Llmwhisperer | Composio Docs

Overview

SLUG: LLMWHISPERER

Description

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

Authentication Details

API Key

region

stringDefaults to us-centralRequired

generic_api_key

stringRequired

Connecting to Llmwhisperer

Create an auth config

Use the dashboard to create an auth config for the Llmwhisperer toolkit. This allows you to connect multiple Llmwhisperer accounts to Composio for agents to use.

Select App

Navigate to Llmwhisperer.

Configure Auth Config Settings

Select among the supported auth schemes of and configure them here.

Create and Get auth config ID

Click “Create Llmwhisperer Auth Config”. After creation, copy the displayed ID starting with ac_. This is your auth config ID. This is not a sensitive ID — you can save it in environment variables or a database. This ID will be used to create connections to the toolkit for a given user.

Connect Your Account

Using API Key

1 from composio import Composio
2 
3 # Replace these with your actual values
4 llmwhisperer_auth_config_id = "ac_YOUR_LLMWHISPERER_CONFIG_ID" # Auth config ID created above
5 user_id = "0000-0000-0000"  # UUID from database/app
6 
7 composio = Composio()
8 
9 def authenticate_toolkit(user_id: str, auth_config_id: str):
10     # Replace this with a method to retrieve an API key from the user.
11     # Or supply your own.
12     user_api_key = input("[!] Enter API key")
13 
14     connection_request = composio.connected_accounts.initiate(
15         user_id=user_id,
16         auth_config_id=auth_config_id,
17         config={"auth_scheme": "API_KEY", "val": {"generic_api_key": user_api_key}}
18     )
19 
20     # API Key authentication is immediate - no redirect needed
21     print(f"Successfully connected Llmwhisperer for user {user_id}")
22     print(f"Connection status: {connection_request.status}")
23     
24     return connection_request.id
25 
26 
27 connection_id = authenticate_toolkit(user_id, llmwhisperer_auth_config_id)
28 
29 # You can verify the connection using:
30 connected_account = composio.connected_accounts.get(connection_id)
31 print(f"Connected account: {connected_account}")

Tools

Executing tools

To prototype you can execute some tools to see the responses and working on the Llmwhisperer toolkit’s playground

For code examples, see the Tool calling guide and Provider examples.

Tool List

LLMWHISPERER_USAGE_GET_INFO

Tool Name: Get Usage Information

Description

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

Action Parameters

Action Response

data

objectRequired

error

successful

booleanRequired

LLMWHISPERER_USAGE_GET_STATS

Tool Name: Get Usage Statistics

Description

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.

Action Parameters

from_date

tag

stringRequired

to_date

Action Response

data

objectRequired

error

successful

booleanRequired

LLMWHISPERER_WEBHOOK_DELETE

Tool Name: Delete Webhook

Description

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

Action Parameters

webhook_name

stringRequired

Action Response

data

objectRequired

error

successful

booleanRequired

LLMWHISPERER_WEBHOOK_GET_DETAILS

Tool Name: Get Webhook Details

Description

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.

Action Parameters

webhook_name

stringRequired

Action Response

data

objectRequired

error

successful

booleanRequired

LLMWHISPERER_WEBHOOK_REGISTER

Tool Name: Register Webhook

Description

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. During registration, a test payload is sent to verify the webhook endpoint is functioning and returns HTTP 200.

Action Parameters

auth_token

stringRequired

url

stringRequired

webhook_name

stringRequired

Action Response

data

objectRequired

error

successful

booleanRequired

LLMWHISPERER_WEBHOOK_UPDATE

Tool Name: Update Webhook Configuration

Description

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.

Action Parameters

auth_token

string

url

stringRequired

webhook_name

stringRequired

Action Response

data

objectRequired

error

successful

booleanRequired

LLMWHISPERER_WHISPER_CHECK_STATUS

Tool Name: Check Whisper Status

Description

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.

Action Parameters

whisper_hash

stringRequired

Action Response

data

objectRequired

error

successful

booleanRequired

LLMWHISPERER_WHISPER_CONVERT_DOCUMENT

Tool Name: Convert Document to Text

Description

Tool to convert PDFs and scanned documents into LLM-optimized text format asynchronously. Use when you need to extract text from documents for LLM processing. After submission, use the returned whisper_hash to poll status and retrieve converted text. Either document_url (with url_in_post=true) or document_content must be provided.

Action Parameters

add_line_nos

document_content

document_url

file_name

gaussian_blur_radius

horizontal_stretch_factor

Defaults to 1

line_splitter_strategy

Defaults to left-priority

line_splitter_tolerance

Defaults to 0.4

mark_horizontal_lines

mark_vertical_lines

median_filter_size

mode

Defaults to form

output_mode

Defaults to layout_preserving

page_separator

Defaults to <<<

pages_to_extract

tag

url_in_post

use_webhook

webhook_metadata

Action Response

data

objectRequired

error

successful

booleanRequired

LLMWHISPERER_WHISPER_GET_DETAIL

Tool Name: Get Whisper Detail

Description

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.

Action Parameters

whisper_hash

stringRequired

Action Response

data

objectRequired

error

successful

booleanRequired

LLMWHISPERER_WHISPER_RETRIEVE_TEXT

Tool Name: Retrieve Whisper Text

Description

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.

Action Parameters

text_only

boolean

whisper_hash

stringRequired

Action Response

data

objectRequired

error

successful

booleanRequired