Introduction
LLMWhisperer APIs are a set of APIs that allow you to:
- Convert your complex PDF documents and scanned documents to text format which can be used with LLMs
- Get bounding box details of search terms in the document. This can be used to highlight the search terms in your frontend application
The APIs are RESTful and can be easily integrated into your existing systems.
API Endpoints
| Endpoint | Description |
|---|---|
/whisper | Convert your PDF/Scanned documents to text format which can be used by LLMs |
/whisper-status | Get the status of the conversion process. This can be used to check the status of the conversion process when the conversion is done in async mode |
/whisper-retrieve | Retrieve the text of the document. This can be used to retrieve the text of the document when the conversion is done in async mode |
/highlight-data | Get bounding box details of search terms in the document. This can be used to highlight the search terms in your frontend application. This requires the conversion to be done with the store_metadata_for_highlighting parameter set to true |
/get-usage-info | Get usage metrics for your account. |
Base URL
The base URL for the APIs is https://llmwhisperer-api.unstract.com/v1
Authentication
All the APIs require an API key to be passed in the header. You can get your API key by signing up for LLMWhisperer. The API key is passed in the header as unstract-key.
Curl example:
curl -X GET --location 'https://llmwhisperer-api.unstract.com/v1/get-usage-info' \
-H 'unstract-key: <PASTE YOUR API KEY>'
Metering
The APIs are metered based on the number of pages processed. You can get the usage metrics by calling the /get-usage-info API endpoint.