LLMs are powerful, but their output is as good as the input you provide. LLMWhisperer is a technology that presents data from complex documents (different designs and formats) to LLMs in a way that they can best understand. LLMWhisperer features include Layout Preserving Mode, Auto-switching between native text and OCR modes, proper representation of radio buttons and checkboxes in PDF forms as raw text, among other features. You can now extract raw text from complex PDF documents or images without having to worry about whether the document is a native text document, a scanned image or just a picture clicked on a smartphone. Extraction of raw text from invoices, purchase orders, bank statements, etc works easily for structured data extraction with LLMs powered by LLMWhisperer's Layout Preserving mode.
Refer to the client documentation for more information: LLMWhisperer Client Documentation
This package provides LLMWhispererClientV2, the client for LLMWhisperer API v2. It is required for all users on API version 2.0.0 and above.
Documentation is available here.
Install test dependencies and run all tests:
uv run --group test pytestTo run only unit tests (skipping integration tests):
uv run --group test pytest tests/unit tests/utils_test.pyTo run only integration tests:
uv run --group test pytest tests/integrationIntegration tests require a valid API key. Copy sample.env to .env and fill in your credentials before running them.
On Slack, join great conversations around LLMs, their ecosystem and leveraging them to automate the previously unautomatable!
LLMWhisperer Playground: Test drive LLMWhisperer with your own documents. No sign up needed!
LLMWhisperer developer documentation and playground: Learn more about LLMWhisperer and its API.