The financial-tone from krandiash

financial-tone's Introduction

Overview

Developed by	Cartesia AI
Date of development	Feb 14, 2024
Validator type	Format
Blog	-
License	Apache 2
Input/Output	Output

Description

This validator checks an LLM-generated output (in a financial context) for a particular tone.

Requirements

Dependencies: transformers, torch

Installation

guardrails hub install hub://cartesia/financial_tone

Usage Examples

Validating string output via Python

In this example, we use the financial_tone validator on any LLM generated text.

# Import Guard and Validator
from guardrails.hub import FinancialTone
from guardrails import Guard

# Use the Guard with the validator
guard = Guard().use(FinancialTone, on_fail="exception")

# Test passing response
guard.validate(
    "Growth is strong and we have plenty of liquidity.",
    metadata={"financial_tone": "positive"}
)

try:
    # Test failing response
    guard.validate(
        "There are doubts about our finances, and we are struggling to stay afloat.",
        metadata={"financial_tone": "positive"}
    )
except Exception as e:
    print(e)

API Reference

__init__(self, on_fail="noop")

Initializes a new instance of the Validator class.

Parameters:

on_fail (str, Callable): The policy to enact when a validator fails. If str, must be one of reask, fix, filter, refrain, noop, exception or fix_reask. Otherwise, must be a function that is called when the validator fails.

__call__(self, value, metadata={}) → ValidationResult

Validates the given value using the rules defined in this validator, relying on the metadata provided to customize the validation process. This method is automatically invoked by guard.parse(...), ensuring the validation logic is applied to the input data.

Note:

This method should not be called directly by the user. Instead, invoke guard.parse(...) where this method will be called internally for each associated Validator.
When invoking guard.parse(...), ensure to pass the appropriate metadata dictionary that includes keys and values required by this validator. If guard is associated with multiple validators, combine all necessary metadata into a single dictionary.

Parameters:

value (Any): The input value to validate.
metadata (dict): A dictionary containing metadata required for validation.

Key	Type	Description	Default	Required
`financial_tone`	string	One of `positive`, `negative`, `neutral`	`neutral`	No
`financial_tone_threshold`	float	A float value between 0 and 1	`0.8`	No

financial-tone's People

Contributors

Watchers

financial-tone's Issues

Running error while installing

`(env) ubuntu@ip-xxxx~/guardrails$ guardrails hub install hub://cartesia/financial_tone
2024-03-31 20:11:54 ip-xxxxxx guardrails-cli[7820] NOTICE Installing hub://cartesia/financial_tone...
  Running command git clone --filter=blob:none --quiet ...
.....
INFO Collecting git+https://github.com/krandiash/financial-tone.git
  Cloning https://github.com/krandiash/financial-tone.git to /tmp/pip-req-build-toevdg8f
  Resolved https://github.com/krandiash/financial-tone.git to commit 26b71c897f13900e2bc1d7ccaa89d086a31050db
  Installing build dependencies: started
  Installing build dependencies: finished with status 'done'
  Getting requirements to build wheel: started
  Getting requirements to build wheel: finished with status 'done'
  Preparing metadata (pyproject.toml): started
  Preparing metadata (pyproject.toml): finished with status 'done'
Building wheels for collected packages: financial_tone
  Building wheel for financial_tone (pyproject.toml): started
  Building wheel for financial_tone (pyproject.toml): finished with status 'done'
  Created wheel for financial_tone: filename=financial_tone-0.0.0-py3-none-any.whl size=12524 sha256=05f854822a0b02e908539d617177039d3512e624ddd72ed6a07bcef2db5fd9b8
  Stored in directory: /tmp/pip-ephem-wheel-cache-wcldyd4e/wheels/0f/b4/d8/4672f892796b72d674501d53d506140583150705a6ac7acccd
Successfully built financial_tone
Installing collected packages: financial_tone
Successfully installed financial_tone-0.0.0

ERROR: unknown command "inspect"
2024-03-31 20:12:01 ip-172-31-86-75 guardrails-cli[7820] ERROR Failed to inspect `

What could be going wrong here?

Recommend Projects