AI-Powered, Fast, Reliable and Accurate Invoice OCR and Receipt OCR API for Seamless Integration
AI-Powered, Fast, Reliable and Accurate Invoice OCR and Receipt OCR API for Seamless Integration On Nagent, Eagle doc is exposed as a fully-configurable ai document extraction integration that any agent can call — 10 actions, and API key authentication. No code is required to wire Eagle doc into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Eagle doc 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 Eagle doc 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 Eagle doc, with input parameters and output schema. Drop these into any step of an agent built in Helix.
EAGLE_DOC_ANY_DOC_OCRTool to process any document type with OCR and automatic classification. Supports bank statements, resumes, passports, delivery sheets, and more. Use when you need to extract structured data from various document types.
Input parameters
Document file to process (PNG, JPG, TIF, or PDF).
Specify document type for targeted extraction. If not provided, the system will automatically classify the document type.
Privacy setting. Default true (file not stored on server). Set to false to store files.
Custom extraction configuration ID for tailored extraction rules.
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
EAGLE_DOC_BATCH_ANY_DOC_OCRTool to submit batch OCR processing tasks for various document types including bank statements, resumes, passports, delivery sheets, and more. Use when you need to asynchronously process documents with custom configurations. The task is processed asynchronously; use the Results Check API with the returned task ID to monitor status and retrieve results.
Input parameters
Document file to process. Supports png, jpg, tif, or PDF formats including multi-page documents.
Privacy setting. Set to false to allow file storage for algorithm enhancement. Defaults to true (files are not stored).
Predefined document type for optimized OCR results. Specify the document type to improve extraction accuracy. If not provided, the system will auto-detect the document type.
Direct URL to download the document file from. Alternative to providing a file directly. Useful when the file is available at a public URL.
Custom extraction configuration ID for specialized extraction needs. Use when you have a predefined configuration for specific document processing requirements.
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
EAGLE_DOC_BATCH_TASK_DELETETool to delete a submitted batch processing task from the queue. Use when you need to cancel or remove a previously submitted batch OCR task before processing completes.
Input parameters
ID of the task received when documents were submitted for batch processing. This task will be removed from the queue.
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
EAGLE_DOC_INVOICE_OCR_BASE64Tool to extract invoice data from base64 encoded images using Eagle Doc OCR API. Use when you need to process invoice images that are already base64 encoded. Supports optional parameters for privacy control, coordinate extraction, and full text extraction.
Input parameters
If true, returns coordinate data (polygon) for each extracted field, indicating the position of the field on the page. Default is false.
Controls server storage of the document. If true, the document is not stored on the server (default). If false, it may be stored for algorithm improvement purposes.
If true, provides full text extraction line-by-line for each page of the document. Default is false.
Base64 encoded invoice image or document string. Must be a valid base64 string representing the image file.
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
EAGLE_DOC_MANAGEMENT_QUOTATool to get contractual quota allowance and current usage counters for all workloads. Use when you need to check remaining capacity for dashboards or billing workflows.
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
EAGLE_DOC_RECEIPT_OCR_V3Tool to process receipt images into structured JSON with 40+ fields including merchant info, line items, taxes, and payments. Use when extracting detailed data from receipt images or PDFs.
Input parameters
Receipt image or multi-page PDF file.
If true, prioritizes speed over accuracy with selective LLM enhancement.
If true, returns coordinate data for drawing polygons around extracted text.
If true (default), file is not stored. If false, file may be stored for algorithm improvement.
Direct URL to download the receipt file from. Alternative to providing a file directly. Useful when the file is available at a public URL.
If true, returns full unstructured text array per page.
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
EAGLE_DOC_RECEIPT_QUOTA_V2Tool to get quota information for receipt processing API v2 (deprecated). Use when you need to check available quota and usage for receipt OCR processing. Note: Multi-page receipts count each page as one request.
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
EAGLE_DOC_USAGE_CURRENT_MONTHTool to get current month's usage statistics including quota, pages processed, over-usage, and costs. Use when you need to check API usage and billing information for the current billing period.
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
EAGLE_DOC_USAGE_MONTHLY_HISTORYTool to retrieve historical monthly usage data with pricing context for reconciliation and forecasting. Use when you need to analyze page processing trends or calculate costs.
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
EAGLE_DOC_USAGE_REQUEST_LOGSTool to retrieve chronological list of recent API calls with page counts and timestamps. Use for troubleshooting and auditing consumption patterns.
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 35 agents privately built on Nagent that already use Eagle doc.
Build on Nagent
Connect Eagle doc 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 Eagle doc, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Eagle doc is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Eagle doc is connected, you configure its 10 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Eagle doc 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 Eagle doc event fires, the agent kicks off automatically.
Every Eagle doc 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 Eagle doc ships with 10 pre-built ai document extraction actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Eagle doc together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Eagle doc-based workflows tailored to your business.