Hurix AI FactChecker SDK
Project description
Factchecker SDK
Factchecker SDK is a Python package that verifies factual statements in text using multiple verification models. It supports streaming and non-streaming responses to suit different accuracy and speed needs.
Installation
You can install the Factchecker SDK via pip:
pip install hurix-ai
Features
- Multiple Verification Models:
verify_with_chunksverify_with_snippets(Fast but low accuracy)verify_with_snippets_and_chunksverify_with_snippets_and_chunks_and_partial_claude_entailment(Most accurate but slow)
- Methods:
fact_check- Standard fact-checking method.fact_check_streaming- Provides a streaming response.
Usage
from hurix_ai.factchecker import FactChecker
# Initialize the FactChecker object
obj = FactChecker(api_key="xxxxx", base_url='xxxx', model_name='verify_with_snippets')
# Perform fact-checking
res = obj.fact_check("The capital of India is Delhi")
print(res)
Streaming Fact-Checking
for response in obj.fact_check_streaming("The capital of India is Delhi"):
print(response)
License
This package is licensed under the MIT License.
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
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file hurix_ai-0.2.0.tar.gz.
File metadata
- Download URL: hurix_ai-0.2.0.tar.gz
- Upload date:
- Size: 1.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.1 CPython/3.12.8 Linux/6.8.0-1023-aws
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
af41e7c3417d0398ee3b3ee39388b57aa40ee2e25df35b452b75c063765b44f2
|
|
| MD5 |
82d2d1f94c3d5c4eaab991418b8ad9a7
|
|
| BLAKE2b-256 |
4f2d3a1cf94a947aac8f52e3b5dd5b8a5005eded9982b106c54e81627f713cb8
|
File details
Details for the file hurix_ai-0.2.0-py3-none-any.whl.
File metadata
- Download URL: hurix_ai-0.2.0-py3-none-any.whl
- Upload date:
- Size: 2.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: poetry/2.1.1 CPython/3.12.8 Linux/6.8.0-1023-aws
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4ad86592c866351a713eebab1913043020e70ee6664237016048c3ac535d2203
|
|
| MD5 |
d0cb576bb50d292b34533c0647a6d334
|
|
| BLAKE2b-256 |
ed77752ced5f7045cbd325d43721467c4f6643cc5824a6c07b2a66a680689564
|