Nano nets | Composio Docs

Overview

SLUG: NANO_NETS

Description

Nanonets provides an AI-driven Intelligent Document Processing API that transforms unstructured documents into structured data, enabling efficient data extraction and workflow automation.

Authentication Details

API Key

basic_encoded

stringRequired

Connecting to Nano nets

Create an auth config

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

Select App

Navigate to [Nano nets](https://platform.composio.dev?next_page=/marketplace/Nano nets).

Configure Auth Config Settings

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

Create and Get auth config ID

Click “Create Nano nets 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 nano_nets_auth_config_id = "ac_YOUR_NANO_NETS_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 Nano nets 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, nano_nets_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 [Nano nets toolkit’s playground](https://app.composio.dev/app/Nano nets)

OpenAI (Python)

Anthropic (TypeScript)

Google (Python)

Vercel (TypeScript)

Python

1 from composio import Composio
2 from openai import OpenAI
3 import json
4 
5 openai = OpenAI()
6 composio = Composio()
7 
8 # User ID must be a valid UUID format
9 user_id = "0000-0000-0000"  # Replace with actual user UUID from your database
10 
11 tools = composio.tools.get(user_id=user_id, toolkits=["NANO_NETS"])
12 
13 print("[!] Tools:")
14 print(json.dumps(tools))
15 
16 def 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 
33 invoke_llm()

Tool List

NANO_NETS_CREATE_MODEL

Tool Name: Create OCR Model

Description

Tool to create a new ocr model. use when you need to initialize an ocr model before training.

Action Parameters

NANO_NETS_DELETE_MODEL

Tool Name: Delete OCR Model

Description

Tool to delete an ocr model. use when you need to permanently remove a trained model by its id.

Action Parameters

model_id

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

NANO_NETS_GET_ALL_MODELS

Tool Name: Get all OCR models

Description

Tool to retrieve a paginated list of all ocr models. use when you need to inspect or manage existing ocr models. call after authentication to fetch your account's models.

Action Parameters

page

integer

page_size

integer

Action Response

data

objectRequired

error

string

successful

booleanRequired

NANO_NETS_GET_ALL_PREDICTION_FILES

Tool Name: Get All Prediction Files

Description

Tool to fetch all prediction files associated with a specific model. use when you need to list all inference requests after model processing is complete.

Action Parameters

limit

integerDefaults to 50

model_id

stringRequired

page

integerDefaults to 1

Action Response

data

objectRequired

error

string

successful

booleanRequired

NANO_NETS_GET_MODEL_DETAILS

Tool Name: Get OCR Model Details

Description

Tool to retrieve details of an ocr model. use when you need full metadata of a model by its id.

Action Parameters

model_id

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

NANO_NETS_GET_TRAINING_IMAGES

Tool Name: Get OCR Training Images

Description

Tool to retrieve training images for an ocr model. use when you need to page through images associated with a model before training or analysis.

Action Parameters

model_id

stringRequired

page

integerDefaults to 1

page_size

integerDefaults to 50

Action Response

data

objectRequired

error

string

successful

booleanRequired

NANO_NETS_GET_WORKFLOWS

Tool Name: Get Workflows

Description

Tool to retrieve a list of all workflows in your nanonets account. use when you need to inventory or inspect all configured workflows.

Action Parameters

Action Response

data

objectRequired

error

string

successful

booleanRequired

NANO_NETS_LIST_DOCUMENTS

Tool Name: List Workflow Documents

Description

Tool to retrieve a paginated list of documents processed by a workflow. use when you need to view documents after processing.

Action Parameters

limit

integer

page

integer

workflow_id

stringRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired

NANO_NETS_UPDATE_MODEL

Tool Name: Update OCR Model

Description

Tool to update an ocr model's details. use after reviewing the model's current configuration to modify its name, categories, notes, or classification settings.

Action Parameters

NANO_NETS_UPLOAD_TRAINING_IMAGES_BY_FILE

Tool Name: Upload Training Images by File

Description

Tool to upload training images by file to a specified ocr model. use when adding files to a model for training purposes.

Action Parameters

annotation

string

NANO_NETS_UPLOAD_TRAINING_IMAGES_BY_URL

Tool Name: Upload Training Images by URL

Description

Tool to upload training images by url to a specified ocr model. use when adding urls of images to a model for training purposes.

Action Parameters

model_id

stringRequired

urls

arrayRequired

Action Response

data

objectRequired

error

string

successful

booleanRequired