Taggun is an AI-powered receipt OCR API that extracts structured data from receipt and invoice images in real-time. It supports 85+ languages, fraud detection, and automated expense tracking.
Taggun is an AI-powered receipt OCR API that extracts structured data from receipt and invoice images in real-time. It supports 85+ languages, fraud detection, and automated expense tracking. On Nagent, Taggun is exposed as a fully-configurable ai document extraction integration that any agent can call — 14 actions, and API key authentication. No code is required to wire Taggun into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Taggun to automate the kinds of tasks ai document extraction teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Taggun into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Taggun, with input parameters and output schema. Drop these into any step of an agent built in Helix.
TAGGUN_ADD_MERCHANT_NAMETool to add a merchant name keyword to your account's model for predicting merchant names. Use when you want to improve merchant name recognition by training the model with specific merchant names. Changes to your account's model are updated daily and will affect future receipt processing.
Input parameters
Merchant name keyword to add to your account's model for predicting merchant names. The model updates are applied daily.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_EXPORT_KNOWN_MERCHANTSExport the complete list of known merchants used for merchant name normalization in Taggun. Returns CSV data with merchant details including location IDs, names, addresses, and coordinates. Use this when you need to retrieve the full merchant registry for synchronization, auditing, or analysis. No parameters required - this is a read-only GET operation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_EXPORT_KNOWN_PRODUCT_CODESExport the complete list of known product codes used for product normalization and matching in Taggun. Returns CSV data with product code information. Use this when you need to retrieve the full product code registry for synchronization, auditing, or analysis. No parameters required - this is a read-only GET operation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_EXPORT_PRODUCT_CATEGORIESExport a list of product categories and descriptions used for product categorization in CSV format. Returns CSV data with product category information for analysis or synchronization purposes. Use this when you need to retrieve the complete product category registry.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_GENERATE_MERCHANTS_CSVGenerate a CSV file with mock merchant data for testing purposes. Creates a temporary CSV file with the specified number of merchant rows, including fields like name, alias, address, coordinates, contact info, and tags. Use this when you need sample merchant data for bulk import operations or testing merchant-related API endpoints. The generated CSV follows a standard format with 10 columns: name, alias, address, postcode, lat, lng, country, phone, email, tags.
Input parameters
Number of merchant rows to generate in the CSV
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_IMPORT_KNOWN_MERCHANTSImport a list of merchant names and addresses to normalize and match in CSV or TSV format. Use this when you need to bulk upload merchant data for name normalization and matching. File must be less than 20MB and contain merchant information in CSV or TSV format.
Input parameters
CSV or TSV file containing merchant data to import. Must be less than 20MB. File should have columns for merchant names and addresses.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_IMPORT_KNOWN_PRODUCT_CODESTool to import a list of product codes in CSV or TSV format for normalization and matching. Use when you need to upload product code data to Taggun for receipt/invoice processing. The file should contain product codes with descriptions (e.g., code,description columns).
Input parameters
CSV or TSV file containing product codes to import. File must be less than 20MB and contain product code data with columns like 'code' and 'description'. Accepted formats: CSV, TSV. If not provided, you may use raw_content instead.
Inline CSV or TSV file content to upload as bytes or UTF-8 string.
Filename for the inline content (e.g., 'product_codes.csv'). Defaults to 'product_codes.csv'.
MIME type for the inline content (e.g., 'text/csv', 'text/tab-separated-values'). Defaults to text/csv.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_IMPORT_PRODUCT_CATEGORIESImport a list of product categories and descriptions for product categorization. Accepts CSV or TSV files (less than 20MB) with category and description columns. Use this when you need to bulk import product category data for matching during receipt processing.
Input parameters
CSV or TSV file containing product categories and descriptions. File must be less than 20MB. Format: category,description. If not provided, you may use raw_content instead.
Inline CSV or TSV file content to upload as bytes or UTF-8 string.
Filename for the inline content (e.g., 'categories.csv'). Defaults to 'categories.csv'.
MIME type for the inline content (e.g., 'text/csv', 'text/tab-separated-values'). Defaults to text/csv.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_TRANSCRIBE_RECEIPT_ENCODED_SIMPLEExtract structured data from a receipt or invoice using base64 encoded image data. Provide a base64 encoded image (JPEG, PNG, PDF, GIF) along with filename and content type to get back extracted fields like total amount, date, merchant name, tax, line items, and confidence scores. Use this when you have receipt/invoice image data already encoded as base64 and need to digitize the data. The API uses machine learning OCR to detect and extract key fields automatically.
Input parameters
Base64 encoded image data of the receipt or invoice. Supported formats: JPEG, PNG, PDF, GIF. The string should contain only the base64-encoded data without any data URI prefix.
Set to true to bypass Taggun's cache and force fresh OCR processing of the image. Default is false (uses cached results if available).
Filename for reference purposes (e.g., 'receipt.jpg'). Required for proper processing.
Set language as a hint for OCR processing. Leave empty for auto detect. Supported languages: en, es, fr, jp, he, iw, et, lv, lt, fi, el, zh, th, ar
Set true to avoid saving the receipt in storage for privacy purposes. Default is false.
