 10.0 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: pdm/2.22.2 CPython/3.13.0 Linux/6.12.4-1-MANJARO

File hashes

Hashes for truthsys-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 7b684510efc8f86c74f8ed5b558c3e143900c55ef584b94edd557ee8ad961ebe
MD5 d87674fb3b4f1096010b75703d48045f
BLAKE2b-256 5e8b0b77ee349844ac5cc85a84a8f133ab12b551498123442b57be3fa2287894

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