Data & Docs · CONNECTIONExtract text from PDFs, scans, images and Office files at a public URL with LLMWhisperer OCR, then read the status, text, details, highlights and usage.
Explore 7 workflow actions for LLMWhisperer, including account permissions and operation limits.
Choose an action in the workflow builder, connect an account, and map its inputs. These actions are available in the catalog; your account access and a successful test determine whether they work for your setup.
Start extracting a public PDF, scan, image, Office file or spreadsheet's text with OCR and layout; poll Get status, then Get extracted text with the whisper_hash.
A repeated request may repeat the external action. Review the previous result before retrying a write.
An extraction's mode, page counts, file size, times and tag.
The extracted text with low-confidence words; LLMWhisperer returns it only once.
Bounding boxes of chosen lines in the original document (needs line numbers at extraction).
An extraction's status (accepted, processing, processed, error or retrieved) with each page's result.
The plan, quotas and pages processed by mode.
Pages processed per mode for one tag over a date range (the last 30 days by default).
Use the account and permissions required for your process. Review the connection check before configuring a workflow action.
Select a listed operation and map its required inputs. Use test records and add a human approval before writes that need review.
Inspect step outputs and confirm the result in LLMWhisperer. A saved workflow is not a completed provider action.