IP Address of the end user for fraud detection purposes
Tag a request with a container ID for fraud detection purposes. Maximum 50 characters.
MIME type of the image file. Required. Supported types: 'image/jpeg', 'image/png', 'application/pdf', 'image/gif'.
Set true to return time if found on the receipt. Otherwise, the time is always set to 12:00:00.000. Default is false.
Ignore this merchant name if detected on the receipt. Use this field to avoid detecting the customer name as the merchant name.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_TRANSCRIBE_RECEIPT_ENCODED_VERBOSETool to transcribe a receipt using base64 encoded image in JSON payload and return detailed results. Use when you have a base64 encoded receipt image and require comprehensive output including line items, merchant details, and confidence levels. The image must be larger than 1x1 pixels to avoid validation errors.
Input parameters
Base64 encoded receipt image. Must meet minimum size requirements (larger than 1x1 pixels).
Set true to force re-process image transcription if receipt is already in storage.
The filename for the receipt image.
Set true to avoid saving the receipt in storage.
Tag a request with a container ID for fraud detection purposes.
MIME type of the image (e.g., image/jpeg, image/png).
Set true to return time if found on the receipt. Otherwise, the time is always set to 12:00:00.000.
Set true to return product line items in an array if found on the receipt.
Ignore this merchant name if detected on the receipt. Use this field to avoid detecting the customer name as the merchant name.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_TRANSCRIBE_RECEIPT_FILE_SIMPLETool to upload a receipt or invoice image file and extract basic data including merchant name, total amount, tax amount, and date. Use when you need to digitize receipt data from a file (PDF, JPG, PNG, GIF, HEIC up to 20MB). The API uses OCR to detect and extract key fields.
Input parameters
Receipt or invoice image file to upload (less than 20MB). Supported formats: PDF, JPG, PNG, GIF, HEIC.
A geo location to search for merchant. Typically in the format of city, state, country.
Tag a request with a user ID so that duplicate receipts by the same user can be detected
Set true to force re-process image transcription if the receipt is already in storage. Default is false.
Supported languages for receipt OCR processing.
Set true to avoid saving the receipt in storage. Default is false.
IP Address of the end user for fraud detection purposes
Tag a request with a container ID for fraud detection purposes
Set true to return time if found on the receipt. Otherwise, the time is always set to 12:00:00.000. Default is false.
Tag a request with a unique reference ID for feedback/training and receipt similarity check purposes
Tag a request with sub-account ID for billing purposes
Ignore this merchant name if detected on the receipt. Use this field to avoid detecting the customer name as the merchant name.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_URLExtract structured data from a receipt or invoice image using OCR. Provide a public URL to a receipt/invoice image (JPEG, PNG, PDF, GIF) and get back extracted fields like total amount, date, merchant name, tax, line items, and confidence scores. Use this when you need to digitize receipt/invoice data from a publicly accessible image URL. The API uses machine learning OCR to detect and extract key fields automatically.
Input parameters
Public HTTPS URL of the receipt/invoice image. Supported formats: JPEG, PNG, PDF, GIF. URL must be publicly accessible and point directly to the image file.
Set to true to bypass Taggun's cache and force fresh OCR processing of the image. Default is false (uses cached results if available).
Optional filename for reference purposes (e.g., 'receipt.jpg'). Does not affect processing.
Optional MIME type of the image file (e.g., 'image/jpeg', 'image/png', 'application/pdf'). Auto-detected if not provided.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_URL_VALIDATIONTool to extract and validate receipt data from a URL. Processes a receipt image from a public URL and returns extracted fields with confidence levels to assess receipt authenticity. Use when you have a receipt URL and need to verify it contains valid receipt data.
Input parameters
The URL of the receipt image to be validated.
Optional filename to assign to the image.
If true, the receipt will not be saved in the database.
An external ID to link with the validation for tracking purposes.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
TAGGUN_URL_VERBOSETool to process a receipt or invoice from a URL for detailed data extraction. Use when you have a publicly accessible receipt or invoice URL and require comprehensive output including line items, merchant details, and confidence metrics. Call after verifying the URL is reachable.
Input parameters
Publicly accessible URL of the receipt or invoice image.
Location hint (city, state, country) for merchant search.
If true, forces reprocessing even if cached results exist.
Language hint for OCR (supports: en, es, fr, jp, he, iw, et, lv, lt, fi, el, zh, th).
If true, excludes this document from Taggun's learning dataset.
End-user IP address for fraud assessment.
Return extracted time; defaults to 12:00:00.000 if not found.
Unique reference ID for feedback tracking.
Tag request for billing purposes.
Set true to return product line items in an array if found.
Merchant name to exclude from detection.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 70 agents privately built on Nagent that already use Taggun.
Build on Nagent
Connect Taggun to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Taggun, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Taggun is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Taggun is connected, you configure its 14 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Taggun steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Taggun event fires, the agent kicks off automatically.
Every Taggun action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Taggun ships with 14 pre-built ai document extraction actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Taggun together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Taggun-based workflows tailored to your business.