Data Extraction

Parseur

Learn how to use Parseur with Composio

Overview

SLUG: PARSEUR

Description

Parseur is an AI-powered data extraction tool that automates the parsing of emails, PDFs, and other documents into structured data.

Authentication Details

generic_api_key
stringRequired

Connecting to Parseur

Create an auth config

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

1

Select App

Navigate to Parseur.

2

Configure Auth Config Settings

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

3

Create and Get auth config ID

Click “Create Parseur 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

1from composio import Composio
2
3# Replace these with your actual values
4parseur_auth_config_id = "ac_YOUR_PARSEUR_CONFIG_ID" # Auth config ID created above
5user_id = "0000-0000-0000"  # UUID from database/app
6
7composio = Composio()
8
9def 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": user_api_key}
18    )
19
20    # API Key authentication is immediate - no redirect needed
21    print(f"Successfully connected Parseur for user {user_id}")
22    print(f"Connection status: {connection_request.status}")
23    
24    return connection_request.id
25
26
27connection_id = authenticate_toolkit(user_id, parseur_auth_config_id)
28
29# You can verify the connection using:
30connected_account = composio.connected_accounts.get(connection_id)
31print(f"Connected account: {connected_account}")

Tools

Executing tools

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

Python
1from composio import Composio
2from openai import OpenAI
3import json
4
5openai = OpenAI()
6composio = Composio()
7
8# User ID must be a valid UUID format
9user_id = "0000-0000-0000"  # Replace with actual user UUID from your database
10
11tools = composio.tools.get(user_id=user_id, toolkits=["PARSEUR"])
12
13print("[!] Tools:")
14print(json.dumps(tools))
15
16def invoke_llm(task = "What can you do?"):
17    completion = openai.chat.completions.create(
18        model="gpt-4o",
19        messages=[
20            {
21                "role": "user",
22                "content": task,  # Your task here!
23            },
24        ],
25        tools=tools,
26    )
27
28    # Handle Result from tool call
29    result = composio.provider.handle_tool_calls(user_id=user_id, response=completion)
30    print(f"[!] Completion: {completion}")
31    print(f"[!] Tool call result: {result}")
32
33invoke_llm()

Tool List

Tool Name: Create webhook

Description

Tool to create a new webhook in parseur. use when you need to send parsed data via http post in real time.

Action Parameters

category
stringDefaults to CUSTOM
event
stringRequired
headers
object
name
string
parser
integerRequired
parser_field
string
target
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Delete webhook

Description

Tool to delete a specific webhook. use when permanently removing a webhook after confirming its id.

Action Parameters

webhook_id
integerRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Enable webhook

Description

Tool to enable a paused webhook for a mailbox. use after confirming the webhook is correctly configured.

Action Parameters

mailbox_id
integerRequired
webhook_id
integerRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: List Documents in Mailbox

Description

Tool to list documents within a specific mailbox. use when you need to paginate, search, or sort the documents of a given mailbox after obtaining its id.

Action Parameters

mailbox_id
stringRequired
ordering
string
page
integerDefaults to 1
page_size
integerDefaults to 25
received_after
string
received_before
string
search
string
tz
string
with_result
boolean

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: List Mailboxes

Description

Tool to retrieve a list of all mailboxes. use when you need to browse or filter mailboxes via pagination, searching, or sorting.

Action Parameters

ordering
string
page
integerDefaults to 1
page_size
integerDefaults to 25
search
string

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: List Templates for Mailbox

Description

Tool to list all templates in a given mailbox. use after fetching mailbox details when you need to page through and inspect available templates for further actions.

Action Parameters

mailbox_id
stringRequired
ordering
string
page
integerDefaults to 1
page_size
integerDefaults to 25
search
string

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: List Webhooks for Mailbox

Description

Tool to list all webhooks for a mailbox. use when you need to retrieve both active and paused webhooks for a given mailbox.

Action Parameters

mailbox_id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Pause webhook

Description

Tool to pause (disable) an existing webhook. use when you need to stop sending parsed data via a webhook after confirming the correct mailbox and webhook ids.

Action Parameters

mailbox_id
integerRequired
webhook_id
integerRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Retrieve a webhook

Description

Tool to retrieve details of a specific webhook. use after creating or listing webhooks.

Action Parameters

mailbox_id
stringRequired
webhook_id
stringRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired

Tool Name: Update webhook

Description

Tool to update an existing webhook’s settings. use when you need to change the webhook’s target url, event type, headers, or name after creation.

Action Parameters

event
string
headers
object
name
string
parser_field
string
target
string
webhook_id
integerRequired

Action Response

data
objectRequired
error
string
successful
booleanRequired