LLMWhisperer

ai document extraction 11 tools available

LLMWhisperer is a technology that presents data from complex documents to LLMs in a way that they can best understand.

About this integration

Connect LLMWhisperer to Definable to automate repetitive tasks, sync data with the rest of your stack, trigger on real-world events. Personas call LLMWhisperer's 11 tools directly from chat or scheduled flows. You can wire it into any persona to read, write, and react when an event fires.

Connect LLMWhisperer to Definable and it becomes a set of typed tools your agents plan with — triggered by events, run on schedules, or invoked mid-conversation. Every write is checked by the verifier before it lands.

Auth OAuth2 · 2 clicks

Tools 11 exposed

Plans All, incl. Free

Data Never trained on

LLMWhisperer · in workflows

What teams actually run.

Three patterns teams run with LLMWhisperer on day one. Each one is a plain-English prompt — no canvas, no glue code — and you can remix them into anything.

Trigger on event

│ Listen for a new event

│ Parse and validate the payload

└ Take an action with the linked tool

Daily summary

│ Pull yesterday's activity

│ Summarise with the model of your choice

└ Send the digest via email or Slack

Cross-tool sync

│ Read records from one app

│ Transform with a persona

└ Write the result back via this integration

11 tools available

The LLMWhisperer toolbox.

Every LLMWhisperer capability your agents can call, each with a typed schema the planner reads. The router picks the right tool per step; the verifier checks the result.

Convert Document to Text (v2)

Tool to convert PDF/scanned documents to text format for LLM consumption. Supports file upload or URL processing with multiple modes (native_text, low_cost, high_quality, form, table). Use when you need to extract text from documents for LLM processing. Returns whisper_hash for status checking and text retrieval.

Get Highlights Metadata

Tool to get line metadata for highlighting extracted text in the original document. Returns bounding box coordinates (x, y, width, height) and page number for each line. Use when you need to create text overlays on document images or highlight specific lines in the source document.

Register Webhook

Tool to register a new webhook endpoint for LLMWhisperer async notifications. Use when you need to set up a callback URL to receive processing results. The webhook URL is validated during registration to ensure it's reachable.

Get Usage Information

Tool to check usage metrics of your LLMWhisperer account. Use when you need to monitor API consumption, verify quotas, or check remaining page limits.

Get Usage Statistics

Tool to retrieve usage statistics for your LLMWhisperer account based on a specific tag. Use when you need to check consumption metrics for a given tag and optional date range. Returns usage data for the preceding 30 days when date parameters are omitted.

Delete Webhook

Tool to delete a registered webhook from LLMWhisperer system. Use when you need to remove a webhook that is no longer needed.

Get Webhook Details

Tool to retrieve registered webhook details for LLMWhisperer. Use when you need to get the configuration of a specific webhook including its URL and authentication token.

Update Webhook Configuration

Tool to update an existing webhook configuration for document conversion callbacks. Use when you need to modify the callback URL, authentication token, or webhook identifier. The system validates the webhook by sending a test payload and requires a 200 status response.

Check Whisper Status

Tool to check the status of a text extraction process in LLMWhisperer. Use when the conversion is done in async mode to poll for completion status.

Get Whisper Detail

Tool to retrieve comprehensive details about ongoing or completed text extraction process. Use when you need to monitor the status and progress metrics of a text extraction job.

Retrieve Whisper Text

Tool to retrieve extracted text from asynchronous whisper processing. Use when the conversion process was initiated in async mode and you need to retrieve the results using the whisper_hash identifier. Note that retrieval is single-use for security - once retrieved, the same whisper_hash cannot be used again.

See it run

One prompt, start to finish.

A real prompt, the LLMWhisperer tools it calls, and what comes back. This is the whole interface — describe the outcome, agents handle the rest.

❯

Run a real LLMWhisperer task end-to-end — plan it, execute across the API, and hand back a verified result.

llmwhisperer.convert_document_to_text_v2 Tool to convert PDF/scanned documents to text format for LLM consumption. Supports file up

llmwhisperer.get_highlights_metadata Tool to get line metadata for highlighting extracted text in the original document. Return

llmwhisperer.register_webhook Tool to register a new webhook endpoint for LLMWhisperer async notifications. Use when you · verified

done

Done. LLMWhisperer responded across 3 calls, the verifier signed off, and the result is logged with every payload.

FAQ · LLMWhisperer

Questions, answered.

What teams ask before connecting LLMWhisperer.

01 What can I automate with LLMWhisperer on Definable?

Anything LLMWhisperer exposes through its API. Common ai document extraction workflows on Definable include automate repetitive tasks, sync data with the rest of your stack, trigger on real-world events. Personas can call any of the 11 LLMWhisperer tools directly, then chain the result into another integration without you writing code.

02 How does LLMWhisperer authentication work?

LLMWhisperer uses API_KEY on Definable. You connect once from the integrations page, scoped to the permissions you choose, and from then on any persona that has the integration enabled can act on your behalf. Tokens are encrypted at rest and rotated automatically.

03 Is the LLMWhisperer integration included in my Definable plan?

Yes — every Definable plan, including Starter, includes access to all 11 LLMWhisperer tools. You only need a separate LLMWhisperer subscription if LLMWhisperer itself charges per seat or per API call.

04 Is using LLMWhisperer through Definable secure?

Every call from a persona to LLMWhisperer is logged with the user, persona, prompt, and response. Tokens never leave Definable's secrets vault, scopes are configurable per persona, and you can revoke access at any time from the integration page.

05 How do I get started with LLMWhisperer on Definable?

Sign up for Definable, open the integrations page, find LLMWhisperer, and connect via OAuth or API key. You can immediately attach LLMWhisperer to any persona and start running workflows. The free Starter plan includes 5,000 credits/month.

06 What LLMWhisperer actions does Definable expose?

Definable exposes all 11 LLMWhisperer actions as callable tools — including `Convert Document to Text (v2)`, `Get Highlights Metadata`, `Register Webhook`, plus 8 more. Each tool gets a typed parameter schema so personas know exactly how to call it.