Metadata-Version: 2.3
Name: linked-claims-extractor
Version: 0.1.1
Summary: Extract structured claims from text and PDFs
Project-URL: homepage, https://github.com/Cooperation-org/linked-claims-extractor
Project-URL: bug_tracker, https://github.com/Cooperation-org/linked-claims-extractor/issues
Author-email: Golda Velez <gvelez17@gmail.com>
License: MIT
License-File: LICENSE
Classifier: License :: OSI Approved :: MIT License
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.8
Requires-Dist: langchain-anthropic>=0.2.4
Requires-Dist: langchain-community>=0.0.10
Requires-Dist: langchain>=0.1.0
Requires-Dist: openai>=1.0.0
Requires-Dist: pdfminer-six>=20221105
Requires-Dist: pypdf>=3.0.0
Requires-Dist: pytest>=7.0.0
Requires-Dist: python-dotenv>=1.0.0
Requires-Dist: requests>=2.25.0
Description-Content-Type: text/markdown

# linked-claims-extractor
Extract claims from text, url or pdf using AI LLMs to help

## Installation and Usage

`pip install linked-claims-extractor`

Default is to use Anthropic which requires setting
`export ANTHROPIC_API_KEY=...`

```
from claim_extractor import ClaimExtractor

extractor = ClaimExtractor()
# or extractor = ClaimExtractor(llm=your_llm, schema=schema_from_list)

result = extractor.extract_claims('some text')

pprint(json.loads(result))
```

## Developer Environment

This project uses pyproject.toml for dependencies

```
python -m venv .venv
. .venv/bin/activate
pip install -e .
```

## Testing and Debugging

```
pytest -s --pdb
```
